Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively u...Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.展开更多
This paper discusses the problem of low-elevation target height estimation for multiple-input multiple-output(MIMO)radar in multipath environments.The beamspace compresses the data and is ideal for reducing the comput...This paper discusses the problem of low-elevation target height estimation for multiple-input multiple-output(MIMO)radar in multipath environments.The beamspace compresses the data and is ideal for reducing the computational burden of elevation estimation.To obtain the height parameter of the target accurately,we propose a height estimation method based on a beamspace joint alternating iterative(BJAI)algorithm in MIMO radar.This method mainly converts the reduced-dimensional MIMO radar element space data into beamspace data and whitens them to improve the reliability.Then,a simplified model is used to obtain the initial value of the elevation,and we combine the reflection coefficient and the target elevation angle for alternate estimation.Finally,we calculate the target height using the obtained elevation information.Simulation results verify that the proposed algorithm has high estimation accuracy and strong robustness.展开更多
Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view re...Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.展开更多
We estimate tree heights using polarimetric interferometric synthetic aperture radar(PolInSAR)data constructed by the dual-polarization(dual-pol)SAR data and random volume over the ground(RVoG)model.Considering the Se...We estimate tree heights using polarimetric interferometric synthetic aperture radar(PolInSAR)data constructed by the dual-polarization(dual-pol)SAR data and random volume over the ground(RVoG)model.Considering the Sentinel-1 SAR dual-pol(SVV,vertically transmitted and vertically received and SVH,vertically transmitted and horizontally received)configuration,one notes that S_(HH),the horizontally transmitted and horizontally received scattering element,is unavailable.The S_(HH)data were constructed using the SVH data,and polarimetric SAR(PolSAR)data were obtained.The proposed approach was first verified in simulation with satisfactory results.It was next applied to construct PolInSAR data by a pair of dual-pol Sentinel-1A data at Duke Forest,North Carolina,USA.According to local observations and forest descriptions,the range of estimated tree heights was overall reasonable.Comparing the heights with the ICESat-2 tree heights at 23 sampling locations,relative errors of 5 points were within±30%.Errors of 8 points ranged from 30%to 40%,but errors of the remaining 10 points were>40%.The results should be encouraged as error reduction is possible.For instance,the construction of PolSAR data should not be limited to using SVH,and a combination of SVH and SVV should be explored.Also,an ensemble of tree heights derived from multiple PolInSAR data can be considered since tree heights do not vary much with time frame in months or one season.展开更多
In this paper, using the generalized Omori-Yau maximum principle, we obtain height estimates for spacelike hypersurface in a generalized Robertson-Walker （GRW） space- time with constant higher order mean curvature a...In this paper, using the generalized Omori-Yau maximum principle, we obtain height estimates for spacelike hypersurface in a generalized Robertson-Walker （GRW） space- time with constant higher order mean curvature and whose boundary is contained in a slice. Furthermore, we apply these results to draw some topological conclusions. Finally, considering the Omori-Yau maximum principle for the Laplacian and for more general elliptic trace type differential operators, we have some further non-existence results.展开更多
In energy-dispersive X-ray fluorescence spectroscopy,the estimation of the pulse amplitude determines the accuracy of the spectrum measurement.The error generated by the amplitude estimation of the pulse output distor...In energy-dispersive X-ray fluorescence spectroscopy,the estimation of the pulse amplitude determines the accuracy of the spectrum measurement.The error generated by the amplitude estimation of the pulse output distorted by the measurement system leads to false peaks in the measured spectrum.To eliminate these false peaks and achieve an accurate estimation of the distorted pulse amplitude,a composite neural network model is proposed,which embeds long and short-term memory(LSTM)into the UNet structure.The UNet network realizes the fusion of pulse sequence features and the LSTM model realizes pulse amplitude estimation.The model is trained using simulated pulse datasets with different amplitudes and distortion times.For the pulse height estimation,the average relative error of the trained model on the test set was approximately 0.64%,which is 27.37% lower than that of the traditional trapezoidal shaping algorithm.Offline processing of a standard iron source further validated the pulse height estimation performance of the UNet-LSTM model.After estimating the amplitude of the distorted pulses using the model,the false peak area was reduced by approximately 91% over the full spectrum and was corrected to the characteristic peak region of interest(ROI).The corrected peak area accounted for approximately 1.32%of the characteristic peak ROI area.The results indicate that the model can accurately estimate the height of distorted pulses and has substantial corrective effects on false peaks.展开更多
With their widespread utilization, cut-to-length harvesters have become a major source of ‘‘big data’’ for forest management as they constantly capture, and provide a daily flow of, information on log production a...With their widespread utilization, cut-to-length harvesters have become a major source of ‘‘big data’’ for forest management as they constantly capture, and provide a daily flow of, information on log production and assortment over large operational areas. Harvester data afford the calculation of the total log length between the stump and the last cut but not the total height of trees. They also contain the length and end diameters of individual logs but not always the diameter at breast height overbark（DBHOB） of harvested stems largely because of time lapse, operating and processing issues and other system deficiencies. Even when DBHOB is extracted from harvester data, errors and/or bias of the machine measurements due to the variation in the stump height of harvested stems from that specified for the harvester head prior to harvesting and diameter measurement errors may need to be corrected. This study developed（1） a system of equations for estimating DBHOB of trees from diameter overbark（DOB） measured by a harvester head at any height up to 3 m above ground level and（2） an equation to predict the total height of harvested stems in P. radiata plantations from harvester data. To generate the data required for this purpose, cut-to-length simulations of more than 3000 trees with detailed taper measurements were carried out in the computer using the cutting patterns extracted from the harvester data and stump height survey data from clearfall operations. The equation predicted total tree height from DBHOB, total log length and the small end diameter of the top log. Prediction accuracy for total tree height was evaluated both globally over the entire data space and locally within partitioned subspaces through benchmarking statistics. These statistics were better than that of the conventional height-diameter equations for P. radiata found in the literature, even when they incorporated stand age and the average height and diameter of dominant trees in the stand as predictors. So this equation when used with harvester data would outperform the conventional equations in tree height prediction. Tree and stand reconstructions of the harvested forest is the necessary first step to provide the essential link of harvester data to conventional inventory, remote sensing imagery and Li DAR data. The equations developed in this study will provide such a linkage for the most effective combined use of harvester data in predicting the attributes of individual trees, stands and forests, and product recovery for the management and planning of P. radiata plantations in New South Wales, Australia.展开更多
Low-angle estimation for very high frequency(VHF)radar is a difficult problem due to the multipath effect in the radar field,especially in complex scenarios where the reflection condition is unknown.To deal with this ...Low-angle estimation for very high frequency(VHF)radar is a difficult problem due to the multipath effect in the radar field,especially in complex scenarios where the reflection condition is unknown.To deal with this problem,we propose an algorithm of target height and multipath attenuation joint estimation.The amplitude of the surface reflection coefficient is estimated by the characteristic of the data itself,and it is assumed that there is no reflected signal when the amplitude is very small.The phase of the surface reflection coefficient and the phase difference between the direct and reflected signals are searched as the same part,and this represents the multipath phase attenuation.The Cramer-Rao bound of the proposed algorithm is also derived.Finally,computer simulations and real data processing results show that the proposed algorithm has good estimation performance under complex scenarios and works well with only one snapshot.展开更多
Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the ta...Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the target data according to the dominant species could improve the subsequent predictions of species-specific attributes in particular in study areas strongly dominated by certain species. Methods： We tested this hypothesis and an operational potential to improve the predictions of timber volumes, stratified to Scots pine, Norway spruce and deciduous trees, in a conifer forest dominated by the pine species. We derived predictor features from airborne laser scanning （ALS） data and used Most Similar Neighbor （MSN） and Seemingly Unrelated Regression （SUR） as examples of non-parametric and parametric prediction methods, respectively Results： The relationships between the ALS features and the volumes of the aforementioned species were considerably different depending on the dominant species. Incorporating the observed dominant species inthe predictions improved the root mean squared errors by 13.3-16.4 % and 12.6-28.9 % based on MSN and SUR, respectively, depending on the species. Predicting the dominant species based on a linear discriminant analysis had an overall accuracy of only 76 % at best, which degraded the accuracies of the predicted volumes. Consequently, the predictions that did not consider the dominant species were more accurate than those refined with the predicted species. The MSN method gave slightly better results than models fitted with SUR. Conclusions： According to our results, incorporating information on the dominant species has a clear potential to improve the subsequent predictions of species-specific forest attributes. Determining the dominant species based solely on ALS data is deemed challenging, but important in particular in areas where the species composition is otherwise seemingly homogeneous except being dominated by certain species.展开更多
Synthetic aperture radar(SAR)records important information about the interaction of electromagnetic waves with the Earth’s surface.However,long-term and high-resolution backscatter coefficient data are still lacking ...Synthetic aperture radar(SAR)records important information about the interaction of electromagnetic waves with the Earth’s surface.However,long-term and high-resolution backscatter coefficient data are still lacking in many urban studies(e.g.,building height estimation).Here,we proposed a framework to reconstruct the 1-km backscatter coefficient in 1990-2022 utilizing the Sentinel-1 Ground Range Detected data and Landsat time series data in the Jing-Jin-Ji(JJJ)region.First,we developed a regression model to convert the optical signals from Landsat into backscatter coefficients as the Sentinel-1 data,using observations from 2015 to 2022.Then,we reconstructed backscatter coefficients from 1990 to 2022 using the long-term Landsat data.Using the reconstructed backscatter coefficients,we analyzed the dynamic patterns of building height over the past decades.The proposed approach performs well on estimating the backscatter coefficient and its spatial pattern,with the annual mean absolute error,root mean square error,and R^(2) of 1.10 dB,1.50 dB,and 0.64,respectively.The temporal trends revealed from the reconstructed backscatter data are reliable compared with satellite observations at a relatively coarse resolution,with Pearson’s coefficients above 0.92 in 6 sample cities.The derived building height from the reconstructed SAR data indicates that the JJJ region experienced a noticeable upward expansion in 1990-2022,e.g.,Beijing has the fastest growth rate of 0.420 km^(3)/decade regarding the total building volumes.The proposed framework of reconstructing SAR data from optical satellite images provides a new insight to complement the long-term and high-resolution backscatter from local to global scales.展开更多
基金National Key R&D Program of China(No.2022ZD0118401).
文摘Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.
基金Project supported by the National Natural Science Foundation of China(No.62271379)the National Radar Signal Processing Laboratory(No.KGJ202401)the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University(No.YJSJ24011)。
文摘This paper discusses the problem of low-elevation target height estimation for multiple-input multiple-output(MIMO)radar in multipath environments.The beamspace compresses the data and is ideal for reducing the computational burden of elevation estimation.To obtain the height parameter of the target accurately,we propose a height estimation method based on a beamspace joint alternating iterative(BJAI)algorithm in MIMO radar.This method mainly converts the reduced-dimensional MIMO radar element space data into beamspace data and whitens them to improve the reliability.Then,a simplified model is used to obtain the initial value of the elevation,and we combine the reflection coefficient and the target elevation angle for alternate estimation.Finally,we calculate the target height using the obtained elevation information.Simulation results verify that the proposed algorithm has high estimation accuracy and strong robustness.
基金supported by National Natural Science Foundation of China[grant number 42001329,42001283]Guangdong Basic and Applied Basic Research Foundation[grant number 2023A1515011718]+1 种基金China Postdoctoral Science Foundation[grant number 2021M701268]Foundation of Anhui Province Key Laboratory of Physical Geographic Environment,P.R.China[grant number 2022PGE012].
文摘Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.
文摘We estimate tree heights using polarimetric interferometric synthetic aperture radar(PolInSAR)data constructed by the dual-polarization(dual-pol)SAR data and random volume over the ground(RVoG)model.Considering the Sentinel-1 SAR dual-pol(SVV,vertically transmitted and vertically received and SVH,vertically transmitted and horizontally received)configuration,one notes that S_(HH),the horizontally transmitted and horizontally received scattering element,is unavailable.The S_(HH)data were constructed using the SVH data,and polarimetric SAR(PolSAR)data were obtained.The proposed approach was first verified in simulation with satisfactory results.It was next applied to construct PolInSAR data by a pair of dual-pol Sentinel-1A data at Duke Forest,North Carolina,USA.According to local observations and forest descriptions,the range of estimated tree heights was overall reasonable.Comparing the heights with the ICESat-2 tree heights at 23 sampling locations,relative errors of 5 points were within±30%.Errors of 8 points ranged from 30%to 40%,but errors of the remaining 10 points were>40%.The results should be encouraged as error reduction is possible.For instance,the construction of PolSAR data should not be limited to using SVH,and a combination of SVH and SVV should be explored.Also,an ensemble of tree heights derived from multiple PolInSAR data can be considered since tree heights do not vary much with time frame in months or one season.
基金Supported by the National Natural Science Foundation of China(Grant No.11371076)
文摘In this paper, using the generalized Omori-Yau maximum principle, we obtain height estimates for spacelike hypersurface in a generalized Robertson-Walker （GRW） space- time with constant higher order mean curvature and whose boundary is contained in a slice. Furthermore, we apply these results to draw some topological conclusions. Finally, considering the Omori-Yau maximum principle for the Laplacian and for more general elliptic trace type differential operators, we have some further non-existence results.
基金supported by the Open Project of Guangxi Key Laboratory of Nuclear Physics and Nuclear Technology(No.NLK2022-05)the Central Government Guidance Funds for Local Scientific and Technological Development,China(No.Guike ZY22096024)+5 种基金the Sichuan Natural Science Youth Fund Project(No.2023NSFSC1366)Key R&D Projects of Sichuan Provincial Department of Science and Technology(No.2023YFG0287)the Open Research Fund of National Engineering Research Center for Agro-Ecological Big Data Analysis&Application,Anhui University(No.AE202209)the National Natural Science Youth Foundation of China(No.12305214)the Vanadium and Titanium Resource Comprehensive Utilization Key Laboratory of Sichuan Province(No.2023FTSZ03)the Key Laboratory of Interior Layout optimization and Security,Institutions of Higher Education of Sichuan Province(No.2023SNKJ-01)。
文摘In energy-dispersive X-ray fluorescence spectroscopy,the estimation of the pulse amplitude determines the accuracy of the spectrum measurement.The error generated by the amplitude estimation of the pulse output distorted by the measurement system leads to false peaks in the measured spectrum.To eliminate these false peaks and achieve an accurate estimation of the distorted pulse amplitude,a composite neural network model is proposed,which embeds long and short-term memory(LSTM)into the UNet structure.The UNet network realizes the fusion of pulse sequence features and the LSTM model realizes pulse amplitude estimation.The model is trained using simulated pulse datasets with different amplitudes and distortion times.For the pulse height estimation,the average relative error of the trained model on the test set was approximately 0.64%,which is 27.37% lower than that of the traditional trapezoidal shaping algorithm.Offline processing of a standard iron source further validated the pulse height estimation performance of the UNet-LSTM model.After estimating the amplitude of the distorted pulses using the model,the false peak area was reduced by approximately 91% over the full spectrum and was corrected to the characteristic peak region of interest(ROI).The corrected peak area accounted for approximately 1.32%of the characteristic peak ROI area.The results indicate that the model can accurately estimate the height of distorted pulses and has substantial corrective effects on false peaks.
基金supported by the Forestry Corporation of New South Wales
文摘With their widespread utilization, cut-to-length harvesters have become a major source of ‘‘big data’’ for forest management as they constantly capture, and provide a daily flow of, information on log production and assortment over large operational areas. Harvester data afford the calculation of the total log length between the stump and the last cut but not the total height of trees. They also contain the length and end diameters of individual logs but not always the diameter at breast height overbark（DBHOB） of harvested stems largely because of time lapse, operating and processing issues and other system deficiencies. Even when DBHOB is extracted from harvester data, errors and/or bias of the machine measurements due to the variation in the stump height of harvested stems from that specified for the harvester head prior to harvesting and diameter measurement errors may need to be corrected. This study developed（1） a system of equations for estimating DBHOB of trees from diameter overbark（DOB） measured by a harvester head at any height up to 3 m above ground level and（2） an equation to predict the total height of harvested stems in P. radiata plantations from harvester data. To generate the data required for this purpose, cut-to-length simulations of more than 3000 trees with detailed taper measurements were carried out in the computer using the cutting patterns extracted from the harvester data and stump height survey data from clearfall operations. The equation predicted total tree height from DBHOB, total log length and the small end diameter of the top log. Prediction accuracy for total tree height was evaluated both globally over the entire data space and locally within partitioned subspaces through benchmarking statistics. These statistics were better than that of the conventional height-diameter equations for P. radiata found in the literature, even when they incorporated stand age and the average height and diameter of dominant trees in the stand as predictors. So this equation when used with harvester data would outperform the conventional equations in tree height prediction. Tree and stand reconstructions of the harvested forest is the necessary first step to provide the essential link of harvester data to conventional inventory, remote sensing imagery and Li DAR data. The equations developed in this study will provide such a linkage for the most effective combined use of harvester data in predicting the attributes of individual trees, stands and forests, and product recovery for the management and planning of P. radiata plantations in New South Wales, Australia.
基金the Fund for Foreign Scholars in University Research and Teaching Programs(the 111 Project)(No.B18039)。
文摘Low-angle estimation for very high frequency(VHF)radar is a difficult problem due to the multipath effect in the radar field,especially in complex scenarios where the reflection condition is unknown.To deal with this problem,we propose an algorithm of target height and multipath attenuation joint estimation.The amplitude of the surface reflection coefficient is estimated by the characteristic of the data itself,and it is assumed that there is no reflected signal when the amplitude is very small.The phase of the surface reflection coefficient and the phase difference between the direct and reflected signals are searched as the same part,and this represents the multipath phase attenuation.The Cramer-Rao bound of the proposed algorithm is also derived.Finally,computer simulations and real data processing results show that the proposed algorithm has good estimation performance under complex scenarios and works well with only one snapshot.
基金financed by the Finnish Funding Agency for Innovation(Tekes) and its business and research partners
文摘Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the target data according to the dominant species could improve the subsequent predictions of species-specific attributes in particular in study areas strongly dominated by certain species. Methods： We tested this hypothesis and an operational potential to improve the predictions of timber volumes, stratified to Scots pine, Norway spruce and deciduous trees, in a conifer forest dominated by the pine species. We derived predictor features from airborne laser scanning （ALS） data and used Most Similar Neighbor （MSN） and Seemingly Unrelated Regression （SUR） as examples of non-parametric and parametric prediction methods, respectively Results： The relationships between the ALS features and the volumes of the aforementioned species were considerably different depending on the dominant species. Incorporating the observed dominant species inthe predictions improved the root mean squared errors by 13.3-16.4 % and 12.6-28.9 % based on MSN and SUR, respectively, depending on the species. Predicting the dominant species based on a linear discriminant analysis had an overall accuracy of only 76 % at best, which degraded the accuracies of the predicted volumes. Consequently, the predictions that did not consider the dominant species were more accurate than those refined with the predicted species. The MSN method gave slightly better results than models fitted with SUR. Conclusions： According to our results, incorporating information on the dominant species has a clear potential to improve the subsequent predictions of species-specific forest attributes. Determining the dominant species based solely on ALS data is deemed challenging, but important in particular in areas where the species composition is otherwise seemingly homogeneous except being dominated by certain species.
基金supported by the National Natural Science Foundation of China(42101418 and 42371413)the National Natural Science Foundation of China/RGC Joint Research Scheme(42361164614 and N_HKU722/23)+1 种基金the NSFC Excellent Young Scientists Fund(Overseas)the Chinese University Scientific Fund.
文摘Synthetic aperture radar(SAR)records important information about the interaction of electromagnetic waves with the Earth’s surface.However,long-term and high-resolution backscatter coefficient data are still lacking in many urban studies(e.g.,building height estimation).Here,we proposed a framework to reconstruct the 1-km backscatter coefficient in 1990-2022 utilizing the Sentinel-1 Ground Range Detected data and Landsat time series data in the Jing-Jin-Ji(JJJ)region.First,we developed a regression model to convert the optical signals from Landsat into backscatter coefficients as the Sentinel-1 data,using observations from 2015 to 2022.Then,we reconstructed backscatter coefficients from 1990 to 2022 using the long-term Landsat data.Using the reconstructed backscatter coefficients,we analyzed the dynamic patterns of building height over the past decades.The proposed approach performs well on estimating the backscatter coefficient and its spatial pattern,with the annual mean absolute error,root mean square error,and R^(2) of 1.10 dB,1.50 dB,and 0.64,respectively.The temporal trends revealed from the reconstructed backscatter data are reliable compared with satellite observations at a relatively coarse resolution,with Pearson’s coefficients above 0.92 in 6 sample cities.The derived building height from the reconstructed SAR data indicates that the JJJ region experienced a noticeable upward expansion in 1990-2022,e.g.,Beijing has the fastest growth rate of 0.420 km^(3)/decade regarding the total building volumes.The proposed framework of reconstructing SAR data from optical satellite images provides a new insight to complement the long-term and high-resolution backscatter from local to global scales.
