Xie et al. (2026) Winter Wheat Yield Estimations Based on Multisource Remote Sensing Parameters and the BiLSTM–CNN Model

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-09
• Authors: Yi Xie, Sicheng Ma, Lan Xun, Shujing Shi, Pengxin Wang
• DOI: 10.3390/rs18183098

Research Groups

• Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences (CASS)
• Key Laboratory of Agro-ecological Processes in Middle and Lower Reaches of Yangtze River, CASS

Short Summary

This study developed a high-spatiotemporal-resolution model for winter wheat yield estimation using remote sensing variables and machine learning algorithms. The model achieved an R2 of 0.69 and RMSE of 478.68 kg/hm2.

Objective

• Investigate the nonlinear associations between multitemporal remote sensing variables and winter wheat yield

Study Configuration

• Spatial Scale: Regional scale in China's agricultural areas
• Temporal Scale: Multitemporal, with a focus on primary growth stages of winter wheat

Methodology and Data

• Models used: Bidirectional long short-term memory (BiLSTM)–one-dimensional convolutional neural network (1-D CNN)
• Data sources: Sentinel-2 normalized difference vegetation index (NDVI), MODIS NDVI, actual evapotranspiration (ET), land surface temperature (LST), precipitation (PRE), and soil moisture (SM)

Main Results

• The BiLSTM–CNN model achieved higher estimation accuracy than individual BiLSTM and 1-D CNN models.
• The use of all parameters produced the best estimation performance among all parameter combinations.

Contributions

• This study provides an important theoretical basis for high-accuracy regional winter wheat yield estimation and pre-harvest forecasting.
• The developed model can be applied to other crops and regions with similar climate and soil conditions.

Funding

• National Key Research and Development Program of China (2017YFD0300401)
• National Natural Science Foundation of China (41877144)

Citation

@article{Xie2026Winter,
  author = {Xie, Yi and Ma, Sicheng and Xun, Lan and Shi, Shujing and Wang, Pengxin},
  title = {Winter Wheat Yield Estimations Based on Multisource Remote Sensing Parameters and the BiLSTM–CNN Model},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183098},
  url = {https://doi.org/10.3390/rs18183098}
}