Department of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, Iran.
Engineering Department, Cardiff University, Cardiff, UK.
Environ Sci Pollut Res Int. 2023 Sep;30(45):101744-101760. doi: 10.1007/s11356-023-29522-5. Epub 2023 Sep 1.
Drought as a natural phenomenon has always been a serious threat to regions with hot and dry climates. One of the major effects of drought is the drop in groundwater level. This paper focused on the SPI (Standardized Precipitation Index) and SWI (Standardized Water-Level Index) to assess meteorological and hydrological drought, respectively. In the first part, we used different time frames of SPI (3, 6, 12, and 24 months) to investigate drought in Yazd, a dry province in the center of Iran for 29 years (1990-2018). Then, in the second part, the relationship between SPI and SWI was investigated in the three aquifers of Yazd by some rain gauge stations and the closest observation wells to them. In addition to using SPI and SWI, we also used different machine learning (ML) algorithms to predict drought conditions including linear model and six non-linear models of K_Nearest_Neighbors, Gradient_Boosting, Decision_Tree, XGBoost, Random_Forest, and Neural_Net. To evaluate the accuracy of the mentioned models, three statistical indicators including Score, RMSE, and MAE were used. Based on the results of the first part, Yazd province has changed from mild wet to mild drought in terms of meteorological drought (the amount of rainfall according to SPI), and this condition can worsen due to climate change. The models used in ML showed that SPI-6 (score ave = 0.977), SPI-3 (score ave = 0.936), SPI-24 (score ave = 0.571), and SPI-12 (score ave = 0.413) indices had the highest accuracy, respectively. The models of Neural_Net (score ave = 0.964-RMSE ave = 0.020-MAE ave = 0.077) and Gradient_Boosting (score ave = 0.551-RMSE ave = 0.124-MAE ave = 0.248) had the highest and lowest accuracy in prediction of the SPI in all four-time scales. Based on the results of the second part, about the SWI, Random_Forest model (score = 0.929-RMSE = 0.052-MAE = 0.150) and model of Neural_Net (score = 0.755-RMSE = 0.235-MAE = 0.456) had the highest and lowest accuracy, respectively. Also, hydrological drought (reduction of the groundwater level) of the region has been much more severe, and according to the low correlation coefficient of average SPI and SWI (R = 0.14), we found that the uncontrolled pumping wells, as a main factor than a shortage of rainfall, have aggravated the hydrological drought, and this region is at risk of becoming a more arid region in the future.
干旱作为一种自然现象，一直是炎热干燥气候地区的严重威胁。干旱的主要影响之一是地下水位下降。本文分别使用标准化降水指数（SPI）和标准化水位指数（SWI）来评估气象和水文干旱。在第一部分，我们使用了不同时间跨度的 SPI（3、6、12 和 24 个月）来研究伊朗中部干旱省份亚兹德 29 年来（1990-2018 年）的干旱情况。然后，在第二部分，我们通过一些雨量站和离它们最近的观测井，研究了亚兹德三个含水层中的 SPI 和 SWI 之间的关系。除了使用 SPI 和 SWI，我们还使用了不同的机器学习（ML）算法来预测干旱情况，包括线性模型和 K_Nearest_Neighbors、Gradient_Boosting、Decision_Tree、XGBoost、Random_Forest 和 Neural_Net 等六种非线性模型。为了评估所述模型的准确性，我们使用了三个统计指标，包括得分、均方根误差和平均绝对误差。根据第一部分的结果，亚兹德省在气象干旱方面（根据 SPI 计算的降雨量）已经从轻度湿润变为轻度干旱，这种情况可能会因气候变化而恶化。ML 中使用的模型表明，SPI-6（得分平均=0.977）、SPI-3（得分平均=0.936）、SPI-24（得分平均=0.571）和 SPI-12（得分平均=0.413）指数的准确性最高。在所有四个时间尺度上，Neural_Net 模型（得分平均=0.964-RMSE 平均=0.020-MAE 平均=0.077）和 Gradient_Boosting 模型（得分平均=0.551-RMSE 平均=0.124-MAE 平均=0.248）的预测精度最高和最低。根据第二部分的结果，关于 SWI，Random_Forest 模型（得分=0.929-RMSE=0.052-MAE=0.150）和 Neural_Net 模型（得分=0.755-RMSE=0.235-MAE=0.456）的准确性最高和最低。此外，该地区的水文干旱（地下水位下降）要严重得多，并且根据平均 SPI 和 SWI 的低相关系数（R=0.14），我们发现，不受控制的抽水井是导致水文干旱的主要因素，而不是降雨量不足，这加剧了水文干旱，该地区未来有变得更加干旱的风险。
