Prediction of meteorological drought and standardized precipitation index based on the random forest (RF), random tree (RT), and Gaussian process regression (GPR) models

Integration of Gaussian process regression and K means clustering for enhanced short term rainfall runoff modeling

Accurate rainfall-runoff modeling is crucial for effective watershed management, hydraulic infrastructure safety, and flood mitigation. However, predicting rainfall-runoff remains challenging due to the nonlinear interplay between hydro-meteorological and topographical variables. This study introduces a hybrid Gaussian process regression (GPR) model integrated with K-means clustering (GPR-K-means) for short-term rainfall-runoff forecasting. The Orgeval watershed in France serves as the study area, providing hourly precipitation and streamflow data spanning 1970-2012. The performance of the GPR-K-means model is compared with standalone GPR and principal component regression (PCR) models across four forecasting horizons: 1-hour, 6-hour, 12-hour, and 24-hour ahead. The results reveal that the GPR-K-means model significantly improves forecasting accuracy across all lead times, with a Nash-Sutcliffe Efficiency (NSE) of approximately 0.999, 0.942, 0.891, and 0.859 for 1-hour, 6-hour, 12-hour, and 24-hour forecasts, respectively. These results outperform other ML models, such as Long Short-Term Memory, Support Vector Machines, and Random Forest, reported in the literature. The GPR-K-means model demonstrates enhanced reliability and robustness in hourly streamflow forecasting, emphasizing its potential for broader application in hydrological modeling. Furthermore, this study provides a novel methodology for combining clustering and Bayesian regression techniques in surface hydrology, contributing to more accurate and timely flood prediction.

Integration of remote sensing and machine learning algorithm for agricultural drought early warning over Genale Dawa river basin, Ethiopia

Drought remains a menace in the Horn of Africa; as a result, the Ethiopia's Genale Dawa River Basin is one of the most vulnerable to agricultural drought. Hence, this study integrates remote sensing and machine learning algorithm for early warning identification through assessment and prediction of index-based agricultural drought over the basin. To track the severity of the drought in the basin from 2003 to 2023, a range of high-resolution satellite imagery output indexes were used, including the Vegetation Condition Index (VCI), Thermal Condition Index (TCI), and Vegetation Health Index (VHI). Additionally, the Artificial Neural Network machine learning technique was used to predict agricultural drought VHI for the period of 2028 and 2033. Results depict that during the 2023 period, 25% of severe drought and 18% of extreme drought countered at the lower part of the basin at Dolo ado and Chereti regions. A high TCI value was found that around 23.24% under extreme drought and low precipitation countered in areas of Moyale, Dolo ado, Dolobay, Afder, and Bure lower than 3.57 mm per month. Similarly, increment of severe drought from 24.26% to 24.58% and 16.53% to 16.58% of extreme drought value of VHI might be experienced during the 2028 and 2033 period respectively in the area of Mada Wolabu, Dolo ado, Dodola, Gore, Gidir, and Rayitu. The findings of this study are significantly essential for the institutes located particularly in the basin as they will allow them to adapt drought-coping mechanisms and decision-making easily.

Enhancing drought monitoring with a multivariate hydrometeorological index and machine learning-based prediction in the south of Iran

Traditional drought indices, such as the Standardized Precipitation Index (SPI) and Standardized Runoff Index (SRI), often fail to capture the complexity of drought events, which involve multiple interacting variables. To address this gap, this study applies the Principle of Maximum Entropy (POME) copula to combine SPI and SRI into a Joint Deficit Index (JDI), offering a more complete assessment of hydrometeorological drought. We used machine learning models, including Random Forest (RF), Quantile Random Forest (QRF), Extreme Gradient Boosting (XGB), and Quantile Regression XGBoost (QXGB), to predict JDI, while also incorporating uncertainty analysis using the Uncertainty Estimation based on Local Errors and Clustering (UNEEC) method. This approach not only improves the accuracy of drought predictions but also quantifies the uncertainty of the models, enhancing reliability. Model performance, evaluated with R2, RMSE, and MAE, showed XGB as the best performer, achieving R2 = 0.93 and RMSE = 0.16. This integration of multivariate drought indices, machine learning, and uncertainty analysis provides a more robust tool for drought monitoring and water resource management in arid regions.

Comparative assessment of empirical and hybrid machine learning models for estimating daily reference evapotranspiration in sub-humid and semi-arid climates

Improving the accuracy of reference evapotranspiration (RET) estimation is essential for effective water resource management, irrigation planning, and climate change assessments in agricultural systems. The FAO-56 Penman-Monteith (PM-FAO56) model, a widely endorsed approach for RET estimation, often encounters limitations due to the lack of complete meteorological data. This study evaluates the performance of eight empirical models and four machine learning (ML) models, along with their hybrid counterparts, in estimating daily RET within the Gharb and Loukkos irrigated perimeters in Morocco. The ML models examined include Random Forest (RF), M5 Pruned (M5P), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), with hybrid combinations of RF-M5P, RF-XGBoost, RF-LightGBM, and XGBoost-LightGBM. Six input combinations were created, utilizing Tmax, Tmin, RHmean, Rs, and U2, with the PM-FAO56 model serving as the benchmark. Model performance was assessed using four statistical indicators: Kling-Gupta efficiency index (KGE), coefficient of determination (R2), mean squared error (RMSE), and relative root squared error (RRSE). Results indicate that the Valiantzas 2013 (VAL2013b) model outperformed other empirical models across all stations, achieving high KGE and R2 values (0.95-0.97) and low RMSE (0.32-0.35 mm/day) and RRSE (8.14-10.30%). The XGBoost-LightGBM and RF-LightGBM hybrid models exhibited the highest accuracy (average RMSE of 0.015-0.097 mm/day), underscoring the potential of hybrid ML models for RET estimation in subhumid and semi-arid regions, thereby enhancing water resource management and irrigation scheduling.

Establishment and Evaluation of Atmospheric Water Vapor Inversion Model Without Meteorological Parameters Based on Machine Learning

Precipitable water vapor (PWV) is an important indicator to characterize the spatial and temporal variability of water vapor. A high spatial and temporal resolution of atmospheric precipitable water can be obtained using ground-based GNSS, but its inversion accuracy is usually limited by the weighted mean temperature, Tm. For this reason, based on the data of 17 ground-based GNSS stations and water vapor reanalysis products over 2 years in the Hong Kong region, a new model for water vapor inversion without the Tm parameter is established by deep learning in this paper, the research results showed that, compared with the PWV information calculated by the traditional model using Tm parameter, the accuracy of the PWV retrieved by the new model proposed in this paper is higher, and its accuracy index parameters BIAS, MAE, and RMSE are improved by 38% on average. At the same time, the PWV was inverted by radiosonde data in the study area as a reference to verify the water vapor inversion results of the new model, and it was found that the BIAS of the new model is only 0.8 mm, which has high accuracy. Further, compared with the LSTM model, the new model is more universal when the accuracy is comparable. In addition, in order to evaluate the spatial and temporal variation characteristics of the atmospheric water vapor retrieved by the new model, based on the rainstorm event caused by typhoon in Hong Kong of September 2023, the ERA5 GSMaP rainfall products and inverted PWV information were comprehensively used for analysis. The results show that the PWV increased sharply with the arrival of the typhoon and the occurrence of a rainstorm event. After the rain stopped, the PWV gradually decreased and tended to be stable. The spatial and temporal variation in the PWV have a strong correlation with the occurrence of extreme rainstorm events. This shows that the PWV inverted by the new model can respond well to extreme rainstorm events, which proves the feasibility and reliability of the new model and provides a reference method for meteorological monitoring and weather forecasting.

Optimising Venturi flume oxygen transfer efficiency using uncertainty-aware decision trees

This study optimizes standard oxygen transfer efficiency (SOTE) in Venturi flumes investigating the impact of key parameters such as discharge per unit width (q), throat width (W), throat length (F), upstream entrance width (E), and gauge readings (Ha and Hb). To achieve this, a comprehensive experimental dataset was analyzed using multiple linear regression (MLR), multiple nonlinear regression (MNLR), gradient boosting machine (GBM), extreme gradient boosting (XRT), random forest (RF), M5 (pruned and unpruned), random tree (RT), and reduced error pruning (REP). Model performance was evaluated based on key metrics: correlation coefficient (CC), root mean square error (RMSE), and mean absolute error (MAE). Among the proposed models, M5_Unprun emerged as the top performer, exhibiting the highest CC (0.9455), the lowest RMSE (0.1918), and the lowest MAE (0.0030). GBM followed closely with a CC value of 0.9372, an RMSE value of 0.2067, and an MAE value of 0.0006. Uncertainty analysis further solidified the superior performance of M5_Unpruned (0.7522) and GBM (0.8055), with narrower prediction bands compared to other models, including MLR, which exhibited the widest band (1.4320). One-way analysis of variance confirmed the reliability and robustness of the proposed models. Sensitivity, correlation, and SHapley Additive exPlanations analyses identified W and Hb as the most influencing factors.

Screening the Best Risk Model and Susceptibility SNPs for Chronic Obstructive Pulmonary Disease (COPD) Based on Machine Learning Algorithms

Background and Purpose

Chronic obstructive pulmonary disease (COPD) is a common and progressive disease that is influenced by both genetic and environmental factors, and genetic factors are important determinants of COPD. This study focuses on screening the best predictive models for assessing COPD-associated SNPs and then using the best models to predict potential risk factors for COPD.

Methods

Healthy subjects (n=290) and COPD patients (n=233) were included in this study, the Agena MassARRAY platform was applied to genotype the subjects for SNPs. The selected sample loci were first screened by logistic regression analysis, based on which the key SNPs were further screened by LASSO regression, RFE algorithm and Random Forest algorithm, and the ROC curves were plotted to assess the discriminative performance of the models to screen the best prediction model. Finally, the best prediction model was used for the prediction of risk factors for COPD.

Results

One-way logistic regression analysis screened 44 candidate SNPs from 146 SNPs, on the basis of which 44 SNPs were screened or feature ranked using LASSO model, RFE-Caret, RFE-Lda, RFE-lr, RFE-nb, RFE-rf, RFE-treebag algorithms and random forest model, respectively, and obtained ROC curve values of 0.809, 0.769, 0.798, 0.743, 0.686, 0.766, 0.743, 0.719, respectively, so we selected the lasso model as the best model, and then constructed a column-line graph model for the 25 SNPs screened in it, and found that rs12479210 might be the potential risk factors for COPD.

Conclusion

The LASSO model is the best predictive model for COPD and rs12479210 may be a potential risk locus for COPD.

Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks

Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in the price channel, to evade risks and enable appropriate policy interventions. However, the traditional mono-scale smoothing techniques often fail to capture the non-stationary and non-linear features due to their multifarious structure. This study has proposed a CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise)-TDNN (Time Delay Neural Network) model for forecasting non-linear, non-stationary agricultural price series. This study has evaluated its suitability in comparison with the other three major EMD (Empirical Mode Decomposition) variants (EMD, Ensemble EMD and Complementary Ensemble EMD) and the benchmark (Autoregressive Integrated Moving Average, Non-linear Support Vector Regression, Gradient Boosting Machine, Random Forest and TDNN) models using monthly wholesale prices of major oilseed crops in India. Outcomes from this investigation reflect that the CEEMDAN-TDNN hybrid models have outperformed all other forecasting models on the basis of evaluation metrics under consideration. For the proposed model, an average improvement of RMSE (Root Mean Square Error), Relative RMSE and MAPE (Mean Absolute Percentage Error) values has been observed to be 20.04%, 19.94% and 27.80%, respectively over the other EMD variant-based counterparts and 57.66%, 48.37% and 62.37%, respectively over the other benchmark stochastic and machine learning models. The CEEMD-TDNN and CEEMDAN-TDNN models have demonstrated superior performance in predicting the directional changes of monthly price series compared to other models. Additionally, the accuracy of forecasts generated by all models has been assessed using the Diebold-Mariano test, the Friedman test, and the Taylor diagram. The results confirm that the proposed hybrid model has outperformed the alternative models, providing a distinct advantage.

A novel statistical framework of drought projection by improving ensemble future climate model simulations under various climate change scenarios

Unlike other natural disasters, drought is one of the most severe threats to all living beings globally. Due to global climate change, the frequency and duration of droughts have increased in many parts of the world. Therefore, accurate prediction and forecasting of droughts are essential for effective mitigation policies and sustainable research. In recent research, the use of ensemble global climate models (GCMs) for simulating precipitation data is common. The objective of this research is to enhance the multi-model ensemble (MME) for improving future drought characterizations. In this research, we propose the use of relative importance metric (RIM) to address collinearity effects and point-wise discrepancy weights (PWDW) in GCMs. Consequently, this paper introduces a new statistical framework for weighted ensembles called the discrepancy-enhanced beta weighting ensemble (DEBWE). DEBWE enhances the weighted ensemble data of precipitation simulated by multiple GCMs. In DEBWE, we addressed uncertainties in GCMs arising from collinearity and outliers. To evaluate the effectiveness of the proposed weighting framework, we compared its performance with the simple average multi-model ensemble (SAMME), Taylor skill score ensemble (TSSE), and mutual information ensemble (MIE). Based on the Kling-Gupta efficiency (KGE) metric, DEBWE outperforms all competitors across all evaluation criteria. These inferences are based on the analysis of historical simulated data from 22 GCMs in the CMIP6 project. The quantitative performance indicators strongly support the superiority of DEBWE. The median and mean KGE values for DEBWE are 0.2650 and 0.2429, compared to SAMME (0.1000, 0.0991), TSSE (0.2600, 0.2397), and MIE (0.1550, 0.1511). For drought assessment, we computed the adaptive standardized precipitation index (SPI) for three future scenarios: SSP1-2.6, SSP2-4.5, and SSP5-8.5. The steady-state probabilities suggest that normal drought (ND) is the most frequent condition, with extreme events (dry or wet) being less probable.

Landsat-based spatiotemporal estimation of subtropical forest aboveground carbon storage using machine learning algorithms with hyperparameter tuning

Introduction

The aboveground carbon storage (AGC) in forests serves as a crucial metric for evaluating both the composition of the forest ecosystem and the quality of the forest. It also plays a significant role in assessing the quality of regional ecosystems. However, current technical limitations introduce a degree of uncertainty in estimating forest AGC at a regional scale. Despite these challenges, remote sensing technology provides an accurate means of monitoring forest AGC. Furthermore, the implementation of machine learning algorithms can enhance the precision of AGC estimates. Lishui City, with its rich forest resources and an approximate forest coverage rate of 80%, serves as a representative example of the typical subtropical forest distribution in Zhejiang Province.

Methods

Therefore, this study uses Landsat remote sensing images, employing backpropagation neural network (BPNN), random forest (RF), and categorical boosting (CatBoost) to model the forest AGC of Lishui City, selecting the best model to estimate and analyze its forest AGC spatiotemporal dynamics over the past 30 years (1989-2019).

Results

The study shows that: (1) The texture information calculated based on 9×9 and 11×11 windows is an important variable in constructing the remote sensing estimation model of the forest AGC in Lishui City; (2) All three machine learning techniques are capable of estimating forest AGC in Lishui City with high precision. Notably, the CatBoost algorithm outperforms the others in terms of accuracy, achieving a model training accuracy and testing accuracy R2 of 0.95 and 0.83, and RMSE of 2.98 Mg C ha-1 and 4.93 Mg C ha-1, respectively. (3) Spatially, the central and southwestern regions of Lishui City exhibit high levels of forest AGC, whereas the eastern and northeastern regions display comparatively lower levels. Over time, there has been a consistent increase in the total forest AGC in Lishui City over the past three decades, escalating from 1.36×107 Mg C in 1989 to 6.16×107 Mg C in 2019.

Discussion

This study provided a set of effective hyperparameters and model of machine learning suitable for subtropical forests and a reference data for improving carbon sequestration capacity of subtropical forests in Lishui City.

Examining optimized machine learning models for accurate multi-month drought forecasting: A representative case study in the USA

The Colorado River has experienced a significant streamflow reduction in recent decades due to climate change, resulting in pronounced hydrological droughts that pose challenges to the environment and human activities. However, current models struggle to accurately capture complex drought patterns, and their accuracy decreases as the lead time increases. Thus, determining the reliability of drought forecasting for specific months ahead presents a challenging task. This study introduces a robust approach that utilizes the Beluga Whale Optimization (BWO) algorithm to train and optimize the parameters of the Regularized Extreme Learning Machine (RELM) and Random Forest (RF) models. The applied models are validated against a KNN benchmark model for forecasting drought from one- to six-month ahead across four hydrological stations distributed over the Colorado River. The achieved results demonstrate that RELM-BWO outperforms RF-BWO and KNN models, achieving the lowest root-mean square error (0.2795), uncertainty (U95 = 0.1077), mean absolute error (0.2104), and highest correlation coefficient (0.9135). Also, the current study uses Global Multi-Criteria Decision Analysis (GMCDA) as an evaluation metric to assess the reliability of the forecasting. The GMCDA results indicate that RELM-BWO provides reliable forecasts up to four months ahead. Overall, the research methodology is valuable for drought assessment and forecasting, enabling advanced early warning systems and effective drought countermeasures.

Daily scale air quality index forecasting using bidirectional recurrent neural networks: Case study of Delhi, India

This research was established to accurately forecast daily scale air quality index (AQI) which is an essential environmental index for decision-making. Researchers have projected different types of models and methodologies for AQI forecasting, such as statistical techniques, machine learning (ML), and most recently deep learning (DL) models. The modelling development was adopted for Delhi city, India which is a major city with air pollution issues simialir to entire urban cities of India especially during winter seasons. This research was predicted AQI using different versions of DL models including Long-Short Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Bidirectional Recurrent Neural Networks (Bi-RNN) in addition to Kernel Ridge Regression (KRR). Results indicated that Bi-RNN model consistently outperformed the other models in both training and testing phases, while the KRR model consistently displayed the weakest performance. The outstanding performance of the models development displayed the requirement of adequate data to train the models. The outcomes of the models showed that LSTM, BI-LSTM, KRR had lower performance compared with Bi-RNN models. Statistically, Bi-RNN model attained maximum cofficient of determination (R2 = 0.954) and minimum root mean square error (RMSE = 25.755). The proposed model in this research revealed the robust predictable to provide a valuable base for decision-making in the expansion of combined air pollution anticipation and control policies targeted at addressing composite air pollution problems in the Delhi city.

Proportional impact prediction model of coating material on nitrate leaching of slow-release Urea Super Granules (USG) using machine learning and RSM technique

An accurate assessment of nitrate leaching is important for efficient fertiliser utilisation and groundwater pollution reduction. However, past studies could not efficiently model nitrate leaching due to utilisation of conventional algorithms. To address the issue, the current research employed advanced machine learning algorithms, viz., Support Vector Machine, Artificial Neural Network, Random Forest, M5 Tree (M5P), Reduced Error Pruning Tree (REPTree) and Response Surface Methodology (RSM) to predict and optimize nitrate leaching. In this study, Urea Super Granules (USG) with three different coatings were used for the experiment in the soil columns, containing 1 kg soil with fertiliser placed in between. Statistical parameters, namely correlation coefficient, Mean Absolute Error, Willmott index, Root Mean Square Error and Nash-Sutcliffe efficiency were used to evaluate the performance of the ML techniques. In addition, a comparison was made in the test set among the machine learning models in which, RSM outperformed the rest of the models irrespective of coating type. Neem oil/ Acacia oil(ml): clay/sulfer (g): age (days) for minimum nitrate leaching was found to be 2.61: 1.67: 2.4 for coating of USG with bentonite clay and neem oil without heating, 2.18: 2: 1 for bentonite clay and neem oil with heating and 1.69: 1.64: 2.18 for coating USG with sulfer and acacia oil. The research would provide guidelines to researchers and policymakers to select the appropriate tool for precise prediction of nitrate leaching, which would optimise the yield and the benefit-cost ratio.

Modeling of soil moisture movement and wetting behavior under point-source trickle irrigation

The design and selection of ideal emitter discharge rates can be aided by accurate information regarding the wetted soil pattern under surface drip irrigation. The current field investigation was conducted in an apple orchard in SKUAST- Kashmir, Jammu and Kashmir, a Union Territory of India, during 2017-2019. The objective of the experiment was to examine the movement of moisture over time and assess the extent of wetting in both horizontal and vertical directions under point source drip irrigation with discharge rates of 2, 4, and 8 L h-1. At 30, 60, and 120 min since the beginning of irrigation, a soil pit was dug across the length of the wetted area on the surface in order to measure the wetting pattern. For measuring the soil moisture movement and wetted soil width and depth, three replicas of soil samples were collected according to the treatment and the average value were considered. As a result, 54 different experiments were conducted, resulting in the digging of pits [3 emitter discharge rates × 3 application times × 3 replications × 2 (after application and 24 after application)]. This study utilized the Drip-Irriwater model to evaluate and validate the accuracy of predictions of wetting fronts and soil moisture dynamics in both orientations. Results showed that the modeled values were very close to the actual field values, with a mean absolute error of 0.018, a mean bias error of 0.0005, a mean absolute percentage error of 7.3, a root mean square error of 0.023, a Pearson coefficient of 0.951, a coefficient of correlation of 0.918, and a Nash-Sutcliffe model efficiency coefficient of 0.887. The wetted width just after irrigation was measured at 14.65, 16.65, and 20.62 cm; 16.20, 20.25, and 23.90 cm; and 20.00, 24.50, and 28.81 cm in 2, 4, and 8 L h-1, at 30, 60, and 120 min, respectively, while the wetted depth was observed 13.10, 16.20, and 20.44 cm; 15.10, 21.50, and 26.00 cm; 19.40, 25.00, and 31.00 cm, respectively. As the flow rate from the emitter increased, the amount of moisture dissemination grew (both immediately and 24 h after irrigation). The soil moisture contents were observed 0.4300, 0.3808, 0.2298, 0.1604, and 0.1600 cm3 cm-3 just after irrigation in 2 L h-1 while 0.4300, 0.3841, 0.2385, 0.1607, and 0.1600 cm3 cm-3 were in 4 L h-1 and 0.4300, 0.3852, 0.2417, 0.1608, and 0.1600 cm3 cm-3 were in 8 L h-1 at 5, 10, 15, 20, and 25 cm soil depth in 30 min of application time. Similar distinct increments were found in 60, and 120 min of irrigation. The findings suggest that this simple model, which only requires soil, irrigation, and simulation parameters, is a valuable and practical tool for irrigation design. It provides information on soil wetting patterns and soil moisture distribution under a single emitter, which is important for effectively planning and designing a drip irrigation system. Investigating soil wetting patterns and moisture redistribution in the soil profile under point source drip irrigation helps promote efficient planning and design of a drip irrigation system.

Assessment of drought conditions and prediction by machine learning algorithms using Standardized Precipitation Index and Standardized Water-Level Index (case study: Yazd province, Iran)

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 (R2 = 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.