Advanced stacked integration method for forecasting long-term drought severity: CNN with machine learning models
Advanced stacked integration method for forecasting long-term drought severity: CNN with machine learning models
复制标题
DOI：
10.1016/j.ejrh.2024.101759
复制
发表时间：
2024-06
期刊：
影响因子：
--
通讯作者：
Ahmed Elbeltagi;Aman Srivastava;M. Ehsan;Gitika Sharma;Jiawen Yu;L. Khadke;Vinay Kumar Gautam;Ahmed Awad;Jinsong Deng
中科院分区：
文献类型：
--
作者：
Ahmed Elbeltagi;Aman Srivastava;M. Ehsan;Gitika Sharma;Jiawen Yu;L. Khadke;Vinay Kumar Gautam;Ahmed Awad;Jinsong Deng
研究区域上埃及的八个省，即阿斯旺、阿苏特、贝尼苏韦夫、法尤姆、卢克索、明亚、基纳和索哈杰。研究重点本研究旨在开发新的混合机器学习（ML）模型，用于预测埃及八个政府的干旱现象，以及ii）评估所开发的用于预测帕尔默干旱严重度指数（PDSI）的ML模型的性能和准确性基于性能统计指标推荐最优模型。混合ML模型包括卷积神经网络（CNN）-长短期记忆（LSTM）、CNN-随机森林（RF）、CNN-支持向量机（SVR）和CNN-极端梯度提升（XGB）。CNN-LSTM的NSE、MAE、MARE、IA、R2和RMSE值分别为0.885、0.915、-2.073、0.967、0.885和0.573。对于测试阶段，CNN-SVR模型表现最好; NSE，MAE，MARE，IA，R2和RMSE的平均值分别为0.828，0.364，-2.903，0.950，0.828和0.688。这项研究为从气象数据中方便地估计PDSI指数提供了一条前进的道路，即推进深度学习算法。所开发的混合模型，或多或少，可以令人满意的预测PDSI值。此外，该研究表明，CNN-LSTM模型是推进研究领域未来研究的最合适模型。
Study regionEight governorates in upper Egypt namely Aswan, Asyut, Beni-Suef, Fayoum, Luxor, Minya, Qena and Sohag.Study focusThis study aims to develop novel hybrid machine learning (ML) models for forecasting the drought phenomena based on limited inputs for the eight Egyptian govern-orates, and ii) evaluate the performance and accuracy of the developed ML models for predicting Palmer Drought Severity Index (PDSI) to recommend the optimal model based on performance statistical metrics. The hybrid ML models were Convolution Neural Networks (CNN)-Long Short-Term Memory (LSTM), CNN-Random Forest (RF), CNN-Support Vector Machine (SVR), and CNN-Extreme Gradient Boosting (XGB).New hydrological insights for the regionResults showed that CNN-LSTM model outperformed the others followed by CNN-RF. Values of NSE, MAE, MARE, IA, R2, and RMSE for CNN-LSTM were 0.885, 0.915, − 2.073, 0.967, 0.885, and 0.573, respectively. For the testing stage CNN-SVR model was found to perform the best; average values of NSE, MAE, MARE, IA, R2, and RMSE were 0.828, 0.364, − 2.903, 0.950, 0.828 and 0.688, respectively. This study provided a way forward for convenient estimation of the PDSI Index from the meteorological data in terms of advancing deep learning algorithms. The developed hybrid models, more or less, can satisfactory predict PDSI values. Additionally, the study suggests the CNN-LSTM model as the most suitable model to advance future investigation in the study area.