Search

One of the most critical stages for developing groundwater resources for drinking water use is assessing the water quality. The use of a Water Quality Index (WQI) is considered an effective method of evaluating water quality. The objective of this research was to evaluate the performance of six multiple artificial intelligence techniques, i.e., linear regression (stepwise), support vector regression SVM (linear and polynomial kernels), Gaussian process regression (GPR), Fit binary tree, and artificial neural network ANN (Bayesian) to predict the WQI in Jizan, Southern Saudi Arabia. A total of 145 groundwater samples were collected from shallow dug wells and boreholes tapping the phreatic aquifer. The WQI was calculated from 11 physicochemical parameters (pH, TDS, Ca2+, Mg2+, Na+, K+, Cl−, SO42−, HCO3−, NO3−, and TH). The spatial distribution results showed that higher values of Cl− and SO42− were recorded in the places close to the coastline, indicating the occurrence of seawater intrusion and salinisation. Seven wells had a WQI of greater than 300, indicating that the water was unfit for consumption. The results showed that the GPR, linear regression (stepwise), and ANN models performed best during the training and testing stages, with a high correlation of 1.00 and low errors. The stepwise fitting model indicated that pH, K+, and NO3− were the most significant variables, while HCO3− was a non-significant variable for the WQI. The GPR, stepwise regression, and ANN models performed best during the training and testing stages, with a high correlation and low errors. In contrast, the SVM and Fit binary tree models performed the worst in the training and testing phases. Based on subset regression analysis, the optimum input combination for WQI model prediction was determined as these eight input combinations with high R2 (0.975–1.00) and high Adj-R2 (0.974–1.00). The resultant WQI model significantly contributes to sustainable groundwater resource management in arid areas and generates improved prediction precision with fewer input parameters.

Recently, machine learning (ML) and deep learning (DL) models based on artificial intelligence (AI) have emerged as fast and reliable tools for predicting water quality index (WQI) in various regions worldwide. In this study, we propose a novel stacking framework based on DL models for WQI prediction, employing a convolutional neural network (CNN) model. Additionally, we introduce explainable AI (XAI) through XGBoost-based SHAP (SHapley Additive exPlanations) values to gain valuable insights that can enhance decision-making strategies in water management. Our findings demonstrate that the stacking model achieves the highest accuracy in WQI prediction (R2: 0.99, MAPE: 15.99%), outperforming the CNN model (R2: 0.90, MAPE: 58.97%). Although the CNN model shows a relatively high R2 value, other statistical measures indicate that it is actually the worst-performing model among the five tested. This discrepancy may be attributed to the limited training data available for the CNN model. Furthermore, the application of explainable AI (XAI) techniques, specifically XGBoost-based SHAP values, allows us to gain deep insights into the models and extract valuable information for water management purposes. The SHAP values and interaction plot reveal that elevated levels of total dissolved solids (TDS), zinc, and electrical conductivity (EC) are the primary drivers of poor water quality. These parameters exhibit a nonlinear relationship with the water quality index, implying that even minor increases in their concentrations can significantly impact water quality. Overall, this study presents a comprehensive and integrated approach to water management, emphasizing the need for collaborative efforts among all stakeholders to mitigate pollution levels and uphold water quality. By leveraging AI and XAI, our proposed framework not only provides a powerful tool for accurate WQI prediction but also offers deep insights into the models, enabling informed decision-making in water management strategies.

The water supply in Saudi Arabia is already depleted. Climate change will exacerbate the demand for these resources. This paper examines how climate change affects the water demands of Saudi Arabia’s most important food crops: wheat, clover, vegetables, and dates. To reduce the adverse climate change impacts on these crops’ productivity, as well as their irrigation water requirements (IWR), a number of adaptation techniques were investigated. The study was carried out for the Ar Riyadh region, Saudi Arabia, with a cultivated area of 179,730 ha. In this study, five climate models from the Coupled Model Intercomparison Project Phase 6 (CMIP6) for two Shared Socio-economic Pathways (SSPs), SSP2-4.5 and SSP5-8.5, were used to forecast and investigate the potential impacts of climate change on agricultural water resources in the Al-Riyadh Region of Saudi Arabia. To simulate IWRs under the present and projected climate change scenarios, CROPWAT8.0 was used. The results showed that the maximum increase ratio in 2100 under SSP2-4.5 and SSP5-8.5, respectively, will be 4.46% and 12.11% higher than in the current case (2020). The results showed that the projected maximum temperatures in 2100 will be increased by 4.46% and 12.11%, respectively, under SSP2-4.5 and SSP5-8.5, compared to the current case (2020), supporting past research on the Arabian Peninsula that revealed that both short- and long-term temperature increases are anticipated to be considerable. Under SSP2-4.5 and SSP5-8.5, the projected ETo was found to be increased by 2.18% and 6.35% in 2100, respectively. Given that evapotranspiration closely mirrors the temperature behavior in the study region from June to August, our data suggest that crop and irrigation demand may increase in the mid to long term. The findings indicate that Riyadh, Saudi Arabia’s capital and commercial hub, will require more water to irrigate agricultural land because of the expanding ETo trend. Under SSP2-4.5 and SSP5-8.5, the projected growth irrigation water requirement (GIWR) will be increased by 3.1% and 6.7% in 2100, respectively. Under SSP5-8.5, crop areas of wheat, clover, dates, maize, citrus, tomato, potato, and other vegetables in Ar Riyadh will decrease by 6.56%, 7.17%, 5.90%, 6.43%, 5.47%, 6.99%, 5.21%, and 5.5%, respectively, in 2100. Conversely, under SSP2-4.5, the crop areas will decrease by 3.10%, 3.67%, 2.35%, 3.83%, 2.32%, 4.18%, 1.72%, and 2.38% in 2100, respectively. This research could aid in clarifying the adverse climate change impacts on GIWR in Ar Riyad, as well as improving water resource management planning.

The present study was carried out using artificial neural network (ANN) model for predicting the sodium hazardness, i.e., sodium adsorption ratio (SAR), percent sodium (%Na) residual, Kelly’s ratio (KR), and residual sodium carbonate (RSC) in the groundwater of the Pratapgarh district of Southern Rajasthan, India. This study focuses on verifying the suitability of water for irrigational purpose, wherein more groundwater decline coupled with water quality problems compared to the other areas are observed. The southern part of the Rajasthan State is more populated as compared to the rest of the parts. The southern part of the Rajasthan is more populated as compared to the rest of the Rajasthan, which leads to the industrialization, urbanization, and evolutionary changes in the agricultural production in the southern region. Therefore, it is necessary to propose innovative methods for analyzing and predicting the water quality (WQ) for agricultural use. The study aims to develop an optimized artificial neural network (ANN) model to predict the sodium hazardness of groundwater for irrigation purposes. The ANN model was developed using ‘nntool’ in MATLAB software. The ANN model was trained and validated for ten years (2010–2020) of water quality data. An L-M 3-layer back propagation technique was adopted in ANN architecture to develop a reliable and accurate model for predicting the suitability of groundwater for irrigation. Furthermore, statistical performance indicators, such as RMSE, IA, R, and MBE, were used to check the consistency of ANN prediction results. The developed ANN model, i.e., ANN4 (3-12-1), ANN4 (4-15-1), ANN1 (4-5-1), and ANN4 (3-12-1), were found best suited for SAR, %Na, RSC, and KR water quality indicators for the Pratapgarh district. The performance analysis of the developed model (3-12-1) led to a correlation coefficient = 1, IA = 1, RMS = 0.14, and MBE = 0.0050. Hence, the proposed model provides a satisfactory match to the empirically generated datasets in the observed wells. This development of water quality modeling using an ANN model may help to useful for the planning of sustainable management and groundwater resources with crop suitability plans as per water quality.

Coastal environments need continuous environmental risk assessment, especially with increasing coastal development and human activities. The present work evaluates the distribution, contamination, and environmental risk of potentially toxic elements (PTEs) in coastal sediments between Al-Jubail and Al-Khafji cities along the Arabian Gulf, Saudi Arabia, and documents the influence of background references applied in pollution indices. Thirty-two sediment samples were collected for analysis of Ni, Cu, Cr, As, Zn, Pb and Hg using ICP-AES. The ranges of PTEs (mg/kg) were in the following order: Cr (3.00–20.0), Ni (2.00–32.0), Zn (2.00–14.0), As (2.00–4.00), Pb (1.50–5.00), Cu (1.00–5.00), and Hg (0.50–1.00). The coastal sediments show severe enrichment with As and Hg, and no to minor enrichment and a low contamination with Cr, Cu, Cr, Zn, and Pb. Based on sediment quality guidelines, concentrations of Cu, Pb, Zn, As, and Cr do not represent a concern for benthic communities, while Ni and Hg show a risk for benthic communities in four and 17 sampled areas, respectively. Multivariate analysis indicated a geogenic source for Zn, Cr, Cu, Ni, and Pb, mixed natural and anthropogenic sources for As, and an anthropogenic source for Hg, mostly from oil pollution, sewage, and industrial effluents spreading near Al-Jubail industrial city.

Loveringite, a rare member of the crichtonite group with nominal formula (Ca,Ce)(Ti,Fe,Cr,Mg)21O38, was found in the Khamal layered mafic intrusion, the first known locality for this mineral in the Arabian Shield. The Khamal intrusion, a large post-collisional mafic complex, is lithologically zoned, bottom to top, from olivine gabbro through gabbronorite, hornblende gabbro, anorthosite, and diorite to quartz diorite. Loveringite is found near the base of the complex, as an intercumulus phase in olivine gabbro. Most loveringite grains are homogeneous, although a few grains are zoned from cores rich in TiO2, Al2O3, Cr2O3, and CaO towards rims rich in FeO*, ZrO2, V2O3, Y2O3, and rare earth elements (REE). Petrographic relations indicate that loveringite formed after crystallization of cumulus olivine, pyroxenes, and plagioclase. Anhedral and corroded crystals of loveringite are surrounded by reaction rims of Mn-bearing ilmenite and baddeleyite, suggesting that the residual liquid evolved into and subsequently out of the stability field of loveringite. The budget of incompatible elements (Zr, Hf, REE, U, and Th) hosted in loveringite is anomalous for a primitive mafic liquid. Saturation in loveringite is likely the result of early contamination of the primary melt by anatexis of country rock, followed by isolation of evolving liquid in intercumulus space that restricted communication with the overlying magma chamber. The zoned crystals likely reflect diffusive equilibration between residual loveringite grains and their reaction rims of ilmenite.

This study assessed the spatiotemporal variability and pollution grades of heavy metals in water and sediments of Bahr El-Baqar drain, Eastern Nile Delta, Egypt, by integration of geochemical analysis, metal pollution indices, correlation, and multivariate statistical analyses. Twenty samples of water and sediments were collected during 2018 and analyzed for heavy metal concentrations using ICP-OES. Heavy metal contents in the water samples followed the order: Fe > Zn > Al > Pb > Mn > Cu > Ni. The drain sediments were highly contaminated with heavy metals that followed the order: Fe > Al > Mn > V > Zn > Cu > Cr > Ba > Ni > Pb > As. Spatiotemporally, most metals in the drain sediments showed a decreasing trend from upstream (south) to downstream sites (north). Results of principal component analysis (PCA) supported those from the Pearson correlation between investigated heavy metals. In water, Mn, Ni, Pb, Zn, Cu, and Fe showed highly significant correlations. In sediments, Ba, Ni, Zn, Fe, Al, Mn, and V showed strong positive correlations indicating that these metals were derived from similar anthropogenic sources. The calculated metal pollution indices: enrichment factor (EF), contamination factor (CF), pollution load index (PLI), degree of contamination (DC), and index of geo-accumulation (Igeo) indicated high loadings of heavy metals in the drain sediments. EFs revealed low, moderate to significant enrichment, whereas CFs showed low, moderate, and considerable contamination. PLI indicated low, baseline, and progressive contamination, while DC indicated low, moderate, and considerable degree of contamination. Igeo of all investigated metals (except for As; class 1) indicated extremely contaminated sediments (class 7).

Changes in the terrestrial total water storage (TWS) have been estimated at both global and river basin scales from the Gravity Recovery and Climate Experiment (GRACE) mission and are still being detected from its GRACE Follow-On (GRACE-FO) mission. In this contribution, the sixth release of GRACE-FO (RL06) level-2 products applying DDK5 (decorrelation filter) were used to detect water mass variations for the Nile River Basin (NRB) in Africa and the Mega Aquifer System (MAS) in Asia. The following approach was implemented to detect the mass variation over the NRB and MAS: (1) TWS mass (June 2018–June 2021) was estimated by converting the spherical harmonic coefficients from the decorrelation filter DDK 5 of the GRACE-FO Level-2 RL06 products into equivalent water heights, where the TWS had been re-produced after removing the mean temporal signal (2) Precipitation data from Global Precipitation Climatology Project was used to investigate the pattern of change over the study area. Our findings include: (1) during the GRACE-FO period, the mass variations extracted from the RL06-DDK5 solutions from the three official centers—CSR, JPL, and GFZ—were found to be consistent with each other, (2) The NRB showed substantial temporal TWS variations, given a basin average of about 6 cm in 2019 and about 12 cm in 2020 between September and November and a lower basin average of about −9 cm in 2019 and −6 cm in 2020 in the wet seasons between March and May, while mass variations for the MAS had a relatively weaker temporal TWS magnitude, (3) the observed seasonal signal over the NRB was attributed to the high intensity of the precipitation events over the NRB (AAP: 1000–1800 mm yr−1), whereas the lack of the seasonal TWS signal over the MAS was due to the low intensity of the precipitation events over the MAS (AAP:180–500 mm yr−1).

Every day, mining corporations grow and develop over Egypt’s Eastern Desert in search of gold, silver, and other metals. Mineral resources in Egypt are a powerful tool for increasing national income. In this study, we are interested in mineral exploration, such as gold and porphyry deposits, using aeromagnetic data, applying various processing techniques such as First Vertical Derivative, Total Horizontal Gradient, Analytical Signal, Tilt Derivative, and the center of exploration targeting (CET). The study area is located at the Central Eastern Desert, which includes the Barramiya, Abu Marwa, and Abu Mireiwah regions. The analysis of the delineated structural trends shows that the N–S, NW–SE, and NE–SW are the most effective directions for managing deposits in the investigated area. A minor trend is also shown in the E–W direction and corresponds to the alteration zones reported by geology and prior investigations. Mineralization zones occur most frequently at the contact between ophiolitic serpentinite, sediments, and other rock types. This study intends to add more about the use of the recently developed technology of CET grid analysis for mineral exploration and structural interpretation across the Central Eastern Desert. The CET porphyry analysis map shows locations where several occurrences of porphyry deposits are probable. The newly discovered spots are similar to the area’s usual deposit sites. This study proves that aeromagnetic data are significant in mineral exploration since they are useful for the discovery of the structure and shear zones controlling the mineralization zones.

Porphyromonas gingivalis (P. gingivalis) is a cornerstone pathogen in the development and progression of periodontal and peri-implant tissue destruction. It is capable of causing dysbiosis of the microbial biofilm and modulation of the host immune system. Hyaluronic acid (HA) is a naturally occurring glycosaminoglycan found in all living organisms. It is well known and has been used for improving tissue healing. In addition, some studies have suggested that there may be an antimicrobial potential to HA. The aim of this study was to evaluate the effect of hyaluronic acid, azithromycin (AZM), and chlorhexidine (CHX) on the expression of genes (i.e., fimA, mfa1, hagA, rgpA, rgpB, and kgp) related to the virulence and adhesion of P. gingivalis. The study groups were divided into four: (1) HA treated group; (2) AZM treated group; (3) CHX treated group; and (4) untreated group to serve as a negative control. P. gingivalis ATCC 33277 was cultured and then exposed to four different concentrations (100% MIC, 50% MIC, 25% MIC, and 12.5% MIC) of HA, AZM, and CHX for 24 h. The expression levels of the aforementioned genes were measured using quantitative reverse transcription polymerase chain reaction (RT-qPCR). Relative fold-change values were calculated and compared between groups. The fold-change values of all genes combined were 0.46 ± 0.33, 0.31 ± 0.24, and 0.84 ± 0.77 for HA, AZM, and CHX, respectively. HA has downregulated all the genes by mostly a half-fold: 0.35 ± 0.20, 0.47 ± 0.35, 0.44 ± 0.25, 0.67 ± 0.46, 0.48 ± 0.33 and 0.35 ± 0.22 with fimA, mfa1, hagA, rgpA, rgpB and kgp, respectively. The effect of HA was significant on all genes except rgpB compared to the untreated control. Lower concentrations of HA tended to exhibit greater downregulation with 1 mg/mL being the most effective. High molecular weight (1.5 MDa) hyaluronic acid has a potent effect on P. gingivalis by downregulating fimA, mfa1, hagA, rgpA, and kgp. The effect of HA was generally less than that of AZM but greater than that of CHX.