Abstract Ensemble learning (EL), an alternative approach in the machine-learning field, offers an accurate reference evapotranspiration (ETo) prediction, which is of paramount significance for the hydrological studies and agricultural water practices. Although the FAO-56 Penman-Monteith (PM) equation is regarded as an ideal model for estimating ETo, its applicability is limited due to the absence of required climatic datasets in many regions of the world. Despite its significance, only a few studies use the EL algorithms for the ETo prediction perspective. In this study, we contribute to fill this gap from a two-fold way. First, we present the potential of new EL Random Tree (RT), Bagging and Random Subspace (RS) algorithms which were compared with two commonly used Random Forest (RF), and Support Vector Machine (SVM) algorithms for predicting daily ETo with the climatic data-limited humid region in Bangladesh during 1983–2017 using a five-fold cross-validation scheme. Second, we explore the role of contributing variables influencing ETo change at the regional scale. When a lack of climatic datasets, Tmax (maximum temperature), Tmin (minimum temperature) and Rs (solar radiation) as 3 input combinations obtained the reasonable precision for estimating ETo in all climatic regions except for south-central and south-western regions. Compared to other state-of-arts models, the RT model performed superior to predict ETo in all input combinations followed by the RF, Bagging, RS, and SVM. Considering less difficulty level, high prediction accuracy, more dependability and fewer computation costs of studied models, RT and RF models have been suggested as the promising potentials for daily ETo estimate in subtropical climate regions of Bangladesh and also may be applicable worldwide in the similar climates. The importance analysis from the RF model depicted that the wind speed (U2) and solar radiation (Rs) are the largest influential variables affecting the observed and predicted daily ETo changes in Bangladesh.

中文翻译：

---

RT、Bagging 和 RS 集成学习算法在孟加拉国气候数据有限的潮湿地区用于参考蒸散预测的潜力

摘要 集成学习 (EL) 是机器学习领域的一种替代方法，它提供了准确的参考蒸发量 (ETo) 预测，这对于水文研究和农业用水实践至关重要。尽管FAO-56 Penman-Monteith (PM) 方程被认为是估算ETo 的理想模型，但由于世界许多地区缺乏所需的气候数据集，其适用性受到限制。尽管它很重要，但只有少数研究将 EL 算法用于 ETo 预测的角度。在这项研究中，我们从两方面帮助填补了这一空白。首先，我们展示了新的 EL 随机树 (RT)、装袋和随机子空间 (RS) 算法的潜力，并与两种常用的随机森林 (RF) 进行了比较，和支持向量机 (SVM) 算法，用于使用五重交叉验证方案预测 1983-2017 年孟加拉国气候数据有限的潮湿地区的每日 ETo。其次，我们探讨了影响 ETo 变化的贡献变量在区域尺度上的作用。当缺乏气候数据集时，Tmax（最高温度）、Tmin（最低温度）和 Rs（太阳辐射）作为 3 个输入组合获得了估算除中南部和西南地区以外所有气候区 ETo 的合理精度。与其他最先进的模型相比，RT 模型在所有输入组合中的表现优于预测 ETo，然后是 RF、Bagging、RS 和 SVM。考虑到所研究模型的难度级别更低、预测精度高、可靠性更高、计算成本更低，RT 和 RF 模型已被认为是孟加拉国亚热带气候地区每日 ETo 估计的有希望的潜力，也可能适用于世界范围内的类似气候。RF 模型的重要性分析表明，风速 (U2) 和太阳辐射 (Rs) 是影响孟加拉国观察到和预测的每日 ETo 变化的最大影响变量。