Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt
Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt
复制标题
DOI：
10.1088/1748-9326/ab68ac
复制
发表时间：
2020-02
影响因子：
6.7
通讯作者：
Aleksandra Wolanin;Gonzalo Mateo-García;Gustau Camps-Valls;L. Gómez-Chova;M. Meroni;Gregory Duveiller;You Liangzhi;L. Guanter
中科院分区：
文献类型：
--
作者：
Aleksandra Wolanin;Gonzalo Mateo-García;Gustau Camps-Valls;L. Gómez-Chova;M. Meroni;Gregory Duveiller;You Liangzhi;L. Guanter
在当前需要确保粮食安全的背景下，预测作物产量变得越来越重要，尽管气候变化带来了挑战，世界人口不断扩大，同时收入增加，土壤侵蚀加剧，水资源减少。温度、辐射、水分可利用性等环境条件以复杂的非线性方式影响作物的生长发育和最终的粮食产量。机器学习(ML)技术，特别是深度学习(DL)方法，可以解释产量与其协变量之间的这种非线性关系。然而，它们通常缺乏透明度和可解释性，因为预测的得出方式并不直接明显。然而，在收益率预测的背景下，理解哪些是预测损失或收益背后的潜在因素具有重要意义。在这里，我们将探讨如何在保持解释模型如何实现其结果的能力的同时，受益于DL方法提高的预测性能。为此，我们将深度神经网络应用于植被和气象数据的多变量时间序列，以估计印度小麦带的小麦产量。然后，我们使用回归激活图来可视化和分析模型学习到的特征和产量驱动因素。DL模型的表现优于其他测试模型(岭回归和随机林)，并有助于解释导致产量变异的变量和过程。习得的特征主要与生长季的长度以及这段时间的温光条件有关。例如，我们的结果表明，2012年的高产与生育期的低温和阳光条件有关。该方法也可推广到其他作物和地区，以促进DL模型在农业上的应用。
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.