Background:Accurate mapping of tree species is highly desired in the management and research of plantation forests,whose ecosystem services are currently under threats.Time-series multispectral satellite images,e.g.,f...Background:Accurate mapping of tree species is highly desired in the management and research of plantation forests,whose ecosystem services are currently under threats.Time-series multispectral satellite images,e.g.,from Landsat-8(L8)and Sentinel-2(S2),have been proven useful in mapping general forest types,yet we do not know quantitatively how their spectral features(e.g.,red-edge)and temporal frequency of data acquisitions(e.g.,16-day vs.5-day)contribute to plantation forest mapping to the species level.Moreover,it is unclear to what extent the fusion of L8 and S2 will result in improvements in tree species mapping of northern plantation forests in China.Methods:We designed three sets of classification experiments(i.e.,single-date,multi-date,and spectral-temporal)to evaluate the performances of L8 and S2 data for mapping keystone timber tree species in northern China.We first used seven pairs of L8 and S2 images to evaluate the performances of L8 and S2 key spectral features for separating these tree species across key growing stages.Then we extracted the spectral-temporal features from all available images of different temporal frequency of data acquisition(i.e.,L8 time series,S2 time series,and fusion of L8 and S2)to assess the contribution of image temporal frequency on the accuracy of tree species mapping in the study area.Results:1)S2 outperformed L8 images in all classification experiments,with or without the red edge bands(0.4%–3.4%and 0.2%–4.4%higher for overall accuracy and macro-F1,respectively);2)NDTI(the ratio of SWIR1 minus SWIR2 to SWIR1 plus SWIR2)and Tasseled Cap coefficients were most important features in all the classifications,and for time-series experiments,the spectral-temporal features of red band-related vegetation indices were most useful;3)increasing the temporal frequency of data acquisition can improve overall accuracy of tree species mapping for up to 3.2%(from 90.1%using single-date imagery to 93.3%using S2 time-series),yet similar overall accuracies were achieved using S2 time-series(93.3%)and the fusion of S2 and L8(93.2%).Conclusions:This study quantifies the contributions of L8 and S2 spectral and temporal features in mapping keystone tree species of northern plantation forests in China and suggests that for mapping tree species in China's northern plantation forests,the effects of increasing the temporal frequency of data acquisition could saturate quickly after using only two images from key phenological stages.展开更多
Assessing the changes in forest carbon stocks over time is critical for monitoring carbon dynamics,estimating the balance between carbon uptake and release from forests,and providing key insights into climate change m...Assessing the changes in forest carbon stocks over time is critical for monitoring carbon dynamics,estimating the balance between carbon uptake and release from forests,and providing key insights into climate change mitigation.In this study,we quantitatively characterized spatiotemporal variations in aboveground carbon density(ACD)in boreal natural forests in the Greater Khingan Mountains(GKM)region using bi-temporal discrete aerial laser scanning(ALS)data acquired in 2012 and 2016.Moreover,we evaluated the transferability of the proposed design model using forest field plot data and produced a wall-to-wall map of ACD changes for the entire study area from 2012 to 2016 at a grid size of 30 m.In addition,we investigated the relationships between carbon dynamics and the dominant tree species,age groups,and topography of undisturbed forested areas to better understand ACD variations by employing heterogeneous forest canopy structural characteristics.The results showed that the performance of the temporally transferable model(R^(2)=0.87,rRMSE=18.25%),which included stable variables,was statistically equivalent to that obtained from the model fitted directly by the 2016 field plots(R^(2)=0.87,rRMSE=17.47%).The average rate of change in carbon sequestration across the entire study region was 1.35 Mg⋅ha^(-1)⋅year^(-1) based on the changes in ALS-based ACD values over the course of four years.The relative change rates of ACD decreased as the elevation increased,with the highest and lowest ACD growth rates occurring in the middle-aged and mature forest stands,respectively.The Gini coefficient,which represents forest canopy surface structure heterogeneity,is sensitive to carbon dynamics and is a reliable predictor of the relative change rate of ACD.This study demonstrated the applicability of bi-temporal ALS for predicting forest carbon dynamics and fine-scale spatial change patterns.Our research contributed to a better understanding of the in-fluence of remote sensing-derived environmental variables on forest carbon dynamic patterns and the development of context-specific management approaches to increase forest carbon stocks.展开更多
Although airborne hyperspectral data with detailed spatial and spectral information has demonstrated significant potential for tree species classification,it has not been widely used over large areas.A comprehensive p...Although airborne hyperspectral data with detailed spatial and spectral information has demonstrated significant potential for tree species classification,it has not been widely used over large areas.A comprehensive process based on multi-flightline airborne hyperspectral data is lacking over large,forested areas influenced by both the effects of bidirectional reflectance distribution function(BRDF)and cloud shadow contamination.In this study,hyperspectral data were collected over the Mengjiagang Forest Farm in Northeast China in the summer of 2017 using the Chinese Academy of Forestry's LiDAR,CCD,and hyperspectral systems(CAF-LiCHy).After BRDF correction and cloud shadow detection processing,a tree species classification workflow was developed for sunlit and cloud-shaded forest areas with input features of minimum noise fraction reduced bands,spectral vegetation indices,and texture information.Results indicate that BRDF-corrected sunlit hyperspectral data can provide a stable and high classification accuracy based on representative training data.Cloud-shaded pixels also have good spectral separability for species classification.The red-edge spectral information and ratio-based spectral indices with high importance scores are recommended as input features for species classification under varying light conditions.According to the classification accuracies through field survey data at multiple spatial scales,it was found that species classification within an extensive forest area using airborne hyperspectral data under various illuminations can be successfully carried out using the effective radiometric consistency process and feature selection strategy.展开更多
Grassland is the second largest terrestrial ecosystem and a fundamental land resource for human survival and development.Although grassland degradation is a recognized and crucial ecological problem,there is no consen...Grassland is the second largest terrestrial ecosystem and a fundamental land resource for human survival and development.Although grassland degradation is a recognized and crucial ecological problem,there is no consensus on the area,scope,and degree of its global degradation trends,making the implementation of Sustainable Development Goals(SDG)15.3 for achieving a land degradation-neutral world uncertain.This study quantitatively explored global grassland degradation trends from 2000 to 2020 by coupling vegetation growth and its response to climate change.Furthermore,the driving factors behind these trends were analyzed,especially in hotspots.Results show that the improvement in global grassland has been remarkable since 2000,with a 1.92 times larger area than degrading grassland,amounting to 372.47×10^(4) and 193.57×10^(4) km^(2),respectively.Africa and Asia lead in global grassland degradation and improvement,respectively.Globally,the combined effects of climate change and human activities are the main driving factors for grassland degradation and improvement,accounting for 84.72 and 87.76%,respectively.Notably,human activities played a crucial role in reversing the trend of grassland degradation in some hotspots.Finally,this study provides an essential scientific reference and support for realizing SDG 15.3 on global and regional scales.展开更多
Plant disease recognition is of vital importance to monitor plant development and predicting crop production.However,due to data degradation caused by different conditions of image acquisition,e.g.,laboratory vs.field...Plant disease recognition is of vital importance to monitor plant development and predicting crop production.However,due to data degradation caused by different conditions of image acquisition,e.g.,laboratory vs.field environment,machine learning-based recognition models generated within a specific dataset(source domain)tend to lose their validity when generalized to a novel dataset(target domain).To this end,domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains.In this paper,we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization,namely,Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification(MSUN).Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial training.Specifically,MSUN comprises multirepresentation,subdomain adaptation modules and auxiliary uncertainty regularization.The multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source domain.This effectively alleviates the problem of large interdomain discrepancy.Subdomain adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass variation.Finally,the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain transfer.MSUN was experimentally validated to achieve optimal results on the PlantDoc,Plant-Pathology,Corn-Leaf-Diseases,and Tomato-Leaf-Diseases datasets,with accuracies of 56.06%,72.31%,96.78%,and 50.58%,respectively,surpassing other state-of-the-art domain adaptation techniques considerably.展开更多
The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)...The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)point cloud data.We proposed the Nyström-based spectral clustering(NSC)algorithm to decrease the computational burden.This novel NSC method showed accurate and rapid in individual tree segmentation using point cloud data.The K-nearest neighbour-based sampling(KNNS)was proposed for the Nyström approximation of voxels to improve the efficiency.The NSC algorithm showed good performance for 32 plots in China and Europe.The overall matching rate and extraction rate of proposed algorithm reached 69%and 103%.For all trees located by Global Navigation Satellite System(GNSS)calibrated tape-measures,the tree height regression of the matching results showed an value of 0.88 and a relative root mean square error(RMSE)of 5.97%.For all trees located by GNSS calibrated total-station measures,the values were 0.89 and 4.49%.The method also showed good performance in a benchmark dataset with an improvement of 7%for the average matching rate.The results demonstrate that the proposed NSC algorithm provides an accurate individual tree segmentation and parameter estimation using airborne LiDAR point cloud data.展开更多
基金supported by National Natural Science Foundation of China(Grant No.41901382)Open Fund of State Key Laboratory of Remote Sensing Science(Grant No.OFSLRSS201917)the HZAU research startup fund(No.11041810340,No.11041810341).
文摘Background:Accurate mapping of tree species is highly desired in the management and research of plantation forests,whose ecosystem services are currently under threats.Time-series multispectral satellite images,e.g.,from Landsat-8(L8)and Sentinel-2(S2),have been proven useful in mapping general forest types,yet we do not know quantitatively how their spectral features(e.g.,red-edge)and temporal frequency of data acquisitions(e.g.,16-day vs.5-day)contribute to plantation forest mapping to the species level.Moreover,it is unclear to what extent the fusion of L8 and S2 will result in improvements in tree species mapping of northern plantation forests in China.Methods:We designed three sets of classification experiments(i.e.,single-date,multi-date,and spectral-temporal)to evaluate the performances of L8 and S2 data for mapping keystone timber tree species in northern China.We first used seven pairs of L8 and S2 images to evaluate the performances of L8 and S2 key spectral features for separating these tree species across key growing stages.Then we extracted the spectral-temporal features from all available images of different temporal frequency of data acquisition(i.e.,L8 time series,S2 time series,and fusion of L8 and S2)to assess the contribution of image temporal frequency on the accuracy of tree species mapping in the study area.Results:1)S2 outperformed L8 images in all classification experiments,with or without the red edge bands(0.4%–3.4%and 0.2%–4.4%higher for overall accuracy and macro-F1,respectively);2)NDTI(the ratio of SWIR1 minus SWIR2 to SWIR1 plus SWIR2)and Tasseled Cap coefficients were most important features in all the classifications,and for time-series experiments,the spectral-temporal features of red band-related vegetation indices were most useful;3)increasing the temporal frequency of data acquisition can improve overall accuracy of tree species mapping for up to 3.2%(from 90.1%using single-date imagery to 93.3%using S2 time-series),yet similar overall accuracies were achieved using S2 time-series(93.3%)and the fusion of S2 and L8(93.2%).Conclusions:This study quantifies the contributions of L8 and S2 spectral and temporal features in mapping keystone tree species of northern plantation forests in China and suggests that for mapping tree species in China's northern plantation forests,the effects of increasing the temporal frequency of data acquisition could saturate quickly after using only two images from key phenological stages.
基金We acknowledge grants from the National Key R&D Program of China(Project Number:2020YFE0200800)National Science and Technology Major Project of China's High Resolution Earth Observation System(Project Number:21-Y20B01-9001-19/22-1).
文摘Assessing the changes in forest carbon stocks over time is critical for monitoring carbon dynamics,estimating the balance between carbon uptake and release from forests,and providing key insights into climate change mitigation.In this study,we quantitatively characterized spatiotemporal variations in aboveground carbon density(ACD)in boreal natural forests in the Greater Khingan Mountains(GKM)region using bi-temporal discrete aerial laser scanning(ALS)data acquired in 2012 and 2016.Moreover,we evaluated the transferability of the proposed design model using forest field plot data and produced a wall-to-wall map of ACD changes for the entire study area from 2012 to 2016 at a grid size of 30 m.In addition,we investigated the relationships between carbon dynamics and the dominant tree species,age groups,and topography of undisturbed forested areas to better understand ACD variations by employing heterogeneous forest canopy structural characteristics.The results showed that the performance of the temporally transferable model(R^(2)=0.87,rRMSE=18.25%),which included stable variables,was statistically equivalent to that obtained from the model fitted directly by the 2016 field plots(R^(2)=0.87,rRMSE=17.47%).The average rate of change in carbon sequestration across the entire study region was 1.35 Mg⋅ha^(-1)⋅year^(-1) based on the changes in ALS-based ACD values over the course of four years.The relative change rates of ACD decreased as the elevation increased,with the highest and lowest ACD growth rates occurring in the middle-aged and mature forest stands,respectively.The Gini coefficient,which represents forest canopy surface structure heterogeneity,is sensitive to carbon dynamics and is a reliable predictor of the relative change rate of ACD.This study demonstrated the applicability of bi-temporal ALS for predicting forest carbon dynamics and fine-scale spatial change patterns.Our research contributed to a better understanding of the in-fluence of remote sensing-derived environmental variables on forest carbon dynamic patterns and the development of context-specific management approaches to increase forest carbon stocks.
基金supported by the National Natural Science Foundation of China (Grant No.42101403)the National Key Researchand Development Program of China (Grant No.2017YFD0600404)。
文摘Although airborne hyperspectral data with detailed spatial and spectral information has demonstrated significant potential for tree species classification,it has not been widely used over large areas.A comprehensive process based on multi-flightline airborne hyperspectral data is lacking over large,forested areas influenced by both the effects of bidirectional reflectance distribution function(BRDF)and cloud shadow contamination.In this study,hyperspectral data were collected over the Mengjiagang Forest Farm in Northeast China in the summer of 2017 using the Chinese Academy of Forestry's LiDAR,CCD,and hyperspectral systems(CAF-LiCHy).After BRDF correction and cloud shadow detection processing,a tree species classification workflow was developed for sunlit and cloud-shaded forest areas with input features of minimum noise fraction reduced bands,spectral vegetation indices,and texture information.Results indicate that BRDF-corrected sunlit hyperspectral data can provide a stable and high classification accuracy based on representative training data.Cloud-shaded pixels also have good spectral separability for species classification.The red-edge spectral information and ratio-based spectral indices with high importance scores are recommended as input features for species classification under varying light conditions.According to the classification accuracies through field survey data at multiple spatial scales,it was found that species classification within an extensive forest area using airborne hyperspectral data under various illuminations can be successfully carried out using the effective radiometric consistency process and feature selection strategy.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences[Grant Numbers XDA 19090124]the National Natural Science Foundation of China:[Grant Number 42001386,42271407].
文摘Grassland is the second largest terrestrial ecosystem and a fundamental land resource for human survival and development.Although grassland degradation is a recognized and crucial ecological problem,there is no consensus on the area,scope,and degree of its global degradation trends,making the implementation of Sustainable Development Goals(SDG)15.3 for achieving a land degradation-neutral world uncertain.This study quantitatively explored global grassland degradation trends from 2000 to 2020 by coupling vegetation growth and its response to climate change.Furthermore,the driving factors behind these trends were analyzed,especially in hotspots.Results show that the improvement in global grassland has been remarkable since 2000,with a 1.92 times larger area than degrading grassland,amounting to 372.47×10^(4) and 193.57×10^(4) km^(2),respectively.Africa and Asia lead in global grassland degradation and improvement,respectively.Globally,the combined effects of climate change and human activities are the main driving factors for grassland degradation and improvement,accounting for 84.72 and 87.76%,respectively.Notably,human activities played a crucial role in reversing the trend of grassland degradation in some hotspots.Finally,this study provides an essential scientific reference and support for realizing SDG 15.3 on global and regional scales.
基金supported in part by the National Natural Science Foundation of China under 61902187in part by the Joint Fund of Science and Technology Department of Liaoning Province and State Key Laboratory of Robotics under grant 2020-KF-22-04in part by the Program of Jiangsu Innovation and Entrepreneurship.
文摘Plant disease recognition is of vital importance to monitor plant development and predicting crop production.However,due to data degradation caused by different conditions of image acquisition,e.g.,laboratory vs.field environment,machine learning-based recognition models generated within a specific dataset(source domain)tend to lose their validity when generalized to a novel dataset(target domain).To this end,domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains.In this paper,we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization,namely,Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification(MSUN).Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial training.Specifically,MSUN comprises multirepresentation,subdomain adaptation modules and auxiliary uncertainty regularization.The multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source domain.This effectively alleviates the problem of large interdomain discrepancy.Subdomain adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass variation.Finally,the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain transfer.MSUN was experimentally validated to achieve optimal results on the PlantDoc,Plant-Pathology,Corn-Leaf-Diseases,and Tomato-Leaf-Diseases datasets,with accuracies of 56.06%,72.31%,96.78%,and 50.58%,respectively,surpassing other state-of-the-art domain adaptation techniques considerably.
文摘The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)point cloud data.We proposed the Nyström-based spectral clustering(NSC)algorithm to decrease the computational burden.This novel NSC method showed accurate and rapid in individual tree segmentation using point cloud data.The K-nearest neighbour-based sampling(KNNS)was proposed for the Nyström approximation of voxels to improve the efficiency.The NSC algorithm showed good performance for 32 plots in China and Europe.The overall matching rate and extraction rate of proposed algorithm reached 69%and 103%.For all trees located by Global Navigation Satellite System(GNSS)calibrated tape-measures,the tree height regression of the matching results showed an value of 0.88 and a relative root mean square error(RMSE)of 5.97%.For all trees located by GNSS calibrated total-station measures,the values were 0.89 and 4.49%.The method also showed good performance in a benchmark dataset with an improvement of 7%for the average matching rate.The results demonstrate that the proposed NSC algorithm provides an accurate individual tree segmentation and parameter estimation using airborne LiDAR point cloud data.
