Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China
Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an u...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/20/5280 |
| _version_ | 1797470102204973056 |
|---|---|
| author | Hai Huang Jianxi Huang Quanlong Feng Junming Liu Xuecao Li Xinlei Wang Quandi Niu |
| author_facet | Hai Huang Jianxi Huang Quanlong Feng Junming Liu Xuecao Li Xinlei Wang Quandi Niu |
| author_sort | Hai Huang |
| collection | DOAJ |
| description | Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China’s major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average <i>R</i><sup>2</sup> of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions. |
| first_indexed | 2024-03-09T19:31:59Z |
| format | Article |
| id | doaj.art-b5f0ea27d2c4457b91bcd4aa0417c3d8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T19:31:59Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b5f0ea27d2c4457b91bcd4aa0417c3d82023-11-24T02:22:38ZengMDPI AGRemote Sensing2072-42922022-10-011420528010.3390/rs14205280Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in ChinaHai Huang0Jianxi Huang1Quanlong Feng2Junming Liu3Xuecao Li4Xinlei Wang5Quandi Niu6College of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100083, ChinaAccurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China’s major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average <i>R</i><sup>2</sup> of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions.https://www.mdpi.com/2072-4292/14/20/5280winter wheatcrop yield predictiondeep learningremote sensingweather datasoil data |
| spellingShingle | Hai Huang Jianxi Huang Quanlong Feng Junming Liu Xuecao Li Xinlei Wang Quandi Niu Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China Remote Sensing winter wheat crop yield prediction deep learning remote sensing weather data soil data |
| title | Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China |
| title_full | Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China |
| title_fullStr | Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China |
| title_full_unstemmed | Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China |
| title_short | Developing a Dual-Stream Deep-Learning Neural Network Model for Improving County-Level Winter Wheat Yield Estimates in China |
| title_sort | developing a dual stream deep learning neural network model for improving county level winter wheat yield estimates in china |
| topic | winter wheat crop yield prediction deep learning remote sensing weather data soil data |
| url | https://www.mdpi.com/2072-4292/14/20/5280 |
| work_keys_str_mv | AT haihuang developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT jianxihuang developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT quanlongfeng developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT junmingliu developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT xuecaoli developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT xinleiwang developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina AT quandiniu developingadualstreamdeeplearningneuralnetworkmodelforimprovingcountylevelwinterwheatyieldestimatesinchina |