Rice Yield Prediction and Model Interpretation Based on Satellite and Climatic Indicators Using a Transformer Method

doi:10.3390/rs14195045

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Rice Yield Prediction and Model Interpretation Based on Satellite and Climatic Indicators Using a Transformer Method
	Liu, Yuanyuan 1,6; Wang, Shaoqiang 1,3,6; Chen, Jinghua 1,6; Chen, Bin 1,6; Wang, Xiaobo 1,6; Hao, Dongze 1,2; Sun, Leigang 4,5
刊名	REMOTE SENSING
	2022-10-01
卷号	14 期号:19 页码:21
关键词	crop yield prediction remote sensing deep learning feature importance attention
DOI	10.3390/rs14195045
通讯作者	Wang, Shaoqiang(sqwang@igsnrr.ac.cn)
英文摘要	As the second largest rice producer, India contributes about 20% of the world's rice production. Timely, accurate, and reliable rice yield prediction in India is crucial for global food security and health issues. Deep learning models have achieved excellent performances in predicting crop yield. However, the interpretation of deep learning models is still rare. In this study, we proposed a transformer-based model, Informer, to predict rice yield across the Indian Indo-Gangetic Plains by integrating time-series satellite data, environmental variables, and rice yield records from 2001 to 2016. The results showed that Informer had better performance (R-2 = 0.81, RMSE = 0.41 t/ha) than four other machine learning and deep learning models for end-of-season prediction. For within-season prediction, the Informer model could achieve stable performances (R-2 approximate to 0.78) after late September, which indicated that the optimal prediction could be achieved 2 months before rice maturity. In addition, we interpreted the prediction models by evaluating the input feature importance and analyzing hidden features. The evaluation of feature importance indicated that NIRV was the most critical factor, while intervals 6 (mid-August) and 12 (mid-November) were the key periods for rice yield prediction. The hidden feature analysis demonstrated that the attention-based long short-term memory (AtLSTM) model accumulated the information of each growth period, while the Informer model focused on the information around intervals 5 to 6 (August) and 11 to 12 (November). Our findings provided a reliable and simple framework for crop yield prediction and a new perspective for explaining the internal mechanism of deep learning models.
资助项目	National Natural Science Foundation of China[31861143015] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA23100202] ; Science and Technology Planning Project of Hebei Academy of Sciences of China[22A03]
WOS关键词	CROPPING SYSTEM ; WHEAT YIELD ; ASSIMILATION ; GROWTH
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	MDPI
WOS记录号	WOS:000867043500001
资助机构	National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Science and Technology Planning Project of Hebei Academy of Sciences of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50364]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Wang, Shaoqiang
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Univ Geosci, Sch Geog & Informat Engn, Lab Reginal Ecol Proc & Environm Change, Wuhan 430074, Peoples R China 4.Hebei Acad Sci, Inst Geog Sci, Shijiazhuang 050011, Hebei, Peoples R China 5.Hebei Technol Innovat Ctr Geog Informat Applicat, Shijiazhuang 050011, Hebei, Peoples R China 6.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Liu, Yuanyuan,Wang, Shaoqiang,Chen, Jinghua,et al. Rice Yield Prediction and Model Interpretation Based on Satellite and Climatic Indicators Using a Transformer Method[J]. REMOTE SENSING,2022,14(19):21.
APA	Liu, Yuanyuan.,Wang, Shaoqiang.,Chen, Jinghua.,Chen, Bin.,Wang, Xiaobo.,...&Sun, Leigang.(2022).Rice Yield Prediction and Model Interpretation Based on Satellite and Climatic Indicators Using a Transformer Method.REMOTE SENSING,14(19),21.
MLA	Liu, Yuanyuan,et al."Rice Yield Prediction and Model Interpretation Based on Satellite and Climatic Indicators Using a Transformer Method".REMOTE SENSING 14.19(2022):21.