Data archive for 'Convolutional neural networks facilitate river barrier detection and evidence severe habitat fragmentation in the Mekong River biodiversity hotspot'

This repository contains the code and database used in the paper 'Convolutional neural networks facilitate river barrier detection and evidence severe habitat fragmentation in the Mekong River biodiversity hotspot'. The 'FCOS' folder contains Python files of the barrier detection model (FCOS ResNext-101-FPN) which was trained to detect river barriers from remotely sensed photographic images in the MMDetection framework. The 'R_script' folder contains R files used in the paper. Coordinate.R was used to extract coordinates from bounding boxes in each TIF image. CAFI.R was used to calculate the CAFI index in each sub-catchment. The 'Barrier Database' folder contains the 'Training Validation Database' used during the training process, and the 'Mekong River Barrier Database' generated in the study. For more information on the MMDetection framework, refer to the following GitHub repository: https://github.com/open-mmlab/mmdetectio