This study presents the utility of remote sensing （RS）, GIS and field observation data to estimate above ground biomass （AGB） and stem volume over tropical forest environment. Application of those data for the mod...This study presents the utility of remote sensing （RS）, GIS and field observation data to estimate above ground biomass （AGB） and stem volume over tropical forest environment. Application of those data for the modeling of forest properties is site specific and highly uncertain, thus further study is encouraged. In this study we used 1460 sampling plots collected in 16 transects measuring tree diameter （DBH） and other forest properties which were useful for the biomass assessment. The study was carded out in tropical forest region in East Kalimantan, Indo- nesia. The AGB density was estimated applying an existing DBH - biomass equation. The estimate was superimposed over the modified GIS map of the study area, and the biomass density of each land cover was calculated. The RS approach was performed using a subset of sample data to develop the AGB and stem volume linear equation models. Pearson correlation statistics test was conducted using ETM bands reflectance, vegetation indices, image transform layers, Principal Component Analysis （PCA） bands, Tasseled Cap （TC）, Grey Level Co-Occurrence Matrix （GLCM） texture features and DEM data as the predictors. Two linear models were generated from the significant RS data. To analyze total biomass and stem volume of each land cover, Landsat ETM images from 2000 and 2003 were preprocessed, classified using maximum likelihood method, and filtered with the majority analysis. We found 158±16 m^3.ha^-1 of stem volume and 168±15 t.ha^-1 of AGB estimated from RS approach, whereas the field measurement and GIS estimated 157±92 m^3.ha^-1 and 167±94 t.ha^-1 of stem volume and AGB, respectively. The dynamics of biomass abundance from 2000 to 2003 were assessed from multi temporal ETM data and we found a slightly declining trend of total biomass over these periods. Remote sensing approach estimated lower biomass abundance than did the GIS and field measurement data. The earlier approach predicted 10.5 Gt and 10.3 Gt of total biomasses in 2000 and 2003, while the later estimated 11.9 Gt and 11.6 Gt of total biomasses, respectively. We found that GLCM mean texture features showed markedly strong correlations with stem volume and biomass.展开更多
When using the image mutual information to assess the quality of reconstructed image in pseudothermal light ghost imaging, a negative exponential behavior with respect to the measurement number is observed. Based on i...When using the image mutual information to assess the quality of reconstructed image in pseudothermal light ghost imaging, a negative exponential behavior with respect to the measurement number is observed. Based on information theory and a few simple and verifiable assumptions, semi-quantitative model of image mutual information under varying measurement numbers is established. It is the Gaussian characteristics of the bucket detector output probability distribution that leads to this negative exponential behavior. Designed experiments verify the model.展开更多
文摘This study presents the utility of remote sensing （RS）, GIS and field observation data to estimate above ground biomass （AGB） and stem volume over tropical forest environment. Application of those data for the modeling of forest properties is site specific and highly uncertain, thus further study is encouraged. In this study we used 1460 sampling plots collected in 16 transects measuring tree diameter （DBH） and other forest properties which were useful for the biomass assessment. The study was carded out in tropical forest region in East Kalimantan, Indo- nesia. The AGB density was estimated applying an existing DBH - biomass equation. The estimate was superimposed over the modified GIS map of the study area, and the biomass density of each land cover was calculated. The RS approach was performed using a subset of sample data to develop the AGB and stem volume linear equation models. Pearson correlation statistics test was conducted using ETM bands reflectance, vegetation indices, image transform layers, Principal Component Analysis （PCA） bands, Tasseled Cap （TC）, Grey Level Co-Occurrence Matrix （GLCM） texture features and DEM data as the predictors. Two linear models were generated from the significant RS data. To analyze total biomass and stem volume of each land cover, Landsat ETM images from 2000 and 2003 were preprocessed, classified using maximum likelihood method, and filtered with the majority analysis. We found 158±16 m^3.ha^-1 of stem volume and 168±15 t.ha^-1 of AGB estimated from RS approach, whereas the field measurement and GIS estimated 157±92 m^3.ha^-1 and 167±94 t.ha^-1 of stem volume and AGB, respectively. The dynamics of biomass abundance from 2000 to 2003 were assessed from multi temporal ETM data and we found a slightly declining trend of total biomass over these periods. Remote sensing approach estimated lower biomass abundance than did the GIS and field measurement data. The earlier approach predicted 10.5 Gt and 10.3 Gt of total biomasses in 2000 and 2003, while the later estimated 11.9 Gt and 11.6 Gt of total biomasses, respectively. We found that GLCM mean texture features showed markedly strong correlations with stem volume and biomass.
基金supported by the National Natural Science Foundation of China (61631014, 61401036, 61471051 and 61531003)the National Science Fund for Distinguished Young Scholars of China (61225003)+1 种基金the China Postdoctoral Science Foundation (2015M580008)the Youth Research and Innovation Program of BUPT (2015RC12)
文摘When using the image mutual information to assess the quality of reconstructed image in pseudothermal light ghost imaging, a negative exponential behavior with respect to the measurement number is observed. Based on information theory and a few simple and verifiable assumptions, semi-quantitative model of image mutual information under varying measurement numbers is established. It is the Gaussian characteristics of the bucket detector output probability distribution that leads to this negative exponential behavior. Designed experiments verify the model.
