To deal with the global and regional issues including food security, climate change, land degradation, biodiversity loss, water resource management, and ecosystem health, detailed accurate spatial soil information is ...To deal with the global and regional issues including food security, climate change, land degradation, biodiversity loss, water resource management, and ecosystem health, detailed accurate spatial soil information is urgently needed. This drives the worldwide development of digital soil mapping. In recent years, significant progresses have been made in different aspects of digital soil mapping. The main purpose of this paper is to provide a review for the major progresses of digital soil mapping in the last decade. First, we briefly described the rise of digital soil mapping and outlined important milestones and their influence, and main paradigms in digital soil mapping. Then, we reviewed the progresses in legacy soil data, environmental covariates, soil sampling, predictive models and the applications of digital soil mapping products. Finally, we summarized the main trends and future prospect as revealed by studies up to now. We concluded that although the digital soil mapping is now moving towards mature to meet various demands of soil information, challenges including new theories, methodologies and applications of digital soil mapping, especially for highly heterogeneous and human-affected environments, still exist and need to be addressed in the future.展开更多
Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not avail...Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not available for those situations with limited samples.To solve the problem,this paper proposed a case-based method which could formalize the covariate selection knowledge contained in practical DSM applications.The proposed method trained Random Forest(RF)classifiers with DSM cases extracted from the practical DSM applications and then used the trained classifiers to determine whether each one potential covariate should be used in a new DSM application.In this study,we took topographic covariates as examples of covariates and extracted 191 DSM cases from 56 peer-reviewed journal articles to evaluate the performance of the proposed case-based method by Leave-One-Out cross validation.Compared with a novices’commonly-used way of selecting DSM covariates,the proposed case-based method improved more than 30%accuracy according to three quantitative evaluation indices(i.e.,recall,precision,and F1-score).The proposed method could be also applied to selecting the proper set of covariates for other similar geographical modeling domains,such as landslide susceptibility mapping,and species distribution modeling.展开更多
The use of landscape covariates to variability of soil properties in similar estimate soil properties is not suitable topographic and vegetation conditions. for the areas of low relief due to the high A new method wa...The use of landscape covariates to variability of soil properties in similar estimate soil properties is not suitable topographic and vegetation conditions. for the areas of low relief due to the high A new method was implemented to map regional soil texture （in terms of sand, silt and clay contents） by hypothesizing that the change in the land surface diurnal temperature difference （DTD） is related to soil texture in case of a relatively homogeneous rainfall input. To examine this hypothesis, the DTDs from moderate resolution imagine spectroradiometer （MODIS） during a selected time period, i.e., after a heavy rainfall between autumn harvest and autumn sowing, were classified using fuzzy-c-means （FCM） clustering. Six classes were generated, and for each class, the sand （〉 0.05 mm）, silt （0.002-0.05 mm） and clay （〈 0.002 mm） contents at the location of maximum membership value were considered as the typical values of that class. A weighted average model was then used to digitally map soil texture. The results showed that the predicted map quite accurately reflected the regional soil variation. A validation dataset produced estimates of error for the predicted maps of sand, silt and clay contents at root mean of squared error values of 8.4%, 7.8% and 2.3%, respectively, which is satisfactory in a practical context. This study thus provided a methodology that can help improve the accuracy and efficiency of soil texture mapping in plain areas using easily available data sources.展开更多
The Soil Land Inference Model(SoLIM) was primarily proposed by Zhu et al.(Zhu A X, Band L, Vertessy R, Dutton B. 1997. Derivation of soil properties using a soil land inference model(SoLIM). Soil Sci Soc Am J. 61: 523...The Soil Land Inference Model(SoLIM) was primarily proposed by Zhu et al.(Zhu A X, Band L, Vertessy R, Dutton B. 1997. Derivation of soil properties using a soil land inference model(SoLIM). Soil Sci Soc Am J. 61: 523–533.) and was based on the Third Law of Geography. Based on the assumption that the soil property value at a location of interest will be more similar to that of a given soil sample when the environmental condition at the location of interest is more similar to that at the location from which the sample was taken, SoLIM estimates the soil property value of the location of interest using the soil property values of known samples weighted by the similarity between those samples and the location of interest in terms of an attribute domain of environmental conditions. However, the current SoLIM method ignores information about the spatial distances between the location of interest and those of the sample. In this study, we proposed a new method of soil property mapping, So LIM-IDW, which incorporates spatial distance information into the SoLIM method by means of inverse distance weighting(IDW). The proposed method is based on the assumption that the soil property value at a location of interest will be more similar to that of a known sample both when the environmental conditions are more similar and when the distance between the location of interest and the sample location is shorter. Our evaluation experiments on A-horizon soil organic matter mapping in two study areas with independent evaluation samples showed that the proposed SoLIM-IDW method can obtain lower prediction errors than the original SoLIM method, multiple linear regression, geographically weighted regression, and regression-kriging with the same modeling points. Future work mainly includes the determination of optimal power parameter values and the appropriate setting of the parameter under different application contexts.展开更多
Spatial distribution of soil salinity can be estimated based on its environmental factors because soil salinity is strongly affected and indicated by environmental factors. Different with other properties such as soil...Spatial distribution of soil salinity can be estimated based on its environmental factors because soil salinity is strongly affected and indicated by environmental factors. Different with other properties such as soil texture, soil salinity varies with short-term time. Thus, how to choose powerful environmental predictors is especially important for soil salinity. This paper presents a similarity-based prediction approach to map soil salinity and detects powerful environmental predictors for the Huanghe(Yellow) River Delta area in China. The similarity-based approach predicts the soil salinities of unsampled locations based on the environmental similarity between unsampled and sampled locations. A dataset of 92 points with salt data at depth of 30–40 cm was divided into two subsets for prediction and validation. Topographical parameters, soil textures, distances to irrigation channels and to the coastline, land surface temperature from Moderate Resolution Imaging Spectroradiometer(MODIS), Normalized Difference Vegetation Indices(NDVIs) and land surface reflectance data from Landsat Thematic Mapper(TM) imagery were generated. The similarity-based prediction approach was applied on several combinations of different environmental factors. Based on three evaluation indices including the correlation coefficient(CC) between observed and predicted values, the mean absolute error and the root mean squared error we found that elevation, distance to irrigation channels, soil texture, night land surface temperature, NDVI, and land surface reflectance Band 5 are the optimal combination for mapping soil salinity at the 30–40 cm depth in the study area(with a CC value of 0.69 and a root mean squared error value of 0.38). Our results indicated that the similarity-based prediction approach could be a vital alternative to other methods for mapping soil salinity, especially for area with limited observation data and could be used to monitor soil salinity distributions in the future.展开更多
Due to the almost homogeneous topography in low relief areas, it is usually difficult to make accurate predictions of soil properties using topographic covariates. In this study, we examined how time series of field s...Due to the almost homogeneous topography in low relief areas, it is usually difficult to make accurate predictions of soil properties using topographic covariates. In this study, we examined how time series of field soil moisture observations can be used to estimate soil texture in an oasis agricultural area with low relief in the semi-arid region of northwest China. Time series of field-observed soil moisture variations were recorded for 132 h beginning at the end of an irrigation event during which the surface soil was saturated.Spatial correlation between two time-adjacent soil moisture conditions was used to select the factors for fuzzy c-means clustering. In each of the ten generated clusters, soil texture of the soil sample with the maximum fuzzy membership value was taken as the cluster centroid. Finally, a linearly weighted average was used to predict soil texture from the centroids. The results showed that soil moisture increased with the increase of clay and silt contents, but decreased with the increase of sand content. The spatial patterns of soil moisture changed during the entire soil drying phase. We assumed that these changes were mainly caused by spatial heterogeneity of soil texture. A total of 64 independent samples were used to evaluate the prediction accuracy. The root mean square error(RMSE)values of clay, silt and sand were 1.63, 2.81 and 3.71, respectively. The mean relative error(RE) values were 9.57% for clay, 3.77% for silt and 12.83% for sand. It could be concluded that the method used in this study was effective for soil texture mapping in the low-relief oasis agricultural area and could be applicable in other similar irrigation agricultural areas.展开更多
Soil type maps at the scale of I Z 1 000 000 are used extensively to provide soil spatial distribution information for soil erosion assessment and watershed management models in China. However, the soil property maps ...Soil type maps at the scale of I Z 1 000 000 are used extensively to provide soil spatial distribution information for soil erosion assessment and watershed management models in China. However, the soil property maps produced through conventional direct linking method usually suffer low accuracy as well as the lack of spatial details within a soil type polygon. This paper presents an effective method to produce detailed soil property map based on representative samples which were extracted from each polygon on the 1 ： 1 000 000 soil type map. The representative sample of each polygon is defined as the location that can represent the largest area within the polygon. The representativeness of a candidate sample is determined by calculating the soil-forming environment condition similarities between the sample and other locations. Once the representative sample of each polygon has been chosen, the property values of the existing typical samples are assigned to the corresponding representative samples with the same soil type. Finally, based on these representative samples, the detailed soil property map could be produced by using existing digital soil mapping methods. The case study in XuanCheng City, Anhui Province of China, demonstrated the proposed method could produce soil property map at a higher level of spatial details and accuracy： 1） The soil organic matter （SOM） map produced based on the representative samples can not only depict the detailed spatial distribution of SOM within a soil type polygon but also largely reduce the abrupt change of soil property at the boundaries of two adjacent polygons. 2） The Root Mean Squared Error （RMSE） of the SOM map based on the representative samples is 1.61, and it is 1.37 for the SOM map produced by using conventional direct linking method. Therefore, the proposed method is an effective approach to produce spatial detailed soil property map with higher accuracy for environment simulation models.展开更多
Detailed knowledge about the estimates and spatial patterns of soil organic carbon(SOC) and total nitrogen(TN) stocks is fundamental for sustainable land management and climate change mitigation.This study aimed at:(1...Detailed knowledge about the estimates and spatial patterns of soil organic carbon(SOC) and total nitrogen(TN) stocks is fundamental for sustainable land management and climate change mitigation.This study aimed at:(1) mapping the spatial patterns,and(2) quantifying SOC and TN stocks to 30 cm depth in the Eastern Mau Forest Reserve using field,remote sensing,geographical information systems(GIS),and statistical modelling approaches.This is a critical ecosystem offering essential services,but its sustainability is threatened by deforestation and degradation.Results revealed that elevation,silt content,TN concentration,and Landsat 8 Operational Land Imager band 11 explained 72% of the variability in SOC stocks,while the same factors(except silt content) explained 71% of the variability in TN stocks.The results further showed that soil properties,particularly TN and SOC concentrations,were more important than that other environmental factors in controlling the observed patterns of SOC and TN stocks,respectively.Forests stored the highest amounts of SOC and TN(3.78 Tg C and 0.38 Tg N) followed by croplands(2.46 Tg C and 0.25 Tg N) and grasslands(0.57 Tg C and 0.06 Tg N).Overall,the Eastern Mau Forest Reserve stored approximately 6.81 Tg C and 0.69 Tg N.The highest estimates of SOC and TN stocks(hotspots) occurred on the western and northwestern parts where forests dominated,while the lowest estimates(coldspots) occurred on the eastern side where croplands had been established.Therefore,the hotspots need policies that promote conservation,while the coldspots need those that support accumulation of SOC and TN stocks.展开更多
Soil salinization is one of the most important causes of land degradation and desertification,especially in arid and semi-arid areas.The dynamic monitoring of soil salinization is of great significance to land managem...Soil salinization is one of the most important causes of land degradation and desertification,especially in arid and semi-arid areas.The dynamic monitoring of soil salinization is of great significance to land management,agricultural activities,water quality,and sustainable development.The remote sensing images taken by the synthetic aperture radar(SAR)Sentinel-1 and the multispectral satellite Sentinel-2 with high resolution and short revisit period have the potential to monitor the spatial distribution of soil attribute information on a large area;however,there are limited studies on the combination of Sentinel-1 and Sentinel-2 for digital mapping of soil salinization.Therefore,in this study,we used topography indices derived from digital elevation model(DEM),SAR indices generated by Sentinel-1,and vegetation indices generated by Sentinel-2 to map soil salinization in the Ogan-Kuqa River Oasis located in the central and northern Tarim Basin in Xinjiang of China,and evaluated the potential of multi-source sensors to predict soil salinity.Using the soil electrical conductivity(EC)values of 70 ground sampling sites as the target variable and the optimal environmental factors as the predictive variable,we constructed three soil salinity inversion models based on classification and regression tree(CART),random forest(RF),and extreme gradient boosting(XGBoost).Then,we evaluated the prediction ability of different models through the five-fold cross validation.The prediction accuracy of XGBoost model is better than those of CART and RF,and soil salinity predicted by the three models has similar spatial distribution characteristics.Compared with the combination of topography indices and vegetation indices,the addition of SAR indices effectively improves the prediction accuracy of the model.In general,the method of soil salinity prediction based on multi-source sensor combination is better than that based on a single sensor.In addition,SAR indices,vegetation indices,and topography indices are all effective variables for soil salinity prediction.Weighted Difference Vegetation Index(WDVI)is designated as the most important variable in these variables,followed by DEM.The results showed that the high-resolution radar Sentinel-1 and multispectral Sentinel-2 have the potential to develop soil salinity prediction model.展开更多
Local terrain attributes,which are derived directly from the digital elevation model,have been widely applied in digital soil mapping.This study aimed to evaluate the mapping accuracy of soil organic carbon(SOC) conce...Local terrain attributes,which are derived directly from the digital elevation model,have been widely applied in digital soil mapping.This study aimed to evaluate the mapping accuracy of soil organic carbon(SOC) concentration in 2 zones of the Heihe River in China,by combining prediction methods with local terrain attributes derived from different polynomial models.The prediction accuracy was used as a benchmark for those who may be more concerned with how accurately the variability of soil properties is modeled in practice,rather than how morphometric variables and their geomorphologic interpretations are understood and calculated.In this study,2 neighborhood types(square and circular) and 6 representative algorithms(Evans-Young,Horn,Zevenbergen-Thorne,Shary,Shi,and Florinsky algorithms) were applied.In general,35 combinations of first-and second-order derivatives were produced as candidate predictors for soil mapping using two mapping methods(i.e.,kriging with an external drift and geographically weighted regression).The results showed that appropriate local terrain attribute algorithms could better capture the spatial variation of SOC concentration in a region where soil properties are strongly influenced by the topography.Among the different combinations of firstand second-order derivatives used,there was a best combination with a more accurate estimate.For different prediction methods,the relative improvement in the two zones varied between 0.30% and 9.68%.The SOC maps resulting from the higher-order algorithms(Zevenbergen-Thorne and Florinsky) yielded less interpolation errors.Therefore,it was concluded that the performance of predictive methods,which incorporated auxiliary variables,could be improved by attempting different terrain analysis algorithms.展开更多
This article presents two approaches for automated building of knowledge bases of soil resources mapping. These methods used decision tree and Bayesian predictive modeling, respectively to generate knowledge from tra...This article presents two approaches for automated building of knowledge bases of soil resources mapping. These methods used decision tree and Bayesian predictive modeling, respectively to generate knowledge from training data. With these methods, building a knowledge base for automated soil mapping is easier than using the conventional knowledge acquisition approach. The knowledge bases built by these two methods were used by the knowledge classifier for soil type classification of the Longyou area, Zhejiang Province, China using TM bi-temporal imageries and GIS data. To evaluate the performance of the resultant knowledge bases, the classification results were compared to existing soil map based on field survey. The accuracy assessment and analysis of the resultant soil maps suggested that the knowledge bases built by these two methods were of good quality for mapping distribution model of soil classes over the study area.展开更多
Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effect...Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide more reliable references for soil conservation policy-making.展开更多
Soil types, humus types and vegetation as well as their hypsometric variation were analysed in terms of sequences in the northern part of the high mountains of the Pirin National Park at altitudes between looo and 240...Soil types, humus types and vegetation as well as their hypsometric variation were analysed in terms of sequences in the northern part of the high mountains of the Pirin National Park at altitudes between looo and 2400 m a.s.1. The study area is characterised by a large variety of natural parameters like petrology （mainly marble and granite）, morphology （different slope deposits, exposition） and the orographic climate gradient. Statistical analyses using these parameters provided a basis for the soil group classification of the sites. Based on a Digital Terrain Model （DTM） and a geological map of the Pirin National Park, the results of these statistical analyses were used to generate a ＂map of potential soil groups＂ （regionalisation using GIS）. Six potential soil groups could be determined. The resulting map exhibits a confidence level of 68 % on 74.4 % of the covered area. Rendzic Leptosols, in combination with Folic Histosols and Histi-lithic Leptosols occur in the alpine and subalpine regions on calcareous substrates. With decreasing altitude they are replaced by a mosaic of Rendzic Leptosols, Phaeozems and an increasing occurrence of Cambic Umbrisols. Umbrisols found on silicatic substrates in the alpine region are replaced by Cambic Umbrisols with decreasing altitude as well. Hence, pedogenesis is characterised by increasing browning and depth of the soil profiles with decreasing altitude. The pH-level is slightly acidic to neutral in lower zones and on calcareous rocky bases. Acidification increases in the subalpine zone. Soil pH decreases down to 4 on silicate subtrates. Typical humic values in mineral topsoils are 10 to 12 %, and in organic layers of the soils above 2000 m a.s.1, they are even more. The C：N ratio closely ranges around 20 （median）.展开更多
Characterizing spatial variability of soil attributes, using traditional soil sampling and laboratory analysis, is cost prohibitive. The potential benefit of managing soils on a site-specific basis is well established...Characterizing spatial variability of soil attributes, using traditional soil sampling and laboratory analysis, is cost prohibitive. The potential benefit of managing soils on a site-specific basis is well established. High variations in glacial till soil render detailed soil mapping difficult with limited number of soil samples. To overcome this problem, this paper demonstrates the feasibility of soil carbon and clay mapping using the newly developed on-the-go near-infrared reflectance spectroscopy (NIRS). Compared with the geostatistics method, the partial least squares regression (PLSR), with NIRS measurements, could yield a more detailed map for both soil carbon and clay. Further, by using independent validation dataset, the accuracy of predicting could be improved significantly for soil clay content and only slightly for soil carbon content. Owing to the complexity of field conditions, more work on data processing and calibration modeling might be necessary for using on-the-go NIRS measurements.展开更多
Soil carbon mapping is extremely useful in assessing the effect of land management practices on soil carbon storage.Applications of neutron-gamma analysis in scanning mode for mapping of soil carbon are discussed.A Gl...Soil carbon mapping is extremely useful in assessing the effect of land management practices on soil carbon storage.Applications of neutron-gamma analysis in scanning mode for mapping of soil carbon are discussed.A Global Positioning System(GPS)device and softwares required to simultaneously acquire gamma signals and geographical positions during scanning operations were added to an existing measurement system.The reliability of soil carbon measurements in scanning mode was demonstrated to be in agreement with results acquired from static mode.The error analysis indicated that scanning measurements can be conducted with the same accuracy as static measurements in approximately one fourth the time.To obtain results suitable for mapping analogous to traditional chemical analyses(i.e.,±0.5 in weight percent or±0.5 w%),scanning time over a given site should be ca.15 min using the current measurement system configuration.Based on this measurement time,a reasonable towing speed of 3–5 km h^-1,the necessity for complete site coverage during scanning,the number of sites(within the surveyed field),and the required total measurement time can be estimated.Soil carbon measurements for 28 field sites(total area ca.2.5 ha)were conducted in ca.8 h.Based on acquired data,a soil carbon distribution map was constructed utilizing various softwares.The surveyed field area included an asphalt road that had carbon readings higher than the surrounding land.The clarity with which these carbon-rich zones were delineated on the constructed map represents evidence supporting the veracity of this method.Neutron-gamma analysis technology can greatly facilitate timely construction of soil carbon maps.展开更多
Soil phosphorus (P) plays a vital role in both ecological and agricultural ecosystems, where total P (TP) in soil serves as a crucial indicator of soil fertility and quality. Most of the studies covered in the literat...Soil phosphorus (P) plays a vital role in both ecological and agricultural ecosystems, where total P (TP) in soil serves as a crucial indicator of soil fertility and quality. Most of the studies covered in the literature employ a single or narrow range of soil databases, which largely overlooks the impact of utilizing multiple mapping scales in estimating soil TP, especially in hilly topographies. In this study, Fujian Province, a subtropical hilly region along China’s southeast coast covered by a complex topographic environment, was taken as a case study. The influence of the mapping scale on soil TP storage (TPS)estimation was analyzed using six digital soil databases that were derived from 3 082 unique soil profiles at different mapping scales, i.e., 1:50 000 (S5),1:200 000 (S20), 1:500 000 (S50), 1:1 000 000 (S100), 1:4 000 000 (S400), and 1:10 000 000 (S1000). The regional TPS in the surface soil (0–20 cm) based on the S5, S20, S50, S100, S400, and S1000 soil maps was 20.72, 22.17, 23.06, 23.05, 22.04, and 23.48 Tg, respectively, and the corresponding TPS at0–100 cm soil depth was 80.98, 80.71, 85.00, 84.03, 82.96, and 86.72 Tg, respectively. By comparing soil TPS in the S20 to S1000 maps to that in the S5map, the relative deviations were 6.37%–13.32%for 0–20 cm and 0.33%–7.09%for 0–100 cm. Moreover, since the S20 map had the lowest relative deviation among different mapping scales as compared to S5, it could provide additional soil information and a richer soil environment than other smaller mapping scales. Our results also revealed that many uncertainties in soil TPS estimation originated from the lack of detailed soil information, i.e., representation and spatial variations among different soil types. From the time and labor perspectives, our work provides useful guidelines to identify the appropriate mapping scale for estimating regional soil TPS in areas like Fujian Province in subtropical China or other places with similar complex topographies. Moreover, it is of tremendous importance to accurately estimate soil TPS to ensure ecosystem stability and sustainable agricultural development, especially for regional decision-making and management of phosphate fertilizer application amounts.展开更多
The first Ukrainian using experience of multispectral space scanning for digital soil mapping is described in this paper. Methodical approaches for detailed soil observation of Ukrainian forest regions are elaborated ...The first Ukrainian using experience of multispectral space scanning for digital soil mapping is described in this paper. Methodical approaches for detailed soil observation of Ukrainian forest regions are elaborated based on modem mapping principles. For the first time in Ukraine, digital soil maps based on GIS （geographic information system） were obtained for individual farms. In GIS based on space images and digital relief models, the medium-scale and large-scale soil maps were created by geo-statistical methods. According to elaborated methods, modem digital soil mapping should provide all combined works： remote sensing and traditional soil observations. The modem digital soil mapping should be based just on quantitative principles： on remote sensing data, geomorphologic field parameters, and chemical analyses. The methodological approaches, which were used for the first time in Ukraine during digital soil mapping by remote sensing methods, are described in this paper.展开更多
Conventional soil maps(CSMs)often have multiple soil types within a single polygon,which hinders the ability of machine learning to accurately predict soils.Soil disaggregation approaches are commonly used to improve ...Conventional soil maps(CSMs)often have multiple soil types within a single polygon,which hinders the ability of machine learning to accurately predict soils.Soil disaggregation approaches are commonly used to improve the spatial and attribute precision of CSMs.The approach disaggregation and harmonization of soil map units through resampled classification trees(DSMART)is popular but computationally intensive,as it generates and assigns synthetic samples to soil series based on the areal coverage information of CSMs.Alternatively,the disaggregation approach pure polygon disaggregation(PPD)assigns soil series based solely on the proportions of soil series in pure polygons in CSMs.This study compared these two disaggregation approaches by applying them to a CSM of Middlesex County,Ontario,Canada.Four different sampling methods were used:two sampling designs,simple random sampling(SRS)and conditional Latin hypercube sampling(cLHS),with two sample sizes(83100 and 19420 samples per sampling plan),both based on an area-weighted approach.Two machine learning algorithms(MLAs),C5.0 decision tree(C5.0)and random forest(RF),were applied to the disaggregation approaches to compare the disaggregation accuracy.The accuracy assessment utilized a set of 500 validation points obtained from the Middlesex County soil survey report.The MLA C5.0(Kappa index=0.58–0.63)showed better performance than RF(Kappa index=0.53–0.54)based on the larger sample size,and PPD with C5.0 based on the larger sample size was the best-performing(Kappa index=0.63)approach.Based on the smaller sample size,both cLHS(Kappa index=0.41–0.48)and SRS(Kappa index=0.40–0.47)produced similar accuracy results.The disaggregation approach PPD exhibited lower processing capacity and time demands(1.62–5.93 h)while yielding maps with lower uncertainty as compared to DSMART(2.75–194.2 h).For CSMs predominantly composed of pure polygons,utilizing PPD for soil series disaggregation is a more efficient and rational choice.However,DSMART is the preferable approach for disaggregating soil series that lack pure polygon representations in the CSMs.展开更多
In agricultural systems,the regular monitoring of Soil Organic Matter(SOM)dynamics is essential.This task is costly and time-consuming when using the conventional method,especially in a very fragmented area and with i...In agricultural systems,the regular monitoring of Soil Organic Matter(SOM)dynamics is essential.This task is costly and time-consuming when using the conventional method,especially in a very fragmented area and with intensive agricultural activity,such as the area of Sidi Bennour.The study area is located in the Doukkala irrigated perimeter in Morocco.Satellite data can provide an alternative and fill this gap at a low cost.Models to predict SOM from a satellite image,whether linear or nonlinear,have shown considerable interest.This study aims to compare SOM prediction using Multiple Linear Regression(MLR)and Artificial Neural Networks(ANN).A total of 368 points were collected at a depth of 0-30 cm and analyzed in the laboratory.An image at 15 m resolution(MSPAN)was produced from a 30 m resolution(MS)Landsat-8 image using image pansharpening processing and panchromatic band(15 m).The results obtained show that the MLR models predicted the SOM with(training/validation)R^(2)values of 0.62/0.63 and 0.64/0.65 and RMSE values of 0.23/0.22 and 0.22/0.21 for the MS and MSPAN images,respectively.In contrast,the ANN models predicted SOM with R2 values of 0.65/0.66 and 0.69/0.71 and RMSE values of 0.22/0.10 and 0.21/0.18 for the MS and MSPAN images,respectively.Image pansharpening improved the prediction accuracy by 2.60%and 4.30%and reduced the estimation error by 0.80%and 1.30%for the MLR and ANN models,respectively.展开更多
Forest soil carbon is a major carbon pool of terrestrial ecosystems,and accurate estimation of soil organic carbon(SOC)stocks in forest ecosystems is rather challenging.This study compared the prediction performance o...Forest soil carbon is a major carbon pool of terrestrial ecosystems,and accurate estimation of soil organic carbon(SOC)stocks in forest ecosystems is rather challenging.This study compared the prediction performance of three empirical model approaches namely,regression kriging(RK),multiple stepwise regression(MSR),random forest(RF),and boosted regression trees(BRT)to predict SOC stocks in Northeast China for 1990 and 2015.Furthermore,the spatial variation of SOC stocks and the main controlling environmental factors during the past 25 years were identified.A total of 82(in 1990)and 157(in 2015)topsoil(0–20 cm)samples with 12 environmental factors(soil property,climate,topography and biology)were selected for model construction.Randomly selected80%of the soil sample data were used to train the models and the other 20%data for model verification using mean absolute error,root mean square error,coefficient of determination and Lin's consistency correlation coefficient indices.We found BRT model as the best prediction model and it could explain 67%and 60%spatial variation of SOC stocks,in 1990,and 2015,respectively.Predicted maps of all models in both periods showed similar spatial distribution characteristics,with the lower SOC in northeast and higher SOC in southwest.Mean annual temperature and elevation were the key environmental factors influencing the spatial variation of SOC stock in both periods.SOC stocks were mainly stored under Cambosols,Gleyosols and Isohumosols,accounting for 95.6%(1990)and 95.9%(2015).Overall,SOC stocks increased by 471 Tg C during the past 25 years.Our study found that the BRT model employing common environmental factors was the most robust method for forest topsoil SOC stocks inventories.The spatial resolution of BRT model enabled us to pinpoint in which areas of Northeast China that new forest tree planting would be most effective for enhancing forest C stocks.Overall,our approach is likely to be useful in forestry management and ecological restoration at and beyond the regional scale.展开更多
基金supported by the National Natural Science Foundation of China (91325301, 41571130051)
文摘To deal with the global and regional issues including food security, climate change, land degradation, biodiversity loss, water resource management, and ecosystem health, detailed accurate spatial soil information is urgently needed. This drives the worldwide development of digital soil mapping. In recent years, significant progresses have been made in different aspects of digital soil mapping. The main purpose of this paper is to provide a review for the major progresses of digital soil mapping in the last decade. First, we briefly described the rise of digital soil mapping and outlined important milestones and their influence, and main paradigms in digital soil mapping. Then, we reviewed the progresses in legacy soil data, environmental covariates, soil sampling, predictive models and the applications of digital soil mapping products. Finally, we summarized the main trends and future prospect as revealed by studies up to now. We concluded that although the digital soil mapping is now moving towards mature to meet various demands of soil information, challenges including new theories, methodologies and applications of digital soil mapping, especially for highly heterogeneous and human-affected environments, still exist and need to be addressed in the future.
基金supported by grants from the National Natural Science Foundation of China(41431177 and 41871300)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD),China+4 种基金the Innovation Project of State Key Laboratory of Resources and Environmental Information System(LREIS),China(O88RA20CYA)the Outstanding Innovation Team in Colleges and Universities in Jiangsu Province,ChinaSupports to A-Xing Zhu through the Vilas Associate Awardthe Hammel Faculty Fellow Awardthe Manasse Chair Professorship from the University of Wisconsin-Madison。
文摘Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not available for those situations with limited samples.To solve the problem,this paper proposed a case-based method which could formalize the covariate selection knowledge contained in practical DSM applications.The proposed method trained Random Forest(RF)classifiers with DSM cases extracted from the practical DSM applications and then used the trained classifiers to determine whether each one potential covariate should be used in a new DSM application.In this study,we took topographic covariates as examples of covariates and extracted 191 DSM cases from 56 peer-reviewed journal articles to evaluate the performance of the proposed case-based method by Leave-One-Out cross validation.Compared with a novices’commonly-used way of selecting DSM covariates,the proposed case-based method improved more than 30%accuracy according to three quantitative evaluation indices(i.e.,recall,precision,and F1-score).The proposed method could be also applied to selecting the proper set of covariates for other similar geographical modeling domains,such as landslide susceptibility mapping,and species distribution modeling.
基金Supported by the Basic Research Program of Jiangsu Province,China (No. BK2008058)the Knowledge Innovation Program of Chinese Academy of Sciences (No. KZCX2-YW-409)
文摘The use of landscape covariates to variability of soil properties in similar estimate soil properties is not suitable topographic and vegetation conditions. for the areas of low relief due to the high A new method was implemented to map regional soil texture （in terms of sand, silt and clay contents） by hypothesizing that the change in the land surface diurnal temperature difference （DTD） is related to soil texture in case of a relatively homogeneous rainfall input. To examine this hypothesis, the DTDs from moderate resolution imagine spectroradiometer （MODIS） during a selected time period, i.e., after a heavy rainfall between autumn harvest and autumn sowing, were classified using fuzzy-c-means （FCM） clustering. Six classes were generated, and for each class, the sand （〉 0.05 mm）, silt （0.002-0.05 mm） and clay （〈 0.002 mm） contents at the location of maximum membership value were considered as the typical values of that class. A weighted average model was then used to digitally map soil texture. The results showed that the predicted map quite accurately reflected the regional soil variation. A validation dataset produced estimates of error for the predicted maps of sand, silt and clay contents at root mean of squared error values of 8.4%, 7.8% and 2.3%, respectively, which is satisfactory in a practical context. This study thus provided a methodology that can help improve the accuracy and efficiency of soil texture mapping in plain areas using easily available data sources.
基金funded by the National Natural Science Foundation of China (Nos.41871300,41422109,and 41431177)the National Basic Research Program of China (No.2015CB954102)+1 种基金the Priority Academic Program Development of Jiangsu Higher Education Institutions,China (No.164320H116)the Outstanding Innovation Team in Colleges and Universities in Jiangsu Province,China the support from the Innovation Project of State Key Laboratory of Resources and Environmental Information System of China (No.O88RA20CYA)。
文摘The Soil Land Inference Model(SoLIM) was primarily proposed by Zhu et al.(Zhu A X, Band L, Vertessy R, Dutton B. 1997. Derivation of soil properties using a soil land inference model(SoLIM). Soil Sci Soc Am J. 61: 523–533.) and was based on the Third Law of Geography. Based on the assumption that the soil property value at a location of interest will be more similar to that of a given soil sample when the environmental condition at the location of interest is more similar to that at the location from which the sample was taken, SoLIM estimates the soil property value of the location of interest using the soil property values of known samples weighted by the similarity between those samples and the location of interest in terms of an attribute domain of environmental conditions. However, the current SoLIM method ignores information about the spatial distances between the location of interest and those of the sample. In this study, we proposed a new method of soil property mapping, So LIM-IDW, which incorporates spatial distance information into the SoLIM method by means of inverse distance weighting(IDW). The proposed method is based on the assumption that the soil property value at a location of interest will be more similar to that of a known sample both when the environmental conditions are more similar and when the distance between the location of interest and the sample location is shorter. Our evaluation experiments on A-horizon soil organic matter mapping in two study areas with independent evaluation samples showed that the proposed SoLIM-IDW method can obtain lower prediction errors than the original SoLIM method, multiple linear regression, geographically weighted regression, and regression-kriging with the same modeling points. Future work mainly includes the determination of optimal power parameter values and the appropriate setting of the parameter under different application contexts.
基金Under the auspices of Special Fund for Ocean Public Welfare Profession Scientific Research(No.201105020)National Natural Science Foundation of China(No.41471178,41023010,41431177)National Key Technology Innovation Project for Water Pollution Control and Remediation(No.2013ZX07103006)
文摘Spatial distribution of soil salinity can be estimated based on its environmental factors because soil salinity is strongly affected and indicated by environmental factors. Different with other properties such as soil texture, soil salinity varies with short-term time. Thus, how to choose powerful environmental predictors is especially important for soil salinity. This paper presents a similarity-based prediction approach to map soil salinity and detects powerful environmental predictors for the Huanghe(Yellow) River Delta area in China. The similarity-based approach predicts the soil salinities of unsampled locations based on the environmental similarity between unsampled and sampled locations. A dataset of 92 points with salt data at depth of 30–40 cm was divided into two subsets for prediction and validation. Topographical parameters, soil textures, distances to irrigation channels and to the coastline, land surface temperature from Moderate Resolution Imaging Spectroradiometer(MODIS), Normalized Difference Vegetation Indices(NDVIs) and land surface reflectance data from Landsat Thematic Mapper(TM) imagery were generated. The similarity-based prediction approach was applied on several combinations of different environmental factors. Based on three evaluation indices including the correlation coefficient(CC) between observed and predicted values, the mean absolute error and the root mean squared error we found that elevation, distance to irrigation channels, soil texture, night land surface temperature, NDVI, and land surface reflectance Band 5 are the optimal combination for mapping soil salinity at the 30–40 cm depth in the study area(with a CC value of 0.69 and a root mean squared error value of 0.38). Our results indicated that the similarity-based prediction approach could be a vital alternative to other methods for mapping soil salinity, especially for area with limited observation data and could be used to monitor soil salinity distributions in the future.
基金supported by the National Natural Science Foundation of China(Nos.41130530,91325301,41201207 and 41571212)the Project of Frontier Fields during the Thirteenth Five-Year Plan Period of the Institute of Soil Science,Chinese Academy of Sciences(ISSASIP1622)
文摘Due to the almost homogeneous topography in low relief areas, it is usually difficult to make accurate predictions of soil properties using topographic covariates. In this study, we examined how time series of field soil moisture observations can be used to estimate soil texture in an oasis agricultural area with low relief in the semi-arid region of northwest China. Time series of field-observed soil moisture variations were recorded for 132 h beginning at the end of an irrigation event during which the surface soil was saturated.Spatial correlation between two time-adjacent soil moisture conditions was used to select the factors for fuzzy c-means clustering. In each of the ten generated clusters, soil texture of the soil sample with the maximum fuzzy membership value was taken as the cluster centroid. Finally, a linearly weighted average was used to predict soil texture from the centroids. The results showed that soil moisture increased with the increase of clay and silt contents, but decreased with the increase of sand content. The spatial patterns of soil moisture changed during the entire soil drying phase. We assumed that these changes were mainly caused by spatial heterogeneity of soil texture. A total of 64 independent samples were used to evaluate the prediction accuracy. The root mean square error(RMSE)values of clay, silt and sand were 1.63, 2.81 and 3.71, respectively. The mean relative error(RE) values were 9.57% for clay, 3.77% for silt and 12.83% for sand. It could be concluded that the method used in this study was effective for soil texture mapping in the low-relief oasis agricultural area and could be applicable in other similar irrigation agricultural areas.
基金Under the auspices of Program of International Science & Technology Cooperation,Ministry of Science and Technology of China(No.2010DFB24140)National Natural Science Foundation of China(No.41023010,41001298)National High Technology Research and Development Program of China(No.2011AA120305)
文摘Soil type maps at the scale of I Z 1 000 000 are used extensively to provide soil spatial distribution information for soil erosion assessment and watershed management models in China. However, the soil property maps produced through conventional direct linking method usually suffer low accuracy as well as the lack of spatial details within a soil type polygon. This paper presents an effective method to produce detailed soil property map based on representative samples which were extracted from each polygon on the 1 ： 1 000 000 soil type map. The representative sample of each polygon is defined as the location that can represent the largest area within the polygon. The representativeness of a candidate sample is determined by calculating the soil-forming environment condition similarities between the sample and other locations. Once the representative sample of each polygon has been chosen, the property values of the existing typical samples are assigned to the corresponding representative samples with the same soil type. Finally, based on these representative samples, the detailed soil property map could be produced by using existing digital soil mapping methods. The case study in XuanCheng City, Anhui Province of China, demonstrated the proposed method could produce soil property map at a higher level of spatial details and accuracy： 1） The soil organic matter （SOM） map produced based on the representative samples can not only depict the detailed spatial distribution of SOM within a soil type polygon but also largely reduce the abrupt change of soil property at the boundaries of two adjacent polygons. 2） The Root Mean Squared Error （RMSE） of the SOM map based on the representative samples is 1.61, and it is 1.37 for the SOM map produced by using conventional direct linking method. Therefore, the proposed method is an effective approach to produce spatial detailed soil property map with higher accuracy for environment simulation models.
文摘Detailed knowledge about the estimates and spatial patterns of soil organic carbon(SOC) and total nitrogen(TN) stocks is fundamental for sustainable land management and climate change mitigation.This study aimed at:(1) mapping the spatial patterns,and(2) quantifying SOC and TN stocks to 30 cm depth in the Eastern Mau Forest Reserve using field,remote sensing,geographical information systems(GIS),and statistical modelling approaches.This is a critical ecosystem offering essential services,but its sustainability is threatened by deforestation and degradation.Results revealed that elevation,silt content,TN concentration,and Landsat 8 Operational Land Imager band 11 explained 72% of the variability in SOC stocks,while the same factors(except silt content) explained 71% of the variability in TN stocks.The results further showed that soil properties,particularly TN and SOC concentrations,were more important than that other environmental factors in controlling the observed patterns of SOC and TN stocks,respectively.Forests stored the highest amounts of SOC and TN(3.78 Tg C and 0.38 Tg N) followed by croplands(2.46 Tg C and 0.25 Tg N) and grasslands(0.57 Tg C and 0.06 Tg N).Overall,the Eastern Mau Forest Reserve stored approximately 6.81 Tg C and 0.69 Tg N.The highest estimates of SOC and TN stocks(hotspots) occurred on the western and northwestern parts where forests dominated,while the lowest estimates(coldspots) occurred on the eastern side where croplands had been established.Therefore,the hotspots need policies that promote conservation,while the coldspots need those that support accumulation of SOC and TN stocks.
基金This work was financially supported by the National Natural Science Foundation of China(41771470)the China Postdoctoral Science Foundation(2020M672776).
文摘Soil salinization is one of the most important causes of land degradation and desertification,especially in arid and semi-arid areas.The dynamic monitoring of soil salinization is of great significance to land management,agricultural activities,water quality,and sustainable development.The remote sensing images taken by the synthetic aperture radar(SAR)Sentinel-1 and the multispectral satellite Sentinel-2 with high resolution and short revisit period have the potential to monitor the spatial distribution of soil attribute information on a large area;however,there are limited studies on the combination of Sentinel-1 and Sentinel-2 for digital mapping of soil salinization.Therefore,in this study,we used topography indices derived from digital elevation model(DEM),SAR indices generated by Sentinel-1,and vegetation indices generated by Sentinel-2 to map soil salinization in the Ogan-Kuqa River Oasis located in the central and northern Tarim Basin in Xinjiang of China,and evaluated the potential of multi-source sensors to predict soil salinity.Using the soil electrical conductivity(EC)values of 70 ground sampling sites as the target variable and the optimal environmental factors as the predictive variable,we constructed three soil salinity inversion models based on classification and regression tree(CART),random forest(RF),and extreme gradient boosting(XGBoost).Then,we evaluated the prediction ability of different models through the five-fold cross validation.The prediction accuracy of XGBoost model is better than those of CART and RF,and soil salinity predicted by the three models has similar spatial distribution characteristics.Compared with the combination of topography indices and vegetation indices,the addition of SAR indices effectively improves the prediction accuracy of the model.In general,the method of soil salinity prediction based on multi-source sensor combination is better than that based on a single sensor.In addition,SAR indices,vegetation indices,and topography indices are all effective variables for soil salinity prediction.Weighted Difference Vegetation Index(WDVI)is designated as the most important variable in these variables,followed by DEM.The results showed that the high-resolution radar Sentinel-1 and multispectral Sentinel-2 have the potential to develop soil salinity prediction model.
基金supported by the National Natural Science Foundation of China(Nos.91325301,41571130051,41401237,41571212,and 41371224)partly by the Jiangsu Provincial Science Foundation for Youths,China(No.BK20141053)
文摘Local terrain attributes,which are derived directly from the digital elevation model,have been widely applied in digital soil mapping.This study aimed to evaluate the mapping accuracy of soil organic carbon(SOC) concentration in 2 zones of the Heihe River in China,by combining prediction methods with local terrain attributes derived from different polynomial models.The prediction accuracy was used as a benchmark for those who may be more concerned with how accurately the variability of soil properties is modeled in practice,rather than how morphometric variables and their geomorphologic interpretations are understood and calculated.In this study,2 neighborhood types(square and circular) and 6 representative algorithms(Evans-Young,Horn,Zevenbergen-Thorne,Shary,Shi,and Florinsky algorithms) were applied.In general,35 combinations of first-and second-order derivatives were produced as candidate predictors for soil mapping using two mapping methods(i.e.,kriging with an external drift and geographically weighted regression).The results showed that appropriate local terrain attribute algorithms could better capture the spatial variation of SOC concentration in a region where soil properties are strongly influenced by the topography.Among the different combinations of firstand second-order derivatives used,there was a best combination with a more accurate estimate.For different prediction methods,the relative improvement in the two zones varied between 0.30% and 9.68%.The SOC maps resulting from the higher-order algorithms(Zevenbergen-Thorne and Florinsky) yielded less interpolation errors.Therefore,it was concluded that the performance of predictive methods,which incorporated auxiliary variables,could be improved by attempting different terrain analysis algorithms.
基金Project supported by the National Natural Science Foundation ofChina (No. 40101014) and by the Science and technology Committee of Zhejiang Province (No. 001110445) China
文摘This article presents two approaches for automated building of knowledge bases of soil resources mapping. These methods used decision tree and Bayesian predictive modeling, respectively to generate knowledge from training data. With these methods, building a knowledge base for automated soil mapping is easier than using the conventional knowledge acquisition approach. The knowledge bases built by these two methods were used by the knowledge classifier for soil type classification of the Longyou area, Zhejiang Province, China using TM bi-temporal imageries and GIS data. To evaluate the performance of the resultant knowledge bases, the classification results were compared to existing soil map based on field survey. The accuracy assessment and analysis of the resultant soil maps suggested that the knowledge bases built by these two methods were of good quality for mapping distribution model of soil classes over the study area.
基金the National Natural Science Foundation of China(U1901601)the National Key Research and Development Program of China(2022YFB3903503)。
文摘Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide more reliable references for soil conservation policy-making.
文摘Soil types, humus types and vegetation as well as their hypsometric variation were analysed in terms of sequences in the northern part of the high mountains of the Pirin National Park at altitudes between looo and 2400 m a.s.1. The study area is characterised by a large variety of natural parameters like petrology （mainly marble and granite）, morphology （different slope deposits, exposition） and the orographic climate gradient. Statistical analyses using these parameters provided a basis for the soil group classification of the sites. Based on a Digital Terrain Model （DTM） and a geological map of the Pirin National Park, the results of these statistical analyses were used to generate a ＂map of potential soil groups＂ （regionalisation using GIS）. Six potential soil groups could be determined. The resulting map exhibits a confidence level of 68 % on 74.4 % of the covered area. Rendzic Leptosols, in combination with Folic Histosols and Histi-lithic Leptosols occur in the alpine and subalpine regions on calcareous substrates. With decreasing altitude they are replaced by a mosaic of Rendzic Leptosols, Phaeozems and an increasing occurrence of Cambic Umbrisols. Umbrisols found on silicatic substrates in the alpine region are replaced by Cambic Umbrisols with decreasing altitude as well. Hence, pedogenesis is characterised by increasing browning and depth of the soil profiles with decreasing altitude. The pH-level is slightly acidic to neutral in lower zones and on calcareous rocky bases. Acidification increases in the subalpine zone. Soil pH decreases down to 4 on silicate subtrates. Typical humic values in mineral topsoils are 10 to 12 %, and in organic layers of the soils above 2000 m a.s.1, they are even more. The C：N ratio closely ranges around 20 （median）.
基金Supported by the Agricultural S&T Cooperation Program of Zhejiang Province, China (No. N20100015)
文摘Characterizing spatial variability of soil attributes, using traditional soil sampling and laboratory analysis, is cost prohibitive. The potential benefit of managing soils on a site-specific basis is well established. High variations in glacial till soil render detailed soil mapping difficult with limited number of soil samples. To overcome this problem, this paper demonstrates the feasibility of soil carbon and clay mapping using the newly developed on-the-go near-infrared reflectance spectroscopy (NIRS). Compared with the geostatistics method, the partial least squares regression (PLSR), with NIRS measurements, could yield a more detailed map for both soil carbon and clay. Further, by using independent validation dataset, the accuracy of predicting could be improved significantly for soil clay content and only slightly for soil carbon content. Owing to the complexity of field conditions, more work on data processing and calibration modeling might be necessary for using on-the-go NIRS measurements.
基金supported by the National Institute of Food and Agriculture(NIFA)Research Grant(No.ALA2016-67021-24417)“Precision geospatial mapping of soil carbon content for agricultural productivity and lifecycle management”
文摘Soil carbon mapping is extremely useful in assessing the effect of land management practices on soil carbon storage.Applications of neutron-gamma analysis in scanning mode for mapping of soil carbon are discussed.A Global Positioning System(GPS)device and softwares required to simultaneously acquire gamma signals and geographical positions during scanning operations were added to an existing measurement system.The reliability of soil carbon measurements in scanning mode was demonstrated to be in agreement with results acquired from static mode.The error analysis indicated that scanning measurements can be conducted with the same accuracy as static measurements in approximately one fourth the time.To obtain results suitable for mapping analogous to traditional chemical analyses(i.e.,±0.5 in weight percent or±0.5 w%),scanning time over a given site should be ca.15 min using the current measurement system configuration.Based on this measurement time,a reasonable towing speed of 3–5 km h^-1,the necessity for complete site coverage during scanning,the number of sites(within the surveyed field),and the required total measurement time can be estimated.Soil carbon measurements for 28 field sites(total area ca.2.5 ha)were conducted in ca.8 h.Based on acquired data,a soil carbon distribution map was constructed utilizing various softwares.The surveyed field area included an asphalt road that had carbon readings higher than the surrounding land.The clarity with which these carbon-rich zones were delineated on the constructed map represents evidence supporting the veracity of this method.Neutron-gamma analysis technology can greatly facilitate timely construction of soil carbon maps.
基金supported by the National Natural Science Foundation of China(Nos.41971050 and 42207271)the Provincial Natural Science Foundation of Fujian,China(No.2022J05036)the Open Project Program of the State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry,Institute of Atmospheric Physics,Chinese Academy of Sciences(No.LAPC-KF-2022-08)。
文摘Soil phosphorus (P) plays a vital role in both ecological and agricultural ecosystems, where total P (TP) in soil serves as a crucial indicator of soil fertility and quality. Most of the studies covered in the literature employ a single or narrow range of soil databases, which largely overlooks the impact of utilizing multiple mapping scales in estimating soil TP, especially in hilly topographies. In this study, Fujian Province, a subtropical hilly region along China’s southeast coast covered by a complex topographic environment, was taken as a case study. The influence of the mapping scale on soil TP storage (TPS)estimation was analyzed using six digital soil databases that were derived from 3 082 unique soil profiles at different mapping scales, i.e., 1:50 000 (S5),1:200 000 (S20), 1:500 000 (S50), 1:1 000 000 (S100), 1:4 000 000 (S400), and 1:10 000 000 (S1000). The regional TPS in the surface soil (0–20 cm) based on the S5, S20, S50, S100, S400, and S1000 soil maps was 20.72, 22.17, 23.06, 23.05, 22.04, and 23.48 Tg, respectively, and the corresponding TPS at0–100 cm soil depth was 80.98, 80.71, 85.00, 84.03, 82.96, and 86.72 Tg, respectively. By comparing soil TPS in the S20 to S1000 maps to that in the S5map, the relative deviations were 6.37%–13.32%for 0–20 cm and 0.33%–7.09%for 0–100 cm. Moreover, since the S20 map had the lowest relative deviation among different mapping scales as compared to S5, it could provide additional soil information and a richer soil environment than other smaller mapping scales. Our results also revealed that many uncertainties in soil TPS estimation originated from the lack of detailed soil information, i.e., representation and spatial variations among different soil types. From the time and labor perspectives, our work provides useful guidelines to identify the appropriate mapping scale for estimating regional soil TPS in areas like Fujian Province in subtropical China or other places with similar complex topographies. Moreover, it is of tremendous importance to accurately estimate soil TPS to ensure ecosystem stability and sustainable agricultural development, especially for regional decision-making and management of phosphate fertilizer application amounts.
文摘The first Ukrainian using experience of multispectral space scanning for digital soil mapping is described in this paper. Methodical approaches for detailed soil observation of Ukrainian forest regions are elaborated based on modem mapping principles. For the first time in Ukraine, digital soil maps based on GIS （geographic information system） were obtained for individual farms. In GIS based on space images and digital relief models, the medium-scale and large-scale soil maps were created by geo-statistical methods. According to elaborated methods, modem digital soil mapping should provide all combined works： remote sensing and traditional soil observations. The modem digital soil mapping should be based just on quantitative principles： on remote sensing data, geomorphologic field parameters, and chemical analyses. The methodological approaches, which were used for the first time in Ukraine during digital soil mapping by remote sensing methods, are described in this paper.
基金the Ontario Ministry of Agriculture,Food and Rural Affairs,Canada,who supported this project by providing updated soil information on Ontario and Middlesex Countysupported by the Natural Science and Engineering Research Council of Canada(No.RGPIN-2014-4100)。
文摘Conventional soil maps(CSMs)often have multiple soil types within a single polygon,which hinders the ability of machine learning to accurately predict soils.Soil disaggregation approaches are commonly used to improve the spatial and attribute precision of CSMs.The approach disaggregation and harmonization of soil map units through resampled classification trees(DSMART)is popular but computationally intensive,as it generates and assigns synthetic samples to soil series based on the areal coverage information of CSMs.Alternatively,the disaggregation approach pure polygon disaggregation(PPD)assigns soil series based solely on the proportions of soil series in pure polygons in CSMs.This study compared these two disaggregation approaches by applying them to a CSM of Middlesex County,Ontario,Canada.Four different sampling methods were used:two sampling designs,simple random sampling(SRS)and conditional Latin hypercube sampling(cLHS),with two sample sizes(83100 and 19420 samples per sampling plan),both based on an area-weighted approach.Two machine learning algorithms(MLAs),C5.0 decision tree(C5.0)and random forest(RF),were applied to the disaggregation approaches to compare the disaggregation accuracy.The accuracy assessment utilized a set of 500 validation points obtained from the Middlesex County soil survey report.The MLA C5.0(Kappa index=0.58–0.63)showed better performance than RF(Kappa index=0.53–0.54)based on the larger sample size,and PPD with C5.0 based on the larger sample size was the best-performing(Kappa index=0.63)approach.Based on the smaller sample size,both cLHS(Kappa index=0.41–0.48)and SRS(Kappa index=0.40–0.47)produced similar accuracy results.The disaggregation approach PPD exhibited lower processing capacity and time demands(1.62–5.93 h)while yielding maps with lower uncertainty as compared to DSMART(2.75–194.2 h).For CSMs predominantly composed of pure polygons,utilizing PPD for soil series disaggregation is a more efficient and rational choice.However,DSMART is the preferable approach for disaggregating soil series that lack pure polygon representations in the CSMs.
文摘In agricultural systems,the regular monitoring of Soil Organic Matter(SOM)dynamics is essential.This task is costly and time-consuming when using the conventional method,especially in a very fragmented area and with intensive agricultural activity,such as the area of Sidi Bennour.The study area is located in the Doukkala irrigated perimeter in Morocco.Satellite data can provide an alternative and fill this gap at a low cost.Models to predict SOM from a satellite image,whether linear or nonlinear,have shown considerable interest.This study aims to compare SOM prediction using Multiple Linear Regression(MLR)and Artificial Neural Networks(ANN).A total of 368 points were collected at a depth of 0-30 cm and analyzed in the laboratory.An image at 15 m resolution(MSPAN)was produced from a 30 m resolution(MS)Landsat-8 image using image pansharpening processing and panchromatic band(15 m).The results obtained show that the MLR models predicted the SOM with(training/validation)R^(2)values of 0.62/0.63 and 0.64/0.65 and RMSE values of 0.23/0.22 and 0.22/0.21 for the MS and MSPAN images,respectively.In contrast,the ANN models predicted SOM with R2 values of 0.65/0.66 and 0.69/0.71 and RMSE values of 0.22/0.10 and 0.21/0.18 for the MS and MSPAN images,respectively.Image pansharpening improved the prediction accuracy by 2.60%and 4.30%and reduced the estimation error by 0.80%and 1.30%for the MLR and ANN models,respectively.
基金funded by the National Key R&D Program of China(Grant No.2021YFD1500200)National Natural Science Foundation of China(Grant No.42077149)+4 种基金China Postdoctoral Science Foundation(Grant No.2019M660782)National Science and Technology Basic Resources Survey Program of China(Grant No.2019FY101300)Doctoral research start-up fund project of Liaoning Provincial Department of Science and Technology(Grant No.2021-BS-136)China Scholarship Council(201908210132)Young Scientific and Technological Talents Project of Liaoning Province(Grant Nos.LSNQN201910 and LSNQN201914)。
文摘Forest soil carbon is a major carbon pool of terrestrial ecosystems,and accurate estimation of soil organic carbon(SOC)stocks in forest ecosystems is rather challenging.This study compared the prediction performance of three empirical model approaches namely,regression kriging(RK),multiple stepwise regression(MSR),random forest(RF),and boosted regression trees(BRT)to predict SOC stocks in Northeast China for 1990 and 2015.Furthermore,the spatial variation of SOC stocks and the main controlling environmental factors during the past 25 years were identified.A total of 82(in 1990)and 157(in 2015)topsoil(0–20 cm)samples with 12 environmental factors(soil property,climate,topography and biology)were selected for model construction.Randomly selected80%of the soil sample data were used to train the models and the other 20%data for model verification using mean absolute error,root mean square error,coefficient of determination and Lin's consistency correlation coefficient indices.We found BRT model as the best prediction model and it could explain 67%and 60%spatial variation of SOC stocks,in 1990,and 2015,respectively.Predicted maps of all models in both periods showed similar spatial distribution characteristics,with the lower SOC in northeast and higher SOC in southwest.Mean annual temperature and elevation were the key environmental factors influencing the spatial variation of SOC stock in both periods.SOC stocks were mainly stored under Cambosols,Gleyosols and Isohumosols,accounting for 95.6%(1990)and 95.9%(2015).Overall,SOC stocks increased by 471 Tg C during the past 25 years.Our study found that the BRT model employing common environmental factors was the most robust method for forest topsoil SOC stocks inventories.The spatial resolution of BRT model enabled us to pinpoint in which areas of Northeast China that new forest tree planting would be most effective for enhancing forest C stocks.Overall,our approach is likely to be useful in forestry management and ecological restoration at and beyond the regional scale.
