To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of curr...To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors.This need is particularly relevant for metallic materials processed through additive manufacturing,which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials.Furthermore,capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties.To address these challenges,we propose the physical spatial mapping of metal diffraction latent space features.This approach integrates(i)point diffraction data encoding via variational autoencoders or contrastive learning and(ii)the physical mapping of the encoded values.Together,these steps offer a method to comprehensively describe metal microstructures.We demonstrate this approach on a wrought and additively manufactured alloy,showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models.This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.展开更多
Realizing precise recording with large populations of neurons has been a long-standing goal in developing next-generation brain-machine interfaces(BMIs)[1,2].Specifically,flexible electrocorticography(ECoG)devices pla...Realizing precise recording with large populations of neurons has been a long-standing goal in developing next-generation brain-machine interfaces(BMIs)[1,2].Specifically,flexible electrocorticography(ECoG)devices placed on the cerebral cortex provide a nonpenetrating means to measure population-level coordinated neural activities across wide cortical areas,and have been successfully applied for speech synthesis,motor decoding,and seizure localization[3].展开更多
Remote sensing has played a pivotal role in our understanding of the geometry of dykes and dyke swarms on Earth,Venus and Mars(West and Ernst,1991;Mege and Masson,1995;Ernst et al.,2005).Since the 1970’s
Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with ar...Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with artificial neural networks,were compared to predict spatial variation of saturated hydraulic conductivity from environmental covariates.All methods except ordinary kriging allow for inclusion of secondary variables.The secondary spatial information used was terrain attributes including elevation,slope gradient,slope aspect,profile curvature and contour curvature.A multiple jackknifing procedure was used as a validation method.Root mean square error (RMSE) and mean absolute error (MAE) were used as the validation indices,with the mean RMSE and mean MAE used to judge the prediction quality.Prediction performance by ordinary kriging was poor,indicating that prediction of saturated hydraulic conductivity can be improved by incorporating ancillary data such as terrain variables.Kriging combined with artificial neural networks performed best.These prediction models made better use of ancillary information in predicting saturated hydraulic conductivity compared with the competing models.The combination of geostatistical predictors with neural computing techniques offers more capability for incorporating ancillary information in predictive soil mapping.There is great potential for further research and development of hybrid methods for digital soil mapping.展开更多
Osteoarthritis(OA)is a degenerative skeletal condition marked by the loss of articular cartilage and changes to subchondral bone homeostasis.Treatments for OA beyond full joint replacement are lacking primarily due to...Osteoarthritis(OA)is a degenerative skeletal condition marked by the loss of articular cartilage and changes to subchondral bone homeostasis.Treatments for OA beyond full joint replacement are lacking primarily due to gaps in molecular knowledge of the biological drivers of disease.Mass Spectrometry Imaging(MSI)enables molecular spatial mapping of the proteomic landscape of tissues.Histologic sections of human tibial plateaus from knees of human OA patients and cadaveric controls were treated with collagenase III to target extracellular matrix(ECM)proteins prior to MS Imaging of bone and cartilage proteins.Spatial MS imaging of the knee identified distinct areas of joint damage to the subchondral bone underneath areas of lost cartilage.This damaged bone signature extended underneath remaining cartilage in OA joints,indicating subchondral bone remodeling could occur before full thickness cartilage loss in OA.Specific ECM peptide markers from OA-affected medial tibial plateaus were compared to their healthier lateral halves from the same patient,as well as to healthy,age-matched cadaveric knees.Overall,31 peptide candidates from ECM proteins,including Collagen alpha-1(Ⅰ),Collagen alpha-1(Ⅲ),and surprisingly,Collagen alpha-1(Ⅵ)and Collagen alpha-3(Ⅵ),exhibited significantly elevated abundance in diseased tissues.Additionally,highly specific hydroxyproline-containing collagen peptides,mainly from collagen typeⅠ,dominated OA subchondral bone directly under regions of lost cartilage but not areas where cartilage remained intact.A separate analysis of synovial fluid from a second cohort of OA patients found similar regulation of collagens and ECM proteins via LC-MS/MS demonstrating that markers of subchondral bone remodeling discovered by MALDI-MS may be detectable as biomarkers in biofluid samples.The identification of specific protein markers for subchondral bone remodeling in OA advances our molecular understanding of disease progression in OA and provides potential new biomarkers for OA detection and disease grading.展开更多
A quick and accurate extraction of dominant colors of background images is the basis of adaptive camouflage design.This paper proposes a Color Image Quick Fuzzy C-Means(CIQFCM)clustering algorithm based on clustering ...A quick and accurate extraction of dominant colors of background images is the basis of adaptive camouflage design.This paper proposes a Color Image Quick Fuzzy C-Means(CIQFCM)clustering algorithm based on clustering spatial mapping.First,the clustering sample space was mapped from the image pixels to the quantized color space,and several methods were adopted to compress the amount of clustering samples.Then,an improved pedigree clustering algorithm was applied to obtain the initial class centers.Finally,CIQFCM clustering algorithm was used for quick extraction of dominant colors of background image.After theoretical analysis of the effect and efficiency of the CIQFCM algorithm,several experiments were carried out to discuss the selection of proper quantization intervals and to verify the effect and efficiency of the CIQFCM algorithm.The results indicated that the value of quantization intervals should be set to 4,and the proposed algorithm could improve the clustering efficiency while maintaining the clustering effect.In addition,as the image size increased from 128×128 to 1024×1024,the efficiency improvement of CIQFCM algorithm was increased from 6.44 times to 36.42 times,which demonstrated the significant advantage of CIQFCM algorithm in dominant colors extraction of large-size images.展开更多
The electrical performance of radomes on high-speed aircraft can be influenced by the thermal and mechanical loads produced during high-speed flight,which can affect the detection dis-tance and accuracy of the guidanc...The electrical performance of radomes on high-speed aircraft can be influenced by the thermal and mechanical loads produced during high-speed flight,which can affect the detection dis-tance and accuracy of the guidance system.This paper presents a new method that uses the Finite Difference Time Domain(FDTD)method to calculate the electrical performance of radomes under Thermo-Mechanical-Electrical(TME)coupling.This method can accurately characterize the effects of material dielectric temperature drift and structural deformation on the electrical performance of the radome under flight conditions,enabling high-precision full-wave calculations of the broadband electrical performance of the radome.The method initiates by utilizing a Finite Element Grid Model(FE-GM)of the radome to sequentially acquire the radome's response temperature field and structural deformation field through thermal and mechanical simulations.Subsequently,spatial mapping techniques are developed to accurately incorporate the dielectric temperature drift and structural deformation of the radome into its Yee grid Electromagnetic(EM)simulation model.A verification case was designed to test the proposed method,and the results confirmed its high computational accuracy.Additionally,the effectiveness and necessity of the method were further demonstrated by analyzing the electrical performance of a fused silica ceramic radome used on a high-speed aircraft.展开更多
Crop production vulnerability to climate change in Northwest China depends upon multiple socio-ecological factors.Knowledge regarding the specific indicators and methods suitable for assessing crop production vulnerab...Crop production vulnerability to climate change in Northwest China depends upon multiple socio-ecological factors.Knowledge regarding the specific indicators and methods suitable for assessing crop production vulnerability is limited that address spatiotemporal variations across large and diverse zones.We propose an integrated assessment framework to quantify the vulnerability of crop production derived from crop yield sensitivity,exposure,and adaptive consequences across 338 counties in Northwest China during 1995–2014.Maps on these indices were generated using climatic and socioeconomic data with spatial mapping method.Different clusters of crop production vulnerability were then identified by a k-means cluster method to assess the heterogeneity of vulnerability at a regional scale.Results show that the vulnerability of crop production in 338 counties varies significantly in both geographical and socioeconomic aspects,specifically,vulnerability indicators are generally higher in Minhe,Menyuan,Hualong,and Ledu,and Xayar had the lowest value of vulnerability.This indicates that adaptation strategies for regional crop production need to focus on several levels,from the improvement of adaptive ability to crop yield fluctuation by promoting irrigation agriculture and optimizing limited water resources in typical arid areas,to agriculture-related financial policies incentivizing the capital investment and technology upgrade of crop production on traditional farming regions.This study provides convincing evidence that the factors related to socioeconomic policies are particularly alarming when a crop’s risk is compared to precipitation fluctuations.We recommend these findings be used to facilitate regional agriculture planning to reduce crop production vulnerability and ensure sustainable food security in specific regions.展开更多
Single-molecule tip-enhanced Raman spectroscopy(TERS)has emerged as an important technique for structural analysis at sub-molecular scale.Here in this work,we report a TERS study of an isolated free-base porphyrin mol...Single-molecule tip-enhanced Raman spectroscopy(TERS)has emerged as an important technique for structural analysis at sub-molecular scale.Here in this work,we report a TERS study of an isolated free-base porphyrin molecule adsorbed on the Ag(100)surface at cryogenic temperature(~7 K).Site-dependent TERS spectra reveal distinct local vibrational information for the chemical constituents within a single molecule.Moreover,distinct spatial features among different Raman peaks can be resolved from the TERS mapping images.These images are found to associate with related vibrational modes,enabling to resolve the mode associated with N-H bonds at the sub-nanometer level.This study will provide deep insights into the symmetry of adsorption configurations and local vibrational information within a single molecule.展开更多
Cognitive linguistics offers a novel approach to studying and elucidating language phenomena,with the theory of mental spaces being particularly adept at interpreting many“non-canonical”linguistic occurrences and pr...Cognitive linguistics offers a novel approach to studying and elucidating language phenomena,with the theory of mental spaces being particularly adept at interpreting many“non-canonical”linguistic occurrences and providing a fresh cognitive framework.The subjunctive mood,one of the three primary moods in English,is integral to English grammar.Yet,it remains a contentious topic within the field,with a lack of consensus among different linguistic schools regarding this significant grammatical category.The substantial role of human cognition in the construction and interpretation of the subjunctive mood’s meaning has been infrequently explored.This paper,from a cognitive perspective,employs the theory of mental spaces to discuss the English subjunctive mood,addressing the questions of its theoretical foundation,the reasons for its use,and the methods of its application.展开更多
Conventional soil maps generally contain one or more soil types within a single soil polygon.But their geographic locations within the polygon are not specified.This restricts current applications of the maps in site-...Conventional soil maps generally contain one or more soil types within a single soil polygon.But their geographic locations within the polygon are not specified.This restricts current applications of the maps in site-specific agricultural management and environmental modelling.We examined the utility of legacy pedon data for disaggregating soil polygons and the effectiveness of similarity-based prediction for making use of the under-or over-sampled legacy pedon data for the disaggregation.The method consisted of three steps.First,environmental similarities between the pedon sites and each location were computed based on soil formative environmental factors.Second,according to soil types of the pedon sites,the similarities were aggregated to derive similarity distribution for each soil type.Third,a hardening process was performed on the maps to allocate candidate soil types within the polygons.The study was conducted at the soil subgroup level in a semi-arid area situated in Manitoba,Canada.Based on 186 independent pedon sites,the evaluation of the disaggregated map of soil subgroups showed an overall accuracy of 67% and a Kappa statistic of 0.62.The map represented a better spatial pattern of soil subgroups in both detail and accuracy compared to a dominant soil subgroup map,which was commonly used in practice.Incorrect predictions mainly occurred in the agricultural plain area and the soil subgroups that are very similar in taxonomy,indicating that new environmental covariates need to be developed.We concluded that the combination of legacy pedon data with similarity-based prediction is an effective solution for soil polygon disaggregation.展开更多
Map is one of the communication means created by human being.Cartographers have been making efforts on the comparison of maps to natural languages so as to establish a"cartographic language"or"map langu...Map is one of the communication means created by human being.Cartographers have been making efforts on the comparison of maps to natural languages so as to establish a"cartographic language"or"map language".One of such efforts is to adopt the Shannon’s Information Theory originated in digital communication into cartography so as to establish an entropy-based cartographic communication theory.However,success has been very limited although research work had started as early as the mid-1960 s.It is then found that the bottleneck problem was the lack of appropriate measures for the spatial(configurational)information of(graphic and image)maps,as the classic Shannon entropy is only capable of characterizing statistical information but fails to capture the configurational information of(graphic and image)maps.Fortunately,after over 40-year development,some bottleneck problems have been solved.More precisely,generalized Shannon entropies for metric and thematic information of(graphic)maps have been developed and the first feasible solution for computing the Boltzmann entropy of image maps has been invented,which is capable of measuring the spatial information of not only numerical images but also categorical maps.With such progress,it is now feasible to build the"Information Theory of Cartography".In this paper,a framework for such a theory is proposed and some key issues are identified.For these issues,some have already been tackled while others still need efforts.As a result,a research agenda is set for future action.After all these issues are tackled,the theory will become matured so as to become a theoretic basis of cartography.It is expected that the Information Theory of Cartography will play an increasingly important role in the discipline of cartography because more and more researchers have advocated that information is more fundamental than matter and energy.展开更多
Sampling design(SD) plays a crucial role in providing reliable input for digital soil mapping(DSM) and increasing its efficiency.Sampling design, with a predetermined sample size and consideration of budget and spatia...Sampling design(SD) plays a crucial role in providing reliable input for digital soil mapping(DSM) and increasing its efficiency.Sampling design, with a predetermined sample size and consideration of budget and spatial variability, is a selection procedure for identifying a set of sample locations spread over a geographical space or with a good feature space coverage. A good feature space coverage ensures accurate estimation of regression parameters, while spatial coverage contributes to effective spatial interpolation.First, we review several statistical and geometric SDs that mainly optimize the sampling pattern in a geographical space and illustrate the strengths and weaknesses of these SDs by considering spatial coverage, simplicity, accuracy, and efficiency. Furthermore, Latin hypercube sampling, which obtains a full representation of multivariate distribution in geographical space, is described in detail for its development, improvement, and application. In addition, we discuss the fuzzy k-means sampling, response surface sampling, and Kennard-Stone sampling, which optimize sampling patterns in a feature space. We then discuss some practical applications that are mainly addressed by the conditioned Latin hypercube sampling with the flexibility and feasibility of adding multiple optimization criteria. We also discuss different methods of validation, an important stage of DSM, and conclude that an independent dataset selected from the probability sampling is superior for its free model assumptions. For future work, we recommend: 1) exploring SDs with both good spatial coverage and feature space coverage; 2) uncovering the real impacts of an SD on the integral DSM procedure;and 3) testing the feasibility and contribution of SDs in three-dimensional(3 D) DSM with variability for multiple layers.展开更多
As maritime activities increase globally,there is a greater dependency on technology in monitoring,control,and surveillance of vessel activity.One of the most prominent systems for monitoring vessel activity is the Au...As maritime activities increase globally,there is a greater dependency on technology in monitoring,control,and surveillance of vessel activity.One of the most prominent systems for monitoring vessel activity is the Automatic Identification System(AIS).An increase in both vessels fitted with AIS transponders and satellite and terrestrial AIS receivers has resulted in a significant increase in AIS messages received globally.This resultant rich spatial and temporal data source related to vessel activity provides analysts with the ability to perform enhanced vessel movement analytics,of which a pertinent example is the improvement of vessel location predictions.In this paper,we propose a novel strategy for predicting future locations of vessels making use of historic AIS data.The proposed method uses a Linear Regression Model(LRM)and utilizes historic AIS movement data in the form of a-priori generated spatial maps of the course over ground(LRMAC).The LRMAC is an accurate low complexity first-order method that is easy to implement operationally and shows promising results in areas where there is a consistency in the directionality of historic vessel movement.In areas where the historic directionality of vessel movement is diverse,such as areas close to harbors and ports,the LRMAC defaults to the LRM.The proposed LRMAC method is compared to the Single-Point Neighbor Search(SPNS),which is also a first-order method and has a similar level of computational complexity,and for the use case of predicting tanker and cargo vessel trajectories up to 8 hours into the future,the LRMAC showed improved results both in terms of prediction accuracy and execution time.展开更多
Temporal map is an isochronal map taking time as a measuring unit. It traces out the isochrones according to the discrepancy of the time distance between the different sites from the outside of the city and the down t...Temporal map is an isochronal map taking time as a measuring unit. It traces out the isochrones according to the discrepancy of the time distance between the different sites from the outside of the city and the down town, It can be clear and intuitional to show the different temporal relationships between the outside of the city and the city centre with the temporal map, The problem of traffic congestion, with its potential /br urban chaos, has increased dramatically with a growing number of vehicles and the continuing aerial expansion of Guangzhou. Both transit riders and drivers find it is a great difficulty to try to acquire the necessary information from urban spatial movements. Valuable time is lost due to the absence of good transportation information. So, the paper analyzes a case in Guangzhou communication with Geographic Information System （GIS）, and uses the most popular vehicles, including buses and taxis that are used to measure the temporal distance in the city. and then proposes the design of a new map that better reflects the status of urban communication, and attempts to change the relationship between one point and another potnt of travel, reducing the amount of time allocated to such. often complex, movements, This paper also points out the obstacles associated with Guangzhou＇s existing traffic congestion, and puts forward a strategy aimed at better d .efining the need of linking the temporal map to spatial map of Guangzhou.展开更多
Atomic layers of hexagonal boron nitride(h-BN)crystal are excellent candidates for structural materials as enabling ultrathin,two-dimensional(2D)nanoelectromechanical systems(NEMS)due to the outstanding mechanical pro...Atomic layers of hexagonal boron nitride(h-BN)crystal are excellent candidates for structural materials as enabling ultrathin,two-dimensional(2D)nanoelectromechanical systems(NEMS)due to the outstanding mechanical properties and very wide bandgap(5.9 eV)of h-BN.In this work,we report the experimental demonstration of h-BN 2D nanomechanical resonators vibrating at high and very high frequencies(from~5 to~70 MHz),and investigations of the elastic properties of h-BN by measuring the multimode resonant behavior of these devices.First,we demonstrate a dry-transferred doubly clamped h-BN membrane with~6.7 nm thickness,the thinnest h-BN resonator known to date.In addition,we fabricate circular drumhead h-BN resonators with thicknesses ranging from~9 to 292 nm,from which we measure up to eight resonance modes in the range of~18 to 35 MHz.Combining measurements and modeling of the rich multimode resonances,we resolve h-BN’s elastic behavior,including the transition from membrane to disk regime,with built-in tension ranging from 0.02 to 2 N m−1.The Young’s modulus of h-BN is determined to be EY≈392 GPa from the measured resonances.The ultrasensitive measurements further reveal subtle structural characteristics and mechanical properties of the suspended h-BN diaphragms,including anisotropic built-in tension and bulging,thus suggesting guidelines on how these effects can be exploited for engineering multimode resonant functions in 2D NEMS transducers.展开更多
Man-made impervious areas map is of great demand in environmen-tal and urbanization studies since impervious areas are considered as a key indication of urbanization,especially for circumpolar Arctic.However,to date,f...Man-made impervious areas map is of great demand in environmen-tal and urbanization studies since impervious areas are considered as a key indication of urbanization,especially for circumpolar Arctic.However,to date,finer resolution and spatially continuous imper-vious areas information remains scarce in the Arctic.In this study,we developed an accurate and complete circumpolar Arctic Man-made impervious areas(CAMI)map at a resolution of 10 m by combining Sentinel-1 C-band Synthetic Aperture Radar,Sentinel-2 multispectral images,OpenStreetMap,and ArcticDEM via Google Earth Engine platform.A random forest classifier model was trained and used to generate corresponding impervious areas map for the year 2020.The evaluation results suggested that CAMI was the most accurate with an overall accuracy of 86.36%and kappa coefficient of 70.73%as against the three existing impervious areas products.Based on the generated map and OpenStreetMap,we estimated that total imper-vious areas area in the Arctic has achieved 807.80 km2,of which roads,industrial and resident land were three major land use types,accounting for 54.08%,17.85%and 10.34%,respectively.The CAMI map will support for new application and provide advanced insight into the infrastructure vulnerability evaluation and environmental sustainability in the Arctic.展开更多
Constellation mapping has provided a great convenience to measure the performance of digital signal modulation in Euclid space. However, traditional in-phase and quadrature(IQ) plane is difficult to express the freque...Constellation mapping has provided a great convenience to measure the performance of digital signal modulation in Euclid space. However, traditional in-phase and quadrature(IQ) plane is difficult to express the frequency modulation scheme such as minimum shift keying(MSK) and the time domain modulation such as cyclic code shift keying(CCSK). How to represent the digital signal modulation visually through constellation mapping is an attractive problem. To address this issue, in this paper, the combined frequency and phase modulation are utilized to define a new kind of constellation mapping, where the phase and frequency are quantized to the same elements. The uniform geometric construction for combined phase and frequency modulation is redefined in the 3D cylindrical coordinate system based on frequency(f), in-phase component(I) and quadrature component(Q). In the new coordinates, the quadrature frequency-phase shift keying(QFPSK) is produced by the QPSK with dimensional rotation matrix and denoted by the reduced dual quaternion. Furthermore, the spatial extension from QFPSK to chirp cyclic shift keying(Chirp CSK) is analyzed with bandwidth efficiency and energy efficiency. At last, the QFPSK is combined with the 2D OFDM, yielding the image OFDM system.Experimental results verify the effectiveness of QFPSK in the proposed system with the time-varying wireless channel and frequency selective fading channel respectively.展开更多
Primordial germ cells(PGCs)are precursors of both male and female gametes as fundamental materials for organism development.The transcriptome,methylome,and chromatin accessibility profiles of PGCs in both mice and hum...Primordial germ cells(PGCs)are precursors of both male and female gametes as fundamental materials for organism development.The transcriptome,methylome,and chromatin accessibility profiles of PGCs in both mice and humans have been recently reported.However,little is known about the characteristics of PGCs at the protein levels,which directly exert cellular functions.Here,we construct landscapes of both proteome and 3D spatial distribution of mouse PGCs at E11.5,E13.5 and E16.5 days,the three critical developmental windows for PGCs'sex differentiation,female meiosis initiation and male mitotic arrest.In each developmental stage of PGCs,nearly 2,000–3,000 proteins are identified,among which specific functional pathways such as oxidative phosphorylation,DNA damage repair,and meiotic cell cycle are involved for different events during PGCs development.Interestingly,by 3D modeling we find that PGCs spatially cluster into around 1,300 nests in genital ridge at E11.5 and the nest number is not increased by the exponential proliferation of PGCs.Comparative analysis of our proteomic data with published transcriptomic data does not show a close correlation,meaning that the practically executive factors are beyond the transcriptome.Thus,our work offers a valuable resource for the systematic investigations of PGC development at protein level and spatial map.展开更多
Soil organic matter(SOM)is a key metric for assessing soil quality and crop yield potential.It plays a vital role in maintaining the ecological balance environment and promoting sustainable farming practices.This revi...Soil organic matter(SOM)is a key metric for assessing soil quality and crop yield potential.It plays a vital role in maintaining the ecological balance environment and promoting sustainable farming practices.This review examines the evolving trends in remote sensing(RS)-based SOM monitoring by analyzing 739 scholarly publications from the Web of Science database from 2003 to 2023 using a bibliometric approach.The study reveals that research on RS-based SOM monitoring has entered a rapid growth phase since 2018,with China and the United States as the main contributors and an extensive international cooperation network.In model construction,high frequency covariates such as soil pH,precipitation,temperature,and topography significantly improved the prediction accuracy.Data preprocessing methods such as Standard Normal Variables(SNV),Principal Component Analysis(PCA),and Multiple Scattering Correction(MSC)enhanced data consistency.Traditional statistical models are gradually being replaced by nonlinear machine learning and deep learning methods(CNN,XGBoost,andStacking),which are particularly good at handling complex high-dimensional data.Regional spectral libraries(OzSoil and AfSIS)excel in local accuracy,while global spectral libraries(ISRIC and LUCAS)are more suitable for cross-region modeling,and the migration learning technique effectively improves the model generalization ability in low data regions.Integrated models(CNN-LSTM and GAN)have significant advantages in capturing the spatial and temporal dynamics of SOMs,and uncertainty quantification methods(Bayesian inference,Monte Carlo simulation)enhance the reliability of the models in multi-source data and data-scarce scenarios.Future research should focus on further optimization of multi-source data fusion and uncertainty quantification to promote the development and applicability of RS-based SOM monitoring techniques for precision soil management and sustainable agriculture.展开更多
基金support from DARPAC.B., D.A., H.P. and J.C.S. acknowledge the NSF (award #2338346) for financial support.This work was carried out in the Materials Research Laboratory Central Research Facilities, University of Illinois. Carpenter Technology is acknowledged for providing the 718 material. Morad Behandish and Adrian Lew are acknowledged for their support and leadership. Tresa Pollock, McLean Echlin and James Lamb are acknowledged for their support on the EBSD sharpness calculations. Marat Latypov, Marie Charpagne, and Florian Strub are gratefully acknowledged for their support and insightful discussions.
文摘To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors.This need is particularly relevant for metallic materials processed through additive manufacturing,which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials.Furthermore,capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties.To address these challenges,we propose the physical spatial mapping of metal diffraction latent space features.This approach integrates(i)point diffraction data encoding via variational autoencoders or contrastive learning and(ii)the physical mapping of the encoded values.Together,these steps offer a method to comprehensively describe metal microstructures.We demonstrate this approach on a wrought and additively manufactured alloy,showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models.This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.
基金supported by the Beijing Municipal Natural Science Foundation(L246017 and Z220015)the National Natural Science Foundation of China(NSFC)(T2425003,52272277,92164202,62304264,T2122010,and 52171239)+3 种基金Neu Cyber Neuro Tech(Beijing)Company,China(NC-2023-HE-02)Tsinghua University Initiative Scientific Research Program(2024Z02ORD001)the Science and Technology Program of Guangzhou City(2024B01J0079)the Beijing Nova Program(20230484254)。
文摘Realizing precise recording with large populations of neurons has been a long-standing goal in developing next-generation brain-machine interfaces(BMIs)[1,2].Specifically,flexible electrocorticography(ECoG)devices placed on the cerebral cortex provide a nonpenetrating means to measure population-level coordinated neural activities across wide cortical areas,and have been successfully applied for speech synthesis,motor decoding,and seizure localization[3].
文摘Remote sensing has played a pivotal role in our understanding of the geometry of dykes and dyke swarms on Earth,Venus and Mars(West and Ernst,1991;Mege and Masson,1995;Ernst et al.,2005).Since the 1970’s
基金Supported by Shahrekord University,Shahrekord,Iran
文摘Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with artificial neural networks,were compared to predict spatial variation of saturated hydraulic conductivity from environmental covariates.All methods except ordinary kriging allow for inclusion of secondary variables.The secondary spatial information used was terrain attributes including elevation,slope gradient,slope aspect,profile curvature and contour curvature.A multiple jackknifing procedure was used as a validation method.Root mean square error (RMSE) and mean absolute error (MAE) were used as the validation indices,with the mean RMSE and mean MAE used to judge the prediction quality.Prediction performance by ordinary kriging was poor,indicating that prediction of saturated hydraulic conductivity can be improved by incorporating ancillary data such as terrain variables.Kriging combined with artificial neural networks performed best.These prediction models made better use of ancillary information in predicting saturated hydraulic conductivity compared with the competing models.The combination of geostatistical predictors with neural computing techniques offers more capability for incorporating ancillary information in predictive soil mapping.There is great potential for further research and development of hybrid methods for digital soil mapping.
文摘Osteoarthritis(OA)is a degenerative skeletal condition marked by the loss of articular cartilage and changes to subchondral bone homeostasis.Treatments for OA beyond full joint replacement are lacking primarily due to gaps in molecular knowledge of the biological drivers of disease.Mass Spectrometry Imaging(MSI)enables molecular spatial mapping of the proteomic landscape of tissues.Histologic sections of human tibial plateaus from knees of human OA patients and cadaveric controls were treated with collagenase III to target extracellular matrix(ECM)proteins prior to MS Imaging of bone and cartilage proteins.Spatial MS imaging of the knee identified distinct areas of joint damage to the subchondral bone underneath areas of lost cartilage.This damaged bone signature extended underneath remaining cartilage in OA joints,indicating subchondral bone remodeling could occur before full thickness cartilage loss in OA.Specific ECM peptide markers from OA-affected medial tibial plateaus were compared to their healthier lateral halves from the same patient,as well as to healthy,age-matched cadaveric knees.Overall,31 peptide candidates from ECM proteins,including Collagen alpha-1(Ⅰ),Collagen alpha-1(Ⅲ),and surprisingly,Collagen alpha-1(Ⅵ)and Collagen alpha-3(Ⅵ),exhibited significantly elevated abundance in diseased tissues.Additionally,highly specific hydroxyproline-containing collagen peptides,mainly from collagen typeⅠ,dominated OA subchondral bone directly under regions of lost cartilage but not areas where cartilage remained intact.A separate analysis of synovial fluid from a second cohort of OA patients found similar regulation of collagens and ECM proteins via LC-MS/MS demonstrating that markers of subchondral bone remodeling discovered by MALDI-MS may be detectable as biomarkers in biofluid samples.The identification of specific protein markers for subchondral bone remodeling in OA advances our molecular understanding of disease progression in OA and provides potential new biomarkers for OA detection and disease grading.
文摘A quick and accurate extraction of dominant colors of background images is the basis of adaptive camouflage design.This paper proposes a Color Image Quick Fuzzy C-Means(CIQFCM)clustering algorithm based on clustering spatial mapping.First,the clustering sample space was mapped from the image pixels to the quantized color space,and several methods were adopted to compress the amount of clustering samples.Then,an improved pedigree clustering algorithm was applied to obtain the initial class centers.Finally,CIQFCM clustering algorithm was used for quick extraction of dominant colors of background image.After theoretical analysis of the effect and efficiency of the CIQFCM algorithm,several experiments were carried out to discuss the selection of proper quantization intervals and to verify the effect and efficiency of the CIQFCM algorithm.The results indicated that the value of quantization intervals should be set to 4,and the proposed algorithm could improve the clustering efficiency while maintaining the clustering effect.In addition,as the image size increased from 128×128 to 1024×1024,the efficiency improvement of CIQFCM algorithm was increased from 6.44 times to 36.42 times,which demonstrated the significant advantage of CIQFCM algorithm in dominant colors extraction of large-size images.
文摘The electrical performance of radomes on high-speed aircraft can be influenced by the thermal and mechanical loads produced during high-speed flight,which can affect the detection dis-tance and accuracy of the guidance system.This paper presents a new method that uses the Finite Difference Time Domain(FDTD)method to calculate the electrical performance of radomes under Thermo-Mechanical-Electrical(TME)coupling.This method can accurately characterize the effects of material dielectric temperature drift and structural deformation on the electrical performance of the radome under flight conditions,enabling high-precision full-wave calculations of the broadband electrical performance of the radome.The method initiates by utilizing a Finite Element Grid Model(FE-GM)of the radome to sequentially acquire the radome's response temperature field and structural deformation field through thermal and mechanical simulations.Subsequently,spatial mapping techniques are developed to accurately incorporate the dielectric temperature drift and structural deformation of the radome into its Yee grid Electromagnetic(EM)simulation model.A verification case was designed to test the proposed method,and the results confirmed its high computational accuracy.Additionally,the effectiveness and necessity of the method were further demonstrated by analyzing the electrical performance of a fused silica ceramic radome used on a high-speed aircraft.
基金funded by the National Natural Science Foundation of China(41601184)the State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau(A314021402-202110)。
文摘Crop production vulnerability to climate change in Northwest China depends upon multiple socio-ecological factors.Knowledge regarding the specific indicators and methods suitable for assessing crop production vulnerability is limited that address spatiotemporal variations across large and diverse zones.We propose an integrated assessment framework to quantify the vulnerability of crop production derived from crop yield sensitivity,exposure,and adaptive consequences across 338 counties in Northwest China during 1995–2014.Maps on these indices were generated using climatic and socioeconomic data with spatial mapping method.Different clusters of crop production vulnerability were then identified by a k-means cluster method to assess the heterogeneity of vulnerability at a regional scale.Results show that the vulnerability of crop production in 338 counties varies significantly in both geographical and socioeconomic aspects,specifically,vulnerability indicators are generally higher in Minhe,Menyuan,Hualong,and Ledu,and Xayar had the lowest value of vulnerability.This indicates that adaptation strategies for regional crop production need to focus on several levels,from the improvement of adaptive ability to crop yield fluctuation by promoting irrigation agriculture and optimizing limited water resources in typical arid areas,to agriculture-related financial policies incentivizing the capital investment and technology upgrade of crop production on traditional farming regions.This study provides convincing evidence that the factors related to socioeconomic policies are particularly alarming when a crop’s risk is compared to precipitation fluctuations.We recommend these findings be used to facilitate regional agriculture planning to reduce crop production vulnerability and ensure sustainable food security in specific regions.
基金supported by the National Key R&D Program of China(No.2016YFA0200600)the National Natural Science Foundation of China,the Chinese Academy of Sciences+1 种基金Anhui Initiative in Quantum Information TechnologiesAtif Ghafoor acknowledges support by the China Scholarship Council
文摘Single-molecule tip-enhanced Raman spectroscopy(TERS)has emerged as an important technique for structural analysis at sub-molecular scale.Here in this work,we report a TERS study of an isolated free-base porphyrin molecule adsorbed on the Ag(100)surface at cryogenic temperature(~7 K).Site-dependent TERS spectra reveal distinct local vibrational information for the chemical constituents within a single molecule.Moreover,distinct spatial features among different Raman peaks can be resolved from the TERS mapping images.These images are found to associate with related vibrational modes,enabling to resolve the mode associated with N-H bonds at the sub-nanometer level.This study will provide deep insights into the symmetry of adsorption configurations and local vibrational information within a single molecule.
文摘Cognitive linguistics offers a novel approach to studying and elucidating language phenomena,with the theory of mental spaces being particularly adept at interpreting many“non-canonical”linguistic occurrences and providing a fresh cognitive framework.The subjunctive mood,one of the three primary moods in English,is integral to English grammar.Yet,it remains a contentious topic within the field,with a lack of consensus among different linguistic schools regarding this significant grammatical category.The substantial role of human cognition in the construction and interpretation of the subjunctive mood’s meaning has been infrequently explored.This paper,from a cognitive perspective,employs the theory of mental spaces to discuss the English subjunctive mood,addressing the questions of its theoretical foundation,the reasons for its use,and the methods of its application.
基金supported by the National Natural Science Foundation of China (41130530,91325301,41431177,41571212,41401237)the Project of "One-Three-Five" Strategic Planning & Frontier Sciences of the Institute of Soil Science,Chinese Academy of Sciences (ISSASIP1622)+1 种基金the Government Interest Related Program between Canadian Space Agency and Agriculture and Agri-Food,Canada (13MOA01002)the Natural Science Research Program of Jiangsu Province (14KJA170001)
文摘Conventional soil maps generally contain one or more soil types within a single soil polygon.But their geographic locations within the polygon are not specified.This restricts current applications of the maps in site-specific agricultural management and environmental modelling.We examined the utility of legacy pedon data for disaggregating soil polygons and the effectiveness of similarity-based prediction for making use of the under-or over-sampled legacy pedon data for the disaggregation.The method consisted of three steps.First,environmental similarities between the pedon sites and each location were computed based on soil formative environmental factors.Second,according to soil types of the pedon sites,the similarities were aggregated to derive similarity distribution for each soil type.Third,a hardening process was performed on the maps to allocate candidate soil types within the polygons.The study was conducted at the soil subgroup level in a semi-arid area situated in Manitoba,Canada.Based on 186 independent pedon sites,the evaluation of the disaggregated map of soil subgroups showed an overall accuracy of 67% and a Kappa statistic of 0.62.The map represented a better spatial pattern of soil subgroups in both detail and accuracy compared to a dominant soil subgroup map,which was commonly used in practice.Incorrect predictions mainly occurred in the agricultural plain area and the soil subgroups that are very similar in taxonomy,indicating that new environmental covariates need to be developed.We concluded that the combination of legacy pedon data with similarity-based prediction is an effective solution for soil polygon disaggregation.
基金National Natural Science Foundation of China(Nos.41930104,41971330)Hong Kong Research Grants Council General Research Fund(No.152219/18E)。
文摘Map is one of the communication means created by human being.Cartographers have been making efforts on the comparison of maps to natural languages so as to establish a"cartographic language"or"map language".One of such efforts is to adopt the Shannon’s Information Theory originated in digital communication into cartography so as to establish an entropy-based cartographic communication theory.However,success has been very limited although research work had started as early as the mid-1960 s.It is then found that the bottleneck problem was the lack of appropriate measures for the spatial(configurational)information of(graphic and image)maps,as the classic Shannon entropy is only capable of characterizing statistical information but fails to capture the configurational information of(graphic and image)maps.Fortunately,after over 40-year development,some bottleneck problems have been solved.More precisely,generalized Shannon entropies for metric and thematic information of(graphic)maps have been developed and the first feasible solution for computing the Boltzmann entropy of image maps has been invented,which is capable of measuring the spatial information of not only numerical images but also categorical maps.With such progress,it is now feasible to build the"Information Theory of Cartography".In this paper,a framework for such a theory is proposed and some key issues are identified.For these issues,some have already been tackled while others still need efforts.As a result,a research agenda is set for future action.After all these issues are tackled,the theory will become matured so as to become a theoretic basis of cartography.It is expected that the Information Theory of Cartography will play an increasingly important role in the discipline of cartography because more and more researchers have advocated that information is more fundamental than matter and energy.
基金funded by the Natural Science and Engineering Research Council (NSERC) of Canada (No. RGPIN-2014-04100)
文摘Sampling design(SD) plays a crucial role in providing reliable input for digital soil mapping(DSM) and increasing its efficiency.Sampling design, with a predetermined sample size and consideration of budget and spatial variability, is a selection procedure for identifying a set of sample locations spread over a geographical space or with a good feature space coverage. A good feature space coverage ensures accurate estimation of regression parameters, while spatial coverage contributes to effective spatial interpolation.First, we review several statistical and geometric SDs that mainly optimize the sampling pattern in a geographical space and illustrate the strengths and weaknesses of these SDs by considering spatial coverage, simplicity, accuracy, and efficiency. Furthermore, Latin hypercube sampling, which obtains a full representation of multivariate distribution in geographical space, is described in detail for its development, improvement, and application. In addition, we discuss the fuzzy k-means sampling, response surface sampling, and Kennard-Stone sampling, which optimize sampling patterns in a feature space. We then discuss some practical applications that are mainly addressed by the conditioned Latin hypercube sampling with the flexibility and feasibility of adding multiple optimization criteria. We also discuss different methods of validation, an important stage of DSM, and conclude that an independent dataset selected from the probability sampling is superior for its free model assumptions. For future work, we recommend: 1) exploring SDs with both good spatial coverage and feature space coverage; 2) uncovering the real impacts of an SD on the integral DSM procedure;and 3) testing the feasibility and contribution of SDs in three-dimensional(3 D) DSM with variability for multiple layers.
文摘As maritime activities increase globally,there is a greater dependency on technology in monitoring,control,and surveillance of vessel activity.One of the most prominent systems for monitoring vessel activity is the Automatic Identification System(AIS).An increase in both vessels fitted with AIS transponders and satellite and terrestrial AIS receivers has resulted in a significant increase in AIS messages received globally.This resultant rich spatial and temporal data source related to vessel activity provides analysts with the ability to perform enhanced vessel movement analytics,of which a pertinent example is the improvement of vessel location predictions.In this paper,we propose a novel strategy for predicting future locations of vessels making use of historic AIS data.The proposed method uses a Linear Regression Model(LRM)and utilizes historic AIS movement data in the form of a-priori generated spatial maps of the course over ground(LRMAC).The LRMAC is an accurate low complexity first-order method that is easy to implement operationally and shows promising results in areas where there is a consistency in the directionality of historic vessel movement.In areas where the historic directionality of vessel movement is diverse,such as areas close to harbors and ports,the LRMAC defaults to the LRM.The proposed LRMAC method is compared to the Single-Point Neighbor Search(SPNS),which is also a first-order method and has a similar level of computational complexity,and for the use case of predicting tanker and cargo vessel trajectories up to 8 hours into the future,the LRMAC showed improved results both in terms of prediction accuracy and execution time.
基金the Projects of the National Construction Foundation of China (Grant No. 05-R2-24)Education Bureau Foundation in Guangzhou (Grant No. 2029)Philosophy and Social Science Foundation in Guangzhou (Grant No. 07Z1)
文摘Temporal map is an isochronal map taking time as a measuring unit. It traces out the isochrones according to the discrepancy of the time distance between the different sites from the outside of the city and the down town, It can be clear and intuitional to show the different temporal relationships between the outside of the city and the city centre with the temporal map, The problem of traffic congestion, with its potential /br urban chaos, has increased dramatically with a growing number of vehicles and the continuing aerial expansion of Guangzhou. Both transit riders and drivers find it is a great difficulty to try to acquire the necessary information from urban spatial movements. Valuable time is lost due to the absence of good transportation information. So, the paper analyzes a case in Guangzhou communication with Geographic Information System （GIS）, and uses the most popular vehicles, including buses and taxis that are used to measure the temporal distance in the city. and then proposes the design of a new map that better reflects the status of urban communication, and attempts to change the relationship between one point and another potnt of travel, reducing the amount of time allocated to such. often complex, movements, This paper also points out the obstacles associated with Guangzhou＇s existing traffic congestion, and puts forward a strategy aimed at better d .efining the need of linking the temporal map to spatial map of Guangzhou.
基金We are grateful for support from the National Academy of Engineering(NAE)Grainger Foundation Frontier of Engineering(FOE)Award(FOE2013-005)the National Science Foundation CAREER Award(Grant ECCS-1454570)partial support from the Department of Energy(DOE)EERE Award(Grant DE-EE0006719),a ThinkEnergy Fellowship(X.-Q.Zheng),and the Case School of Engineering.A portion of the device fabrication was performed at the Cornell NanoScale Science and Technology Facility(CNF),a member of the National Nanotechnology Infrastructure Network(NNIN)supported by the National Science Foundation(Grant ECCS-0335765).
文摘Atomic layers of hexagonal boron nitride(h-BN)crystal are excellent candidates for structural materials as enabling ultrathin,two-dimensional(2D)nanoelectromechanical systems(NEMS)due to the outstanding mechanical properties and very wide bandgap(5.9 eV)of h-BN.In this work,we report the experimental demonstration of h-BN 2D nanomechanical resonators vibrating at high and very high frequencies(from~5 to~70 MHz),and investigations of the elastic properties of h-BN by measuring the multimode resonant behavior of these devices.First,we demonstrate a dry-transferred doubly clamped h-BN membrane with~6.7 nm thickness,the thinnest h-BN resonator known to date.In addition,we fabricate circular drumhead h-BN resonators with thicknesses ranging from~9 to 292 nm,from which we measure up to eight resonance modes in the range of~18 to 35 MHz.Combining measurements and modeling of the rich multimode resonances,we resolve h-BN’s elastic behavior,including the transition from membrane to disk regime,with built-in tension ranging from 0.02 to 2 N m−1.The Young’s modulus of h-BN is determined to be EY≈392 GPa from the measured resonances.The ultrasensitive measurements further reveal subtle structural characteristics and mechanical properties of the suspended h-BN diaphragms,including anisotropic built-in tension and bulging,thus suggesting guidelines on how these effects can be exploited for engineering multimode resonant functions in 2D NEMS transducers.
基金the National Key R&D Program of China[2018YFC1407103 and 2017YFA0604401]Annual Report(2022)on Remote Sensing Monitoring of Global Ecosystems and Environment[TC210E01B].
文摘Man-made impervious areas map is of great demand in environmen-tal and urbanization studies since impervious areas are considered as a key indication of urbanization,especially for circumpolar Arctic.However,to date,finer resolution and spatially continuous imper-vious areas information remains scarce in the Arctic.In this study,we developed an accurate and complete circumpolar Arctic Man-made impervious areas(CAMI)map at a resolution of 10 m by combining Sentinel-1 C-band Synthetic Aperture Radar,Sentinel-2 multispectral images,OpenStreetMap,and ArcticDEM via Google Earth Engine platform.A random forest classifier model was trained and used to generate corresponding impervious areas map for the year 2020.The evaluation results suggested that CAMI was the most accurate with an overall accuracy of 86.36%and kappa coefficient of 70.73%as against the three existing impervious areas products.Based on the generated map and OpenStreetMap,we estimated that total imper-vious areas area in the Arctic has achieved 807.80 km2,of which roads,industrial and resident land were three major land use types,accounting for 54.08%,17.85%and 10.34%,respectively.The CAMI map will support for new application and provide advanced insight into the infrastructure vulnerability evaluation and environmental sustainability in the Arctic.
基金supported in part by National Natural Science Foundation of China(Grant Nos.61501051,61421001)Ph.D.Programs Foundation of Ministry of Education of China(Grant No.20121101130001)
文摘Constellation mapping has provided a great convenience to measure the performance of digital signal modulation in Euclid space. However, traditional in-phase and quadrature(IQ) plane is difficult to express the frequency modulation scheme such as minimum shift keying(MSK) and the time domain modulation such as cyclic code shift keying(CCSK). How to represent the digital signal modulation visually through constellation mapping is an attractive problem. To address this issue, in this paper, the combined frequency and phase modulation are utilized to define a new kind of constellation mapping, where the phase and frequency are quantized to the same elements. The uniform geometric construction for combined phase and frequency modulation is redefined in the 3D cylindrical coordinate system based on frequency(f), in-phase component(I) and quadrature component(Q). In the new coordinates, the quadrature frequency-phase shift keying(QFPSK) is produced by the QPSK with dimensional rotation matrix and denoted by the reduced dual quaternion. Furthermore, the spatial extension from QFPSK to chirp cyclic shift keying(Chirp CSK) is analyzed with bandwidth efficiency and energy efficiency. At last, the QFPSK is combined with the 2D OFDM, yielding the image OFDM system.Experimental results verify the effectiveness of QFPSK in the proposed system with the time-varying wireless channel and frequency selective fading channel respectively.
基金supported by the National Key Research and Development Program of China(2017YFC1001501,2016YFC1000604,2018YFC1004002)the Foundation for Innovative Research Groups of National Natural Science Foundation of China(81521002)。
文摘Primordial germ cells(PGCs)are precursors of both male and female gametes as fundamental materials for organism development.The transcriptome,methylome,and chromatin accessibility profiles of PGCs in both mice and humans have been recently reported.However,little is known about the characteristics of PGCs at the protein levels,which directly exert cellular functions.Here,we construct landscapes of both proteome and 3D spatial distribution of mouse PGCs at E11.5,E13.5 and E16.5 days,the three critical developmental windows for PGCs'sex differentiation,female meiosis initiation and male mitotic arrest.In each developmental stage of PGCs,nearly 2,000–3,000 proteins are identified,among which specific functional pathways such as oxidative phosphorylation,DNA damage repair,and meiotic cell cycle are involved for different events during PGCs development.Interestingly,by 3D modeling we find that PGCs spatially cluster into around 1,300 nests in genital ridge at E11.5 and the nest number is not increased by the exponential proliferation of PGCs.Comparative analysis of our proteomic data with published transcriptomic data does not show a close correlation,meaning that the practically executive factors are beyond the transcriptome.Thus,our work offers a valuable resource for the systematic investigations of PGC development at protein level and spatial map.
基金funded by the National Key Research and Development Program(2022YFD2001501)the National Natural Science Foundation of China(32371997)the Qing Lan Project of Jiangsu Universities.
文摘Soil organic matter(SOM)is a key metric for assessing soil quality and crop yield potential.It plays a vital role in maintaining the ecological balance environment and promoting sustainable farming practices.This review examines the evolving trends in remote sensing(RS)-based SOM monitoring by analyzing 739 scholarly publications from the Web of Science database from 2003 to 2023 using a bibliometric approach.The study reveals that research on RS-based SOM monitoring has entered a rapid growth phase since 2018,with China and the United States as the main contributors and an extensive international cooperation network.In model construction,high frequency covariates such as soil pH,precipitation,temperature,and topography significantly improved the prediction accuracy.Data preprocessing methods such as Standard Normal Variables(SNV),Principal Component Analysis(PCA),and Multiple Scattering Correction(MSC)enhanced data consistency.Traditional statistical models are gradually being replaced by nonlinear machine learning and deep learning methods(CNN,XGBoost,andStacking),which are particularly good at handling complex high-dimensional data.Regional spectral libraries(OzSoil and AfSIS)excel in local accuracy,while global spectral libraries(ISRIC and LUCAS)are more suitable for cross-region modeling,and the migration learning technique effectively improves the model generalization ability in low data regions.Integrated models(CNN-LSTM and GAN)have significant advantages in capturing the spatial and temporal dynamics of SOMs,and uncertainty quantification methods(Bayesian inference,Monte Carlo simulation)enhance the reliability of the models in multi-source data and data-scarce scenarios.Future research should focus on further optimization of multi-source data fusion and uncertainty quantification to promote the development and applicability of RS-based SOM monitoring techniques for precision soil management and sustainable agriculture.
