当前位置: X-MOL 学术Agric. For. Meteorol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Crop yield prediction via explainable AI and interpretable machine learning: Dangers of black box models for evaluating climate change impacts on crop yield
Agricultural and Forest Meteorology ( IF 6.2 ) Pub Date : 2023-05-06 , DOI: 10.1016/j.agrformet.2023.109458
Tongxi Hu, Xuesong Zhang, Gil Bohrer, Yanlan Liu, Yuyu Zhou, Jay Martin, Yang Li, Kaiguang Zhao

Statistical crop modeling is pivotal for understanding climate impacts on crop yields. Choices of models matter: Linear regression is interpretable but limited in predictive power; machine learning predicts well but often remains a black box. To develop explainable artificial intelligence (AI) for exploring historical crop yield data and predicting crop yield, here we reported a Bayesian ensemble model (BM) that is interpretable with great explanatory and predictive power. BM embraces many competitive models via Bayesian model averaging, fits complex functions, and quantifies model uncertainty. Long-term crop yields are driven by both climate and technology; the common practice of first detrending and then analyzing the detrended data has an incorrigible bias. Therefore, BM was also aimed at decomposing historical yield data to jointly estimate technological trends and climate effects on crop yield. We compared BM with ElasticNet, Neural Network, MARS, SVM, Random Forests, and XGBoost. BM excelled at both predicting and explaining. When tested on synthetic data, BM was the only method unveiling the true relationships: BM has stronger interpretability; other methods predicted well but for wrong reasons. When tested on maize yield data in Ohio, BM detected two technological shifts, attributable to hybrid corn adoption in the 1940′s and the technological slowing-down in the 1970′s: No other methods detected such changepoints. BM derived nonlinear asymmetric crop responses to climate and non-negligible temperature-precipitation interacting effects, with patterns consistent with theoretical or experimental evidence. Extrapolation of all the models for future yield prediction was highly uncertain, but BM provided more reliable predictions under novel climate whereas Random Forests and XGBoost proved unsuitable for extrapolation. Overall, BM provided new insights unattainable by the existing black-box methods. We caution against blind use of black-box machine learning for statistical crop modeling and call for more efforts to apply interpretable machine learning for mechanistic understandings of crop-climate interactions.



中文翻译:

通过可解释的人工智能和可解释的机器学习预测作物产量:用于评估气候变化对作物产量影响的黑盒模型的危险

统计作物模型对于了解气候对作物产量的影响至关重要。模型的选择很重要:线性回归是可解释的,但预测能力有限;机器学习预测得很好,但通常仍然是一个黑匣子。为了开发可解释的人工智能 (AI) 来探索历史作物产量数据和预测作物产量,我们在这里报告了一个贝叶斯集成模型 (BM),该模型具有强大的解释和预测能力。BM 通过贝叶斯模型平均包含许多竞争模型,适合复杂的功能,并量化模型的不确定性。长期作物产量受气候和技术的驱动;首先去除趋势然后分析去除趋势数据的常见做法具有不可纠正的偏差。所以,BM 还旨在分解历史产量数据,以联合估计技术趋势和气候对作物产量的影响。我们将 BM 与 ElasticNet、神经网络、MARS、SVM、随机森林和 XGBoost 进行了比较。BM 擅长预测和解释。当对合成数据进行测试时,BM 是唯一揭示真实关系的方法:BM 具有更强的可解释性;其他方法预测得很好,但出于错误的原因。在对俄亥俄州的玉米产量数据进行测试时,BM 发现了两个技术转变,归因于 1940 年代杂交玉米的采用和 1970 年代的技术放缓:没有其他方法检测到这样的变化点。BM 导出非线性不对称作物对气候和不可忽略的温度-降水相互作用影响的响应,其模式与理论或实验证据一致。未来产量预测的所有模型的外推具有高度不确定性,但 BM 在新气候下提供了更可靠的预测,而随机森林和 XGBoost 被证明不适合外推。总体而言,BM 提供了现有黑盒方法无法获得的新见解。我们告诫不要盲目使用黑盒机器学习进行作物统计建模,并呼吁更多地努力应用可解释的机器学习来理解作物与气候相互作用的机制。

更新日期:2023-05-06
down
wechat
bug