College of Environment and Resource Sciences, Zhejiang University, Hangzhou, 310058, Zhejiang, China; Zhejiang Ecological Civilization Academy, Anji, 313300, Zhejiang, China; Agricultural Engineering Department, Faculty of Agriculture, Mansoura University, Mansoura, 35516, Egypt.
Department of Civil Engineering, Indian Institute of Technology (IIT) Kharagpur, Kharagpur, 721302, West Bengal, India.
J Environ Manage. 2023 Nov 1;345:118697. doi: 10.1016/j.jenvman.2023.118697. Epub 2023 Sep 7.
As a non-linear phenomenon that varies along with agro-climatic conditions alongside many other factors, Evapotranspiration (ET) process represents a complexity when be assessed especially if there is a data scarcity in the weather data. However, even under such a data scarcity, the accurate estimates of ET values remain necessary for precise irrigation. So, the present study aims to: i) evaluate the performance of six hybrid machine learning (ML) models in estimating the monthly actual ET values under different agro-climatic conditions in China for seven provinces (Shandong, Jiangsu, Zhejiang, Fujian, Jiangxi, Hubei, and Henan), and ii) select the best-developed model based on statistical metrics and reduce errors between predicted and actual ET (AET) values. AET datasets were divided into 78% for model training (from 1958 to 2007) and the remaining was used for testing (from 2008 to 2021). Deep Neural Networks (DNN) was used as a standalone model at first then the stacking method was applied to integrate DNN with data-driven models such as Additive regression (AR), Random Forest (RF), Random Subspace (RSS), M5 Burned Tree (M5P) and Reduced Error Purning Tree (REPTree). Partial Auto-Correlation Function (PACF) was used for selection of the best lags inputs to the developed models. Results have revealed that DNN-based hybrid models held better performance than non-hybrid DNN models, such that the DNN-RF algorithm outperformed others during both training and testing stages, followed by DNN-RSS. This model has acquired the best values of every statistical measure [MAE (10.8, 12.9), RMSE (15.6, 17.4), RAE (31.9%, 41.4%), and RRSE (39.3%, 47.2%)] for training and testing, respectively. In contrast, the DNN model held the worst performance [MAE (14.9, 13.7), RMSE (20.1, 18.2), RAE (43.9%, 43.7%), and RRSE (50.6%, 49.3%)], for training and testing, respectively. Results from the study presented have revealed the capability of DNN-based hybrid models for long-term predictions of the AET values. Moreover, the DNN-RF model has been suggested as the most suitable model to improve future investigation for AET predictions, which could benefit the enhancement of the irrigation process and increase crop yield.
作为一种随农业气候条件和许多其他因素而变化的非线性现象，蒸散（ET）过程在评估时具有复杂性，尤其是在气象数据匮乏的情况下。然而，即使在这种数据匮乏的情况下，准确估计 ET 值对于精确灌溉仍然是必要的。因此，本研究旨在：i）评估六种混合机器学习（ML）模型在估计中国七个省份（山东、江苏、浙江、福建、江西、湖北和河南）不同农业气候条件下的月实际 ET 值的性能，ii）根据统计指标选择最佳开发模型，并减少预测与实际 ET（AET）值之间的误差。AET 数据集分为 78%用于模型训练（1958 年至 2007 年），其余用于测试（2008 年至 2021 年）。首先使用深度神经网络（DNN）作为独立模型，然后应用堆叠方法将 DNN 与数据驱动模型（如加法回归（AR）、随机森林（RF）、随机子空间（RSS）、M5 燃烧树（M5P）和简化错误燃烧树（REPTree）集成。偏自相关函数（PACF）用于选择开发模型的最佳滞后输入。结果表明，基于 DNN 的混合模型比非混合 DNN 模型具有更好的性能，例如，在训练和测试阶段，DNN-RF 算法都优于其他算法，其次是 DNN-RSS。该模型在训练和测试阶段分别获得了每个统计度量的最佳值[MAE（10.8、12.9）、RMSE（15.6、17.4）、RAE（31.9%、41.4%）和 RRSE（39.3%、47.2%）]。相比之下，DNN 模型的表现最差[MAE（14.9、13.7）、RMSE（20.1、18.2）、RAE（43.9%、43.7%）和 RRSE（50.6%、49.3%）]，用于训练和测试，分别。该研究的结果表明，基于 DNN 的混合模型具有长期预测 AET 值的能力。此外，建议使用 DNN-RF 模型作为改进未来 AET 预测研究的最合适模型，这有助于提高灌溉过程和增加作物产量。
