Department of Civil Engineering, Erciyes University, Kayseri, Turkey.
Turkish General Directorate of State Hydraulic Works (DSI), Kayseri, Turkey.
Environ Sci Pollut Res Int. 2022 Oct;29(50):75487-75511. doi: 10.1007/s11356-022-21083-3. Epub 2022 Jun 3.
Drought is a harmful natural disaster with various negative effects on many aspects of life. In this research, short-term meteorological droughts were predicted with hybrid machine learning models using monthly precipitation data (1960-2020 period) of Sakarya Meteorological Station, located in the northwest of Turkey. Standardized precipitation index (SPI), depending only on precipitation data, was used as the drought index, and 1-, 3-, and 6-month time scales for short-term droughts were considered. In the prediction models, drought index was predicted at t + 1 output variable by using t, t - 1, t - 2, and t - 3 input variables. Artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), Gaussian process regression (GPR), support vector machine regression (SVMR), k-nearest neighbors (KNN) algorithms were employed as stand-alone machine learning methods. Variation mode decomposition (VMD), discrete wavelet transform (DWT), and empirical mode decomposition (EMD) were utilized as pre-processing techniques to create hybrid models. Six different performance criteria were used to assess model performance. The hybrid models used together with the pre-processing techniques were found to be more successful than the stand-alone models. Hybrid VMD-GPR model yielded the best results (NSE = 0.9345, OI = 0.9438, R = 0.9367) for 1-month time scale, hybrid VMD-GPR model (NSE = 0.9528, OI = 0.9559, R = 0.9565) for 3-month time scale, and hybrid DWT-ANN model (NSE = 0.9398, OI = 0.9483, R = 0.9450) for 6-month time scale. Considering the entire performance criteria, it was determined that the decomposition success of VMD was higher than DWT and EMD.
干旱是一种有害的自然灾害，对生活的许多方面都有各种负面影响。在这项研究中，使用位于土耳其西北部的 Sakarya 气象站的月降水数据（1960-2020 年期间），通过混合机器学习模型预测短期气象干旱。仅依赖降水数据的标准化降水指数（SPI）被用作干旱指数，并考虑了 1、3 和 6 个月的短期干旱时间尺度。在预测模型中，使用 t、t-1、t-2 和 t-3 输入变量来预测 t+1 输出变量的干旱指数。人工神经网络（ANNs）、自适应神经模糊推理系统（ANFIS）、高斯过程回归（GPR）、支持向量机回归（SVMR）、k-最近邻（KNN）算法被用作独立的机器学习方法。变分模态分解（VMD）、离散小波变换（DWT）和经验模态分解（EMD）被用作创建混合模型的预处理技术。使用了六种不同的性能标准来评估模型性能。与独立模型相比，使用预处理技术的混合模型被发现更成功。对于 1 个月时间尺度，混合 VMD-GPR 模型产生了最佳结果（NSE=0.9345，OI=0.9438，R=0.9367），对于 3 个月时间尺度，混合 VMD-GPR 模型（NSE=0.9528，OI=0.9559，R=0.9565），对于 6 个月时间尺度，混合 DWT-ANN 模型（NSE=0.9398，OI=0.9483，R=0.9450）。考虑到整个性能标准，确定 VMD 的分解成功度高于 DWT 和 EMD。
