Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework
Water ( IF 3.0 ) Pub Date : 2021-02-22 , DOI: 10.3390/w13040557 Hakan Başağaoğlu , Debaditya Chakraborty , James Winterle
Water ( IF 3.0 ) Pub Date : 2021-02-22 , DOI: 10.3390/w13040557 Hakan Başağaoğlu , Debaditya Chakraborty , James Winterle
Evapotranspiration is often expressed in terms of reference crop evapotranspiration ( ), actual evapotranspiration ( ), or surface water evaporation ( ), and their reliable predictions are critical for groundwater, irrigation, and aquatic ecosystem management in semi-arid regions. We demonstrated that a newly developed probabilistic machine learning (ML) model, using a hybridized “boosting” framework, can simultaneously predict the daily , , & from local hydroclimate data with high accuracy. The probabilistic approach exhibited great potential to overcome data uncertainties, in which of the , of the , and of the test data at three watersheds were within the models’ prediction intervals. The modeling results revealed that the hybrid boosting framework can be used as a reliable computational tool to predict while bypassing net solar radiation calculations, estimate while overcoming uncertainties associated with pan evaporation & pan coefficients, and predict while offsetting high capital & operational costs of EC towers. In addition, using the Shapley analysis built on a coalition game theory, we identified the order of importance and interactions between the hydroclimatic variables to enhance the models’ transparency and trustworthiness.
中文翻译:
带有概率机器学习框架的可靠的蒸散量预测
蒸散量通常用参考作物的蒸散量来表示( ),实际蒸散量( )或地表水蒸发( )及其可靠的预测对于半干旱地区的地下水,灌溉和水生生态系统管理至关重要。我们证明了使用混合的“提升”框架的新开发的概率机器学习(ML)模型可以同时预测每日 , ,& 从本地水文气候数据中获取高精度。概率方法具有克服数据不确定性的巨大潜力,其中 的 , 的 , 和 的 三个分水岭的测试数据都在模型的范围内 预测间隔。建模结果表明,混合提升框架可以作为可靠的计算工具进行预测 在绕过净太阳辐射计算的同时,估算 同时克服与锅蒸发和锅系数相关的不确定性,并进行预测 同时抵消了EC塔的高昂资本和运营成本。此外,使用基于联盟博弈论的Shapley分析,我们确定了重要性顺序和水文气候变量之间的相互作用,以增强模型的透明度和可信度。
更新日期:2021-02-22
中文翻译:
带有概率机器学习框架的可靠的蒸散量预测
蒸散量通常用参考作物的蒸散量来表示(