Wang et al. (2026) Multi-Source Monitoring of High-Temperature Heat Damage During Summer Maize Flowering Period Based on Machine Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Agriculture
• Year: 2026
• Date: 2026-01-13
• Authors: Xiaofei Wang, Hongwei Tian, Lin Cheng, Fangmin Zhang, Lizhu Xing
• DOI: 10.3390/agriculture16020207

Research Groups

Not specified in the provided text.

Short Summary

This study developed an hourly, high-resolution framework for monitoring high-temperature stress on summer maize in Henan Province by fusing satellite, reanalysis, and ground data with machine learning, revealing intensified heat damage in 2024 compared to 2023.

Objective

• To develop a high-resolution, hourly monitoring framework for high-temperature stress affecting summer maize yields in Henan Province, North China.

Study Configuration

• Spatial Scale: Henan Province, North China, with a resolution of 0.02° × 0.02°.
• Temporal Scale: Hourly monitoring, comparing conditions in 2023 and 2024.

Methodology and Data

• Models used: XGBoost (best performing), Support Vector Regression, Random Forest. A High-Temperature Damage Index (HTDI) was constructed using hourly temperature thresholds of 32 °C and 35 °C.
• Data sources: Himawari-8 satellite observations, ERA5 reanalysis data, ground-based measurements.

Main Results

• XGBoost achieved the best performance for generating the near-surface air temperature dataset (R² = 0.933, RMSE = 0.841 °C).
• The High-Temperature Damage Index (HTDI) exhibited a statistically significant but modest negative correlation with ear grain number (R² = 0.054, p = 0.0007).
• Heat damage was more intense in 2024 (average HTDI = 0.51; over 67% of the area experienced moderate or worse damage) compared to 2023 (average HTDI = 0.22).
• Severe heat damage in 2024 was concentrated in south–central and east–central Henan.

Contributions

• Developed a refined, hourly monitoring approach for high-temperature heat stress, surpassing the limitations of conventional daily scale assessments.
• Advanced the deep integration of remote sensing and machine learning in agricultural meteorology.
• Provided technical support for addressing food security challenges under climate change.

Funding

Not specified in the provided text.

Citation

@article{Wang2026MultiSource,
  author = {Wang, Xiaofei and Tian, Hongwei and Cheng, Lin and Zhang, Fangmin and Xing, Lizhu},
  title = {Multi-Source Monitoring of High-Temperature Heat Damage During Summer Maize Flowering Period Based on Machine Learning},
  journal = {Agriculture},
  year = {2026},
  doi = {10.3390/agriculture16020207},
  url = {https://doi.org/10.3390/agriculture16020207}
}