摘要：
Rice is one of the world’s major staple foods, especially in China. Highly accurate monitoring on rice-producing land is, therefore, crucial for assessing food supplies and productivity. Recently, the deep-learning convolutional neural network (CNN) has achieved considerable success in remote-sensing data analysis. A CNN-based paddy-rice mapping method using the multitemporal Landsat 8, phenology data, and land-surface temperature (LST) was developed during this study. First, the spatial–temporal adaptive reflectance fusion model (STARFM) was used to blend the moderate-resolution imaging spectroradiometer (MODIS) and Landsat data for obtaining multitemporal Landsat-like data. Subsequently, the threshold method is applied to derive the phenological variables from the Landsat-like (Normalized difference vegetation index) NDVI time series. Then, a generalized single-channel algorithm was employed to derive LST from the Landsat 8. Finally, multitemporal Landsat 8 spectral images, combined with phenology and LST data, were employed to extract paddy-rice information using a patch-based deep-learning CNN algorithm. The results show that the proposed method achieved an overall accuracy of 97.06% and a Kappa coefficient of 0.91, which are 6.43% and 0.07 higher than that of the support vector machine method, and 7.68% and 0.09 higher than that of the random forest method, respectively. Moreover, the Landsat-derived rice area is strongly correlated (R2 = 0.9945) with government statistical data, demonstrating that the proposed method has potential in large-scale paddy-rice mapping using moderate spatial resolution images.
摘要：
There is a large amount of remote sensing data available for land use and land cover (LULC) classification and thus optimizing selection of remote sensing variables is a great challenge. Although many methods such as Jeffreys-Matusita (JM) distance and random forests (RF) have been developed for this purpose, the existing methods ignore correlation and information duplication among remote sensing variables. In this study, a novel approach was proposed to improve the measures of potential class separability for the selection of remote sensing variables by taking into account correlations among the variables. The proposed method was examined with a total of thirteen spectral variables from a Gaofen-1 image, three class separability measures including JM distance, transformed divergence and B-distance and three classifiers including Bayesian discriminant (BD), Mahalanobis distance (MD) and RF for classification of six LULC types at the East Dongting Lake of Hunan, China. The results showed that (1) The proposed approach selected the first three spectral variables and resulted in statistically stable classification accuracies for three improved class separability measures. That is, the classification accuracies using three or more spectral variables statistically did not significantly differ from each other at a significant level of 0.05; (2) The statistically stable classification accuracies obtained by integrating MD and BD classifiers with the improved class separability measures were also statistically not significantly different from those by RF; (3) The numbers of the selected spectral variables using the improved class separability measures to create the statistically stable classification accuracies by MD and BD classifiers were much smaller than those from the original class separability measures and RF; and (4) Three original class separability measures and RF led to similar ranks of importance of the spectral variables, while the ranks achieved by the improved class separability measures were different due to the consideration of correlations among the variables. This indicated that the proposed method more effectively and quickly selected the spectral variables to produce the statistically stable classification accuracies compared with the original class separability measures and RF and thus improved the selection of the spectral variables for the classification.
作者机构：
[严恩萍; 林辉; 王广兴; 赵运林; 莫登奎] Key Laboratory of Forestry Remote Sensing Big Data &, Ecological Security for Hunan Province, Central South University of Forestry &, Technology, Changsha, 410004, China;[王广兴] Department of Geography, Southern Illinois University, Carbondale, IL, 629012, United States;[严恩萍; 林辉; 王广兴; 赵运林; 莫登奎] College of Forestry, Central South University of Forestry &, Technology, Changsha, 410004, China
通讯机构：
Key Laboratory of Forestry Remote Sensing Big Data & Ecological Security for Hunan Province, Central South University of Forestry & Technology, Changsha, China
关键词：
林业遥感;森林资源清查;多源遥感;基于块的序列高斯协同模拟;森林碳密度
摘要：
【目的】基于遥感影像空间分辨率和地面样地大小不一致的现象,采用地统计学和多源遥感数据进行森林碳密度估算,为MODIS数据在区域森林碳密度估算领域的应用提供参考。【方法】以湖南省攸县为试验区,首先利用基于块的序列高斯协同模拟算法,将25. 8 m × 25. 8 m的样地数据分别上推到250 m × 250 m、500 m × 500 m和1 000 m × 1 000 m;然后将上推后的样地数据分别与MOD13Q1、MOD09A1、MOD15A2数据结合,利用序列高斯协同模拟算法开展区域森林碳密度估算研究;最后将最优结果用于湖南省森林碳密度估算。【结果】Landsat5和 MODIS数据与森林碳密度的敏感因子具有高度相似性,排在前3位的分别为1 /TM3、1 /TM2、1 /TM1和1 /Band1、 1 /Band4、1 /Band3;与植被指数产品MOD13Q1和MOD15A2相比,多光谱数据Landsat5和MOD09A1在攸县森林碳密度估算方面显示出巨大潜力,估算精度分别为82. 02%和75. 64%;基于MOD09A1的序列高斯协同模拟算法具有很好的适用性,可用于湖南省森林碳密度的空间模拟,估算精度为74. 07%。【结论】采用基于块的序列高斯协同模拟算法,可以实现由地面样地到不同空间分辨率MODIS像元之间的转换;由于空间分辨率的限制,MOD09A1数据在刻画空间细节方面不如Landsat5精细。该研究方法适用于地面调查样地大小和遥感影像空间分辨率不一致的区域森林碳密度估算。
期刊：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2015年12(9):1993-1997 ISSN：1545-598X
通讯作者：
Sun, Hua
作者机构：
[Wang, Guangxing; Li, Jiping; Sun, Hua; Lin, Hui] Cent South Univ Forestry & Technol, Res Ctr Forest Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China.;[Wang, Guangxing] South Illinois Univ, Dept Geog, Carbondale, IL 62901 USA.;[Ju, Hongbo; Zhang, Huaiqing] Chinese Acad Forestry, Res Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China.
通讯机构：
[Sun, Hua] C;Cent South Univ Forestry & Technol, Res Ctr Forest Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China.
关键词：
Accuracy assessment;estimation;point cloud data;terrestrial laser scanning (TLS);tree and stand parameters
摘要：
Compared with airborne laser scanning, terrestrial laser scanning (TLS) offers ground-based point cloud data of trees and provides greater potential to accurately estimate tree and stand parameters. However, there is a lack of effective methods to accurately identify locations of individual trees from TLS point cloud data. It is also unknown whether the estimation accuracy of the parameters, including tree height (H), diameter at breast height (DBH), and so on, using TLS can meet the requirement of forest management and planning. In this letter, a novel method to effectively process point cloud data and further determine the locations of individual trees in a stand based on the central coordinates of point cloud data on a defined grid according to the largest DBH was developed. Moreover, a point-cloud-data-based convex hull algorithm and the cylinder method were, respectively, used to estimate DBH and H of individual trees. This study was conducted in a pure Chinese fir plantation of 45 trees located in Huang-Feng-Qiao forest farm, You County of Hunan, China. The comparison of the estimated and observed values showed that the obtained tree locations had errors of less than 20 cm, and the relative root mean square errors for the estimates of both DBH and H were less than 5%. This implies that TLS is very promising for the retrieval of tree and stand parameters in forest stands. For the applications of these methods to mixed forests with a structure of multilayer canopies, further examination is needed.
期刊：
International Journal of Remote Sensing,2015年36(2):489-512 ISSN：0143-1161
通讯作者：
Wang, Guangxing
作者机构：
[Wang, Guangxing; Yan, Enping; Lin, Hui; Sun, Hua] Cent South Univ Forestry & Technol, Res Ctr Forest Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China.;[Wang, Guangxing] So Illinois Univ, Dept Geog & Environm Resources, Carbondale, IL 62901 USA.;[Xia, Chaozong] State Forestry Adm, Acad Forest Inventory & Planning, Beijing 100714, Peoples R China.
通讯机构：
[Wang, Guangxing] C;Cent South Univ Forestry & Technol, Res Ctr Forest Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China.
摘要：
Remotely sensed data have been widely used for classification of land-use and land-cover (LULC) types. However, classifying different forest types in Northeast China using satellite images is still a great challenge because of the similar spectral reflectances of different tree species. The differences of vegetation phenological characteristics provide the potential of classifying the types using time series of spectral variables derived from images. In this study, time series of the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) from Moderate Resolution Imaging Spectroradiometer (MODIS) images obtained in 2012 for Northeast China were used to calculate various phenological metrics and to further derive amplitude and phase information of harmonic components using Fourier transforms. The separability of eight vegetation cover types plus water and built-up areas was then analysed using phenological metrics, and amplitude and phase of harmonic components. Moreover, a phenology-based decision tree classifier was developed to classify the types in this area. Out of 4900 national forest inventory plots, 3700 plots were used to train the decision tree classifier and 1200 plots to assess the accuracy of classification by combining the plots’ observations with the values of a published LULC map that had a higher spatial resolution and accuracy of classification using a window majority rule. In addition, three data sets from different temporal resolution MODIS NDVI and EVI time series and two similarity measures were compared for separability and classification of the types. The results showed that (1) Fourier transforms of NDVI and EVI time series led to the first four harmonic components (including component 0, average annual NDVI, and EVI) that captured the phenological characteristics of the cover types; (2) compared to those using only NDVI, the separability values of the classes using NDVI, amplitude, and phase increased from 1.71 to 1.95, implying the potential improvement of classification; (3) the data set from 10-day NDVI time series had higher classification accuracy than those from 16-day NDVI and EVI time series, although the EVI time series performed slightly better than the NDVI time series at the same temporal resolution; and (4) a classification accuracy of 83.8% with a kappa coefficient of 0.79 was finally obtained. This study implied that this method is applicable for classification of vegetation cover types for large areas.
通讯机构：
Research Center of Forestry Remote Sensing and Information Engineering, Central South University of Forestry and Technology, Changsha, Hunan, China
摘要：
Forest ecosystems have a great potential in mitigation of carbon concentration in the atmosphere. Thus, generating its spatially explicit estimates at national, regional and global scale becomes very important. In Southern China, mapping forest carbon is often conducted by combining ground plot data from national forest inventory and remotely sensed images from Landsat and MODIS (Moderate Resolution Imaging Spectroradiometer) with variable spatial resolutions. However, the inconsistency of sample plot sizes with spatial resolutions of images will lead to a great challenge for mapping and accuracy assessment of forest carbon. In this study, an image based spatial co-simulation was used to map forest carbon by directly combining a total of 56 sample plots with plot size of 25.8 m x 25.8 m and a Landsat Thematic Mapper (TM) image at a spatial resolution of 30 m x 30 m for You County of Hunan with a area of 4.82x10(5) hm(2). An image based spatial block co-simulation was then employed to combine and scale up the plot and TM image data to 225 m x 225 m, 450 m x 450 m and 900 m x 900 m to create forest carbon maps at multiple spatial resolutions. Moreover, MODIS images, including MOD13Q1, MOD09A1 and MOD15A2 with three spatial resolutions corresponding to those above, were applied to map forest carbon for this County. The obtained map from TM image at the spatial resolution of 30 m x 30 m was validated using a dataset of 26 sample plots that were not used for simulation, while the accuracy of the MODIS derived maps was assessed using the higher resolution TM image derived estimates. The results showed that the coefficient of determination between the TM image derived forest carbon estimates and the observations was 0.81 with a root mean square error of 8.8 T/ha. The determination coefficient between the TM and MODIS derived estimates varied from 0.78 to 0.82. Moreover, all the TM and MODIS derived estimates had similar spatial distributions and patterns to those of the sample plot data. But, compared with the maps from TM image, the MODIS derived forest carbon maps were more smoothed. This study, to some extent, overcame some of significant gaps that currently exists in mapping and accuracy assessment of forest carbon using remotely sensed data when the ground data have different spatial resolutions from used images.
摘要：
Forests play an important role in providing timber, soil and water conservation, and control of global climate and environmental change through carbon sequestration. Thus, the health status of tree species is worthy of major concern. Every year various tree species especially rare tree species disappear from natural disasters or plant disease and insect pests. However, many trees can be saved if effective measures are taken through early diagnostics of health. Due to the potential of hyperspectral data in detecting the changes of tree leaves in colors, moisture, and materials due to natural disasters or plant disease and insects, hyperspectral data can be used to monitor the health status of trees and achieve the health diagnosis of trees and forests. In this study, a hyperspectral radiometer with spectrum range of 350 nm to 2500 nm from ASD company was used to observe high-density hyperspectral changes of tree leaves due to defoliation for the tree species of metasequoia glyptostroboides and ginkgo biloba, with time period of September 2013 to December 2013. First order differential and its logarithmic transformations were employed for processing the hyspectral data. The results showed that the peak location of visible light reflectance for the tree species was highly related to their health status. The peaks of spectral reflectance appeared at the locations of 550 nm and 650 nm identified the healthy and dead leaves, respectively. In addition, the peaks appeared at yellow band implied the sub-healthy of trees. This finding has critical significance for early health diagnosis of tree species.
摘要：
Hyperspectral techniques have made it possible the recognition and classification of tree species. However, it is unknown which bands are the most suitable to distinguish tree species. This study aimed at obtaining sensitive bands that can be used for tree species classification based on correlation analysis between the hyperspectral data and pigment contents of trees. In this study, a total of 264 spectral data sets were collected with a band range of 400 nm to 925 nm at fixed points and times form March 2010 to February 2011, including 171 and 93 pieces of branches and leaves for Cunninghamia Lance olata and Pinus massoniana Lamb, respectively. The in situ hyperspectral reflectance data of these two tree species were collected at canopy using ASD (Analytical Spectral Devices) FieldSpec HandHeld spectrradiometer, a new product of ASD America Inc. At the same time, chlorophyll a&b, chlorophyll-a, chlorophyll-b, carotenoids and xanthophyll of branches and leaves for these species were measured in lab. First, the correlation between the hyperspectral data and the pigment contents was analyzed, and the spectral intervals of these two conifers with higher coefficients of correlation were obtained. The data of spectral intervals selected were used for classification of these tree species using five classification algorithms including Support Vector Machine-Radial Basis Function (SVM-RBF), BP neural network, Mahalanobis Distance, Bayes, and Spectral Angle Mapping (SAM). The results showed that the use of chlorophyll led to better performance of classification than other pigments. The sensitive spectral intervals for these two conifers based on chlorophyll ranged from 401 nm to 504 nm and from 659 nm to 686 nm. Among these five methods, it was found that SVM-RBF and BP neural network classifications resulted in better performance. Second, in order to test the dependence and adaptability for imaging spectral data, the obtained spectral intervals were combined using Gaussian curve instead of spectral response function (SRF) and the combined data was classified using the above five methods. The accuracy of classification obviously reduced around 15% to 20%. But, the performance of chlorophyll a&b could be still better than other pigments. Third, In order to test the applicability of the spectral intervals, we added 46 spectral data sets of Cinnamomum camphora, collected from 2004 to 2006, to do the classification. The performance of chlorophyll was also better than other pigments. This implied that the obtained spectral intervals 401 nm to 504 nm and 659 nm to 686 nm based on chlorophyll were consistent and could be applied to classification of other tree species. But, the spectral intervals were not narrow enough and there is a need of further study and examination.
摘要：
Because of high spectral and temporal resolutions, large coverage and low cost, MODIS (Moderate Resolution Imaging Spectroradiometer) data has been widely used to extract information of forest types at regional, national and global scales. However, its coarse spatial resolution often leads to mixed pixels and impedes increasing classification accuracy of forest types. Spectral unmixing can, to some extent, increase the accuracy of classification. But, how to accurately extract pure endmembers for a study area is a great challenge. The selection of linear or non-linear spectral unmixing algorithm is another challenge. In this study, a method to extract endmembers - different land cover and vegetation types from MODIS images was developed. In this method, the time series of MODIS derived vegetation index was first obtained and the phenological variation of forest types were analyzed. Moreover, decision tree classification was then conducted and the obtained results were then used to enhance the extraction of endmembers. With the endmembers, linear spectral unmixing of MODIS images with and without constraints, and nonlinear spectral unmixing were finally carried out and the classification results were compared. In addition, for comparison, the classification was also made using a widely used classifier - maximum likelihood. This study was conducted in Hunan of China, where typical vegetation types included coniferous forests, deciduous forests, bamboo, and shrubs. Moreover, water, built up area, and agricultural lands were involved. The classification accuracy of the land cover types using MODIS images was assessed using the data from a total of 1179 forest inventory plots and the area data of the land cover classes from forest inventory across Hunan, and the classification results using Landsat Thematic Mapper (TM) images for Zhuzhou City of Hunan, respectively. The results showed that the overall accuracies for three kinds of validation data were 85.8%, 87.4% and 85.9% for linear spectral unmixing without constraints, 85.1%, 88.4% and 84.7% for linear spectral unmixing with constraints, 64.2%, 67.5% and 64.7% for nonlinear spectral unmixing, and 72.7%, 79.7% and 73.8% for maximum likelihood classifier. These implied that linear spectral unmixing regardless of with and without constraint led to much higher accuracy than the maximum likelihood classification and non-linear spectral unmixing.
会议名称：
3rd International Workshop on Earth Observation and Remote Sensing Applications (EORSA)
会议时间：
JUN 11-14, 2014
会议地点：
Changsha, PEOPLES R CHINA
会议主办单位：
[Ling, Chengxing;Zhang, Huaiqing;Ju, Hongbo;Liu, Hua] CAF, IFRIT, Beijing 100091, Peoples R China.^[Sun, Hua;Lin, Hui] CSUFT, Res Ctr Forestry Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China.
会议论文集名称：
International Workshop on Earth Observation and Remote Sensing Applications
关键词：
Wetland;Above-Ground Biomass;Remote sensing;Worldview-2 Data;Estimation Model
摘要：
This paper discusses the relationship between vegetation index and the above-ground biomass(AGB) of wetland and gets the AGB distribution in the study area, based on the Worldview-2 data and filed sampling data, establishing the East Dong Ting lake as the study area. The results shows that, multiple linear regression model (MLRM) test is significant (hitting a level of 0.000), while the model correlation coefficient is 0.9567, fitting accuracy reaches 34.5g/m(2). The MLRM prediction results has an error of 56.4 g/m(2), the determine coefficient is 0.9011, estimation of AGB total to 27.3418 t/hm(2) in study area, with the actual biomass has a difference of 1.8206t/hm(2), the relative error is 7%, and the total of 12440.5294t in study area. This research proved method of the MLRM has a better precision and forecasting ability by comparing that of LAI-AGB and SCRM (single curve regression model)AGB. It has a widely application value to the wetland research.
