Published August 7, 2023 | Version v1
Dataset Open

Dataset for Deep learning solutions for mapping contour levee rice production systems from very high resolution imagery

Authors/Creators

  • 1. Department of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR, USA
  • 2. Department of Geography and the Environment, University of North Texas, Denton, TX, USA
  • 3. Department of Water Resources, State of California, Sacramento, CA, USA
  • 4. USDA Agricultural Research Service, Delta Water Management Research Unit, Jonesboro, AR, USA
  • 5. Department of Biological and Agricultural Engineering, University of Arkansas, Fayetteville, AR, USA

Description

This dataset contains the two datasets detailed in "Deep learning solutions for mapping contour levee rice production systems from very high resolution imagery" by D.S. Dale Et al. (2023). 

The file "LonokeComplete.zip" file contains 16 .lif files that were used in the training and testing phase of the study. 

The "55tilesComplete.zip" file contains 110 .tif files (55 image and 55 label). These images were used to assess the models spatial transferability. 

Both file configurations are processed by the code linked in the paper. 

Notes

Supported in Part by NASA Water Resources Award 80NSSC22K0923 and U.S. Geological Survey under Cooperative Agreement G20AC00448 and G21AC10729.

Files

55tilesComplete.zip

Files (3.4 GB)

Name Size
md5:7ddd50b12a616cf4a7a6f16544261f25
2.6 GB Preview Download
md5:8331449fe1af38516a39a8057e0d92d5
781.2 MB Preview Download

Additional details

Related works

Is referenced by
Journal article: 10.1016/j.compag.2023.107954 (DOI)

Funding

U.S. National Science Foundation
CAREER: Developing climate-smart irrigation strategies for rice agriculture in Arkansas 1752083

References

  • DS Dale Et al., 2023