Soybean Yield Estimation Using Improved Deep Learning Models With Integrated Multisource and Multitemporal Remote Sensing Data
Accurate soybean yield estimation is critically imperative for modern agricultural systems amid escalating global food security pressures, yet conventional methodologies are constrained for large-scale high-frequency monitoring. To address this, an innovative deep learning framework, TransBiHGRU-PSO...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11079987/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Accurate soybean yield estimation is critically imperative for modern agricultural systems amid escalating global food security pressures, yet conventional methodologies are constrained for large-scale high-frequency monitoring. To address this, an innovative deep learning framework, TransBiHGRU-PSO, is proposed for precise large-scale soybean yield estimation via effective fusion of multisource multitemporal remote sensing data, emphasizing robust and accurate estimation even with anomalous yield data. This framework synergistically integrates an optimized bidirectional hierarchical gated recurrent unit (BiHGRU), a Transformer encoder, and a novel Greenness and Water Content Composite Index, with critical parameters optimized by particle swarm optimization (PSO). County-level yield data from 12 U.S. states were used, supplemented by multitemporal remote sensing datasets (MODIS surface reflectance, vegetation indices, and environmental variables). Empirical analyses showed that TransBiHGRU-PSO demonstrated improved estimation capability and generalizability compared to multiple benchmark models. Notably, with anomalous yield data retained, the model achieved solid test set performance [coefficient of determination (<italic>R</italic><sup>2</sup>) of 0.71 and root-mean-square error (RMSE) of 4.2812 bushels/acre]. Compared to the best traditional machine learning model (support vector regression), <italic>R</italic><sup>2</sup> increased by 52.96% and RMSE decreased by 26.05%, and relative to the best deep learning baseline model (long short-term memory), <italic>R</italic><sup>2</sup> and RMSE improved by 7.04% and 7.04%, respectively. Furthermore, validation of interannual stability (2008–2018, anomalies retained) revealed a mean <italic>R</italic><sup>2</sup> of 0.70 and a mean RMSE of 4.4701 bushels/acre, affirming its consistency under complex real-world conditions. This TransBiHGRU-PSO algorithmic framework, combined with multisource and multitemporal remote sensing data, offers a valuable exploration for large-scale soybean yield estimation. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |