There is a newer version of the record available.

Published October 18, 2023 | Version v1.1.3
Dataset Open

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

  • 1. Yunnan University
  • 2. Durham University
  • 3. South China University of Technology

Description

This repository contains the code and databases 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 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 'FCOS_x101_v2' folder contains the enhanced FCOS model.

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/mmdetection

Files

Files (17.0 GB)

Name Size Download all
md5:2d01a17c245fcb4459223b6ad9a3d8c4
1.2 MB Download
md5:59d30f523ade016caec7515c21c941cb
679.1 MB Download
md5:1b2a5299682a154bdb3e9cdb63588f91
2.4 GB Download
md5:aa65caa0a718b9641ad43cd01ebdf877
2.4 GB Download
md5:9e948e5749713f4090a3ff53e7c989b9
2.4 GB Download
md5:dc3ebb8a6074873930ed8f6a84fd9439
2.4 GB Download
md5:bcad6a3756fb87bc2558ddd1fb8c01d6
2.4 GB Download
md5:87f580280245ae5a85bba5dce9c9b4f0
2.4 GB Download
md5:ebc097a3607322f87370a51343c339be
2.1 GB Download
md5:ffbbf3638c6bbe07817f3d182d5af67a
1.7 kB Download

Additional details

Related works

Is published in
10.1029/2022WR034375 (DOI)