A ROUGH SET DECISION TREE BASED MLP-CNN FOR VERY HIGH RESOLUTION REMOTELY SENSED IMAGE CLASSIFICATION

We identify 119 km² of meltwater area over West Antarctica in January 2017. In combination with Stokes et al., 2019, this forms the first continent-wide assessment helping to quantify the mass balance of Antarctica and its contribution to global sea level rise. We apply thresholds for meltwater classification to satellite images, mapping the extent and manually post-processing to remove false positives. Our study provides a high-fidelity dataset to train and validate machine learning methods.

The environmental effects of the world's largest Three Gorges Dam (TGD) have been received worldwide attentions. It is the first dynamics monitoring of mid-channel bars (MCBs) in the downstream of TGD at large spatiotemporal scale. The study shows most of the MCBs are located in the lower reach. Small MCBs become shorter and wider whereas the others became slimmer in post-TGD period. Impacts from the TGD operation on the MCB dynamics could decrease along with the increasing distance from TGD.