Wheat yield prediction of Rajasthan using climatic and satellite data and machine learning techniques
For global food security, accurate large-scale wheat yield estimates are critical. The solar induced chlorophyll fluorescence is more sensitive to photosynthesis than any other vegetation indices, so it is crucial to uncover its potential for accurately predicting wheat yields. In the present study...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of agrometeorologists
2025-03-01
|
| Series: | Journal of Agrometeorology |
| Subjects: | |
| Online Access: | https://journal.agrimetassociation.org/index.php/jam/article/view/2807 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | For global food security, accurate large-scale wheat yield estimates are critical. The solar induced chlorophyll fluorescence is more sensitive to photosynthesis than any other vegetation indices, so it is crucial to uncover its potential for accurately predicting wheat yields. In the present study, we implemented three machine learning algorithms, support vector regression, Random Forest and XGBoost, one linear regression method, Least Absolute Shrinkage and Selection Operator regression, and one deep learning method, long short-term memory, to predict the wheat yield prediction from 2008 to 2019 using satellite data (SIF) and vegetation indices. The results indicated Support Vector Regression outperformed Long Short-Term Machine in wheat yield prediction. In comparison to coarse-resolution SIF products, the high-resolution SIF product offers superior prediction. The results emphasize that with high-quality SIF the crop predictions can be improved.
|
|---|---|
| ISSN: | 0972-1665 2583-2980 |