Corn Yield Prediction Based on an SVR Model with a Fused Matern Kernel Function

DOI

10.2991/978-94-6463-992-6_35How to use a DOI?

Keywords

SVR; remote sensing data; corn yield prediction; Matern kernel function

Abstract

This study focuses on Northeast China and utilizes field-measured estimated yield data along with L2A-level surface reflectance data from the European Space Agency’s Sentinel-2 Multi-Spectral Instrument (MSI), combined with environmental factors, to predict corn yields using machine learning algorithms. The research innovatively employs a Support Vector Regression (SVR) model fused with the Matern kernel function to enhance non-linear fitting capability. Furthermore, normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) were calculated using the fundamental band signals, and the random forest algorithm was employed to extract important features for band signal fusion. Gaussian noise is introduced for data augmentation, L2 regularization is applied to suppress weight overfitting, and an early stopping strategy is adopted to optimize the training process. Experimental results show that the improved SVR model achieves an R² of 0.87 on the test set, with a Root Mean Square Error (RMSE) of 29.7 and a Mean Absolute Error (MAE) of 26.1, significantly outperforming comparative models such as Linear Regression, XGBoost, Random Forest Regression (RFR), and Fully Connected Networks (FC). This study confirms that the improved SVR model with the fused Matern kernel function achieves superior performance in remote sensing-based corn yield prediction, providing a practical tool with high accuracy and low error for precision agricultural management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yanhui Niu
AU  - Yuehui Li
AU  - Qilong Yan
PY  - 2026
DA  - 2026/02/20
TI  - Corn Yield Prediction Based on an SVR Model with a Fused Matern Kernel Function
BT  - Proceedings of the 2025 4th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2025)
PB  - Atlantis Press
SP  - 377
EP  - 385
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-992-6_35
DO  - 10.2991/978-94-6463-992-6_35
ID  - Niu2026
ER  -