Summary of Comparing Deep Learning Models For Rice Mapping in Bhutan Using High Resolution Satellite Imagery, by Biplov Bhandari et al.
Comparing Deep Learning Models for Rice Mapping in Bhutan Using High Resolution Satellite Imagery
by Biplov Bhandari, Timothy Mayer
First submitted to arxiv on: 11 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG); Geophysics (physics.geo-ph)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study employs Deep Learning (DL) approaches to predict crop type and extent in Paro, Bhutan, utilizing publicly available satellite imagery from Planet. Two DL models, point-based (DNN) and patch-based (U-Net), were trained on different combinations of RGBN, elevation, and Sentinel-1 data. The U-Net model displayed higher performance metrics across both training and validation efforts. The study shows that DL approaches can predict rice yield and suggests using them with survey-based approaches currently utilized by the Bhutan Department of Agriculture. Additionally, the study demonstrates the usage of regional land cover products as a weak label approach to capture different strata and address class imbalance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses computer vision technology to help the government of Bhutan decide which crops to grow where. They used special kinds of computers that can analyze pictures taken from space. The researchers compared different ways of using this technology, and found that one method called U-Net worked best. This method was able to accurately identify what kind of crop is growing in a particular area. The study shows how useful this technology could be for farmers and the government, and suggests it could help them make better decisions about where to grow different crops. |
Keywords
» Artificial intelligence » Deep learning
