Summary of Machine Learning and Multi-source Remote Sensing in Forest Carbon Stock Estimation: a Review, by Autumn Nguyen and Sulagna Saha
Machine Learning and Multi-source Remote Sensing in Forest Carbon Stock Estimation: A Review
by Autumn Nguyen, Sulagna Saha
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 This research study systematically reviews the most recent machine learning (ML) methods and remote sensing (RS) combinations used to quantify forest carbon, with a focus on considering forest characteristics. The analysis identifies 28 ML methods and key RS data combinations from over 80 related studies, highlighting Random Forest as the most frequently appearing method (88% of studies). Extreme Gradient Boosting shows superior performance in 75% of comparisons with other methods. Sentinel-1 is the most utilized remote sensing source, with multi-sensor approaches proving effective. The findings provide grounds for recommending best practices in integrating ML and RS for accurate and scalable forest carbon stock estimation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps us understand how to better measure the amount of carbon stored in forests. It looks at recent ways that machine learning (ML) and remote sensing (RS) are used together to do this. The research analyzes 25 papers that meet certain criteria, finding 28 different ML methods and RS combinations. It shows that Random Forest is often used, but Extreme Gradient Boosting performs well too. The study also finds that using data from multiple sensors, like Sentinel-1 and Sentinel-2, works well. Overall, the findings help us understand what works best for measuring forest carbon. |
Keywords
» Artificial intelligence » Extreme gradient boosting » Machine learning » Random forest
