Abstract
This practice focuses on one of the simplest yet effective machine learning models, the random forest model. We will first introduce basic concepts in random forest modeling and then apply this model to an example of predicting soil organic carbon (SOC) distributions across the ecosystems of North Macedonia, a country in Southeast Europe. We will compare the predicting results from the random forest with linear regression models. At the end of this practice, we will discuss the interpretability of the random forest model.
| Original language | English (US) |
|---|---|
| Title of host publication | Land Carbon Cycle Modeling |
| Subtitle of host publication | Matrix Approach, Data Assimilation, Ecological Forecasting, and Machine Learning, Second Edition |
| Publisher | CRC Press |
| Pages | 229-234 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781040026298 |
| ISBN (Print) | 9781032698496 |
| DOIs | |
| State | Published - Jan 1 2024 |
All Science Journal Classification (ASJC) codes
- General Business, Management and Accounting
- General Agricultural and Biological Sciences
- General Earth and Planetary Sciences
- General Environmental Science
- General Engineering
Fingerprint
Dive into the research topics of 'Practice 9: Applications of Machine Learning to Predict Soil Organic Carbon Content'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver