ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Plant Bioinformatics
This article is part of the Research TopicModelling Environmental and Crop Production Systems: Evaluating Impacts of Abiotic Stress on Crop Growth and Resource Use EfficiencyView all 4 articles
Yield Estimation of Winter Wheat in the Huang-Huai-Hai Region Using MODIS and Meteorological Data: Spatio-Temporal Analysis and County-Level Modeling
Provisionally accepted
- 1Shanxi Agricultural University, Taiyuan, China
- 2College of Engineering, Northeast Agricultural University, Harbin, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The Huang-Huai-Hai region is a major winter wheat production area in China. Achieving accurate yield estimation through high spatio-temporal resolution MODIS remote sensing combined with meteorological monitoring has become an important issue for ensuring food security. This study integrates multi-source MODIS satellite data (surface reflectance, leaf area index LAI, and fraction of absorbed photosynthetically active radiation FPAR) with precipitation and temperature data to construct a county-level winter wheat yield prediction model. First, spatio-temporal analyses were conducted on multidimensional parameters during key periods (overwintering, growth, and maturation). The results showed that reflectance responded sensitively to phenological changes; FPAR and LAI revealed photosynthetic capacity and canopy structure evolution; monthly mean precipitation and temperature exhibited significant spatio-temporal heterogeneity, providing data support for effective yield prediction. Next, PLS, RF, and BP models were constructed for the three periods. The BP model performed best across multiple periods, achieving the highest accuracy in the growth period (R²=0.81, RMSE=414.48 kg/ha) and was thus selected as the optimal window period and model. Shapley Additive Explanations (SHAP) analysis revealed the influence of model features on yield prediction, with specific reflectance bands, precipitation, and LAI identified as key contributing factors. Furthermore, the BP model was validated using remote sensing and meteorological data from the 2023 growth period, combined with county-level yields. The results showed R²=0.73 and RMSE = 509.30 kg/ha, further confirming the model's prediction accuracy and stability in practical applications. This study enables county-level estimation of winter wheat yield, providing scientific evidence and methodological reference for agricultural monitoring and food security assurance.
Keywords: winter wheat, Yield estimation, MODIS remote sensing, Meteorological factors, machine learning, SHAP analysis
Received: 10 Oct 2025; Accepted: 28 Nov 2025.
Copyright: © 2025 Lou and Sun. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Deng Sun
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.