气候变化领域集成服务门户(CCPortal): Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt

CCPortal

DOI	10.1088/1748-9326/ab68ac
	Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt
	Wolanin A.; Mateo-Garciá G.; Camps-Valls G.; Gómez-Chova L.; Meroni M.; Duveiller G.; Liangzhi Y.; Guanter L.
发表日期	2020
ISSN	17489318
卷号	15 期号:2
英文摘要	Forecasting crop yields is becoming increasingly important under the current context in which food security needs to be ensured despite the challenges brought by climate change, an expanding world population accompanied by rising incomes, increasing soil erosion, and decreasing water resources. Temperature, radiation, water availability and other environmental conditions influence crop growth, development, and final grain yield in a complex nonlinear manner. Machine learning (ML) techniques, and deep learning (DL) methods in particular, can account for such nonlinear relations between yield and its covariates. However, they typically lack transparency and interpretability, since the way the predictions are derived is not directly evident. Yet, in the context of yield forecasting, understanding which are the underlying factors behind both a predicted loss or gain is of great relevance. Here, we explore how to benefit from the increased predictive performance of DL methods while maintaining the ability to interpret how the models achieve their results. To do so, we applied a deep neural network to multivariate time series of vegetation and meteorological data to estimate the wheat yield in the Indian Wheat Belt. Then, we visualized and analyzed the features and yield drivers learned by the model with the use of regression activation maps. The DL model outperformed other tested models (ridge regression and random forest) and facilitated the interpretation of variables and processes that lead to yield variability. The learned features were mostly related to the length of the growing season, and temperature and light conditions during this time. For example, our results showed that high yields in 2012 were associated with low temperatures accompanied by sunny conditions during the growing period. The proposed methodology can be used for other crops and regions in order to facilitate application of DL models in agriculture. © 2020 The Author(s). Published by IOP Publishing Ltd.
英文关键词	deep learning (DL); explainable artificial intelligence (XAI); food security; Indian Wheat Belt; regression activation map (RAM); remote sensing; wheat yield
语种	英语
scopus关键词	Chemical activation; Climate change; Crops; Decision trees; Deep neural networks; Food supply; Forecasting; Random forests; Regression analysis; Remote sensing; Water resources; Environmental conditions; explainable artificial intelligence (XAI); Food security; Multivariate time series; Nonlinear relations; Predictive performance; regression activation map (RAM); Wheat yield; Deep learning; artificial intelligence; climate change; crop yield; environmental conditions; estimation method; food security; greenbelt; machine learning; regression analysis; remote sensing; wheat; Triticum aestivum
来源期刊	Environmental Research Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/154098
作者单位	Remote Sensing and Geoinformatics Section, GFZ German Research Centre for Geosciences, Helmholtz-Centre, Potsdam, Germany; Image Processing Laboratory, Universitat de Valencia, Valencia, Spain; European Commission, Joint Research Centre (JRC), Ispra, Italy; Environment and Production Technology Division, International Food Policy Research Institute (IFPRI), Washington, DC, United States; Centro de Tecnologiás Físicas, Universitat Politècnica de Valencia, Valencia, Spain
推荐引用方式 GB/T 7714	Wolanin A.,Mateo-Garciá G.,Camps-Valls G.,et al. Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt[J],2020,15(2).
APA	Wolanin A..,Mateo-Garciá G..,Camps-Valls G..,Gómez-Chova L..,Meroni M..,...&Guanter L..(2020).Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt.Environmental Research Letters,15(2).
MLA	Wolanin A.,et al."Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt".Environmental Research Letters 15.2(2020).