Snow cover plays an important role in meteorological and hydrological researches.However,the accuracies of currently available snow cover products are significantly lower in mountainous areas than in plains,due to the...Snow cover plays an important role in meteorological and hydrological researches.However,the accuracies of currently available snow cover products are significantly lower in mountainous areas than in plains,due to the serious snow/cloud confusion problem caused by high altitude and complex topography.Aiming at this problem,an improved snow cover mapping approach for mountainous areas was proposed and applied in Qinghai-Tibetan Plateau.In this work,a deep learning framework named Stacked Denoising Auto-Encoders(SDAE)was employed to fuse the MODIS multispectral images and various geographic datasets,which are then classified into three categories:Snow,cloud and snow-free land.Moreover,two independent SDAE models were trained for snow mapping in snow and snow-free seasons respectively in response to the seasonal variations of meteorological conditions.The proposed approach was verified using in-situ snow depth records,and compared to the most widely used snow products MOD10A1 and MYD10A1.The comparison results show that our method got the best performance:Overall accuracy of 98.95%and F-measure of 73.84%.The results indicated that our method can effectively improve the snow recognition accuracy,and it can be further extended to other multi-source remote sensing image classification issues.展开更多
The Normalized Difference Vegetation Index （NDVI） is an important vegetation greenness indicator. Compared to the AVHRR GIMMS NDVI data, the availability of two datasets with 1 km spatial resolution, i.e., Terra MOD...The Normalized Difference Vegetation Index （NDVI） is an important vegetation greenness indicator. Compared to the AVHRR GIMMS NDVI data, the availability of two datasets with 1 km spatial resolution, i.e., Terra MODIS （MODI3A3） monthly composite and SPOT Vegetation （VGT） 10-day composite NDVI, extends the application dimensions at spatial and temporal scales. An overlapping period of 12 years between the datasets now makes it possible to investigate the consistency of the two datasets. Linear regression trend analysis was performed to compare the two datasets in this study. The results show greater consistency in regression slopes in the semi-arid regions of northern China. Alternatively, the results show only slight changes in the Terra MODIS NDVI regression slope in most areas of southern China whereas the SPOT VGT NDVI shows positive changes over a large area. The corresponding regression slope values between Terra MODIS and SPOT VGT NDVI datasets from the linear fit had a fair agreement in the spatial dimension. However, larger positive and negative differences were observed at the junction of the three regions （East China, Central China, and North China）. These differences can be partially explained by the positive standard deviation differences distributed over a large area at the junction of these three regions. This study demonstrated that Terra MODIS and SPOT VGT NDVI have a relatively robust basis for characterizing vegetation changes in annual NDVI in most of the semi-arid and arid regions in northern China.展开更多
基金This research was supported by National Natural Science Foundation of China(Grant Nos.41661144039,91337102,41401481)and Natural Science Foundation of Jiangsu Province of China(Grant No.BK20140997).
文摘Snow cover plays an important role in meteorological and hydrological researches.However,the accuracies of currently available snow cover products are significantly lower in mountainous areas than in plains,due to the serious snow/cloud confusion problem caused by high altitude and complex topography.Aiming at this problem,an improved snow cover mapping approach for mountainous areas was proposed and applied in Qinghai-Tibetan Plateau.In this work,a deep learning framework named Stacked Denoising Auto-Encoders(SDAE)was employed to fuse the MODIS multispectral images and various geographic datasets,which are then classified into three categories:Snow,cloud and snow-free land.Moreover,two independent SDAE models were trained for snow mapping in snow and snow-free seasons respectively in response to the seasonal variations of meteorological conditions.The proposed approach was verified using in-situ snow depth records,and compared to the most widely used snow products MOD10A1 and MYD10A1.The comparison results show that our method got the best performance:Overall accuracy of 98.95%and F-measure of 73.84%.The results indicated that our method can effectively improve the snow recognition accuracy,and it can be further extended to other multi-source remote sensing image classification issues.
文摘The Normalized Difference Vegetation Index （NDVI） is an important vegetation greenness indicator. Compared to the AVHRR GIMMS NDVI data, the availability of two datasets with 1 km spatial resolution, i.e., Terra MODIS （MODI3A3） monthly composite and SPOT Vegetation （VGT） 10-day composite NDVI, extends the application dimensions at spatial and temporal scales. An overlapping period of 12 years between the datasets now makes it possible to investigate the consistency of the two datasets. Linear regression trend analysis was performed to compare the two datasets in this study. The results show greater consistency in regression slopes in the semi-arid regions of northern China. Alternatively, the results show only slight changes in the Terra MODIS NDVI regression slope in most areas of southern China whereas the SPOT VGT NDVI shows positive changes over a large area. The corresponding regression slope values between Terra MODIS and SPOT VGT NDVI datasets from the linear fit had a fair agreement in the spatial dimension. However, larger positive and negative differences were observed at the junction of the three regions （East China, Central China, and North China）. These differences can be partially explained by the positive standard deviation differences distributed over a large area at the junction of these three regions. This study demonstrated that Terra MODIS and SPOT VGT NDVI have a relatively robust basis for characterizing vegetation changes in annual NDVI in most of the semi-arid and arid regions in northern China.
