Development of artificial intelligence models for well groundwater quality simulation: Different modeling scenarios

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.

Effects of elevated arsenic and nitrate concentrations on groundwater resources in deltaic region of Sundarban Ramsar site, Indo-Bangladesh region

An attempt has been adopted to predict the As and NO₃^- concentration in groundwater (GW) in fast-growing coastal Ramsar region in eastern India. This study is focused to evaluate the As and NO₃^- vulnerable areas of coastal belts of the Indo-Bangladesh Ramsar site a hydro-geostrategic region of the world by using advanced ensemble ML techniques including NB-RF, NB-SVM and NB-Bagging. A total of 199 samples were collected from the entire study area for utilizing the 12 GWQ conditioning factors. The predicted results are certified that NB-Bagging the most suitable and preferable model in this current research. The vulnerability of As and NO₃^- concentration shows that most of the areas are highly vulnerable to As and low to moderately vulnerable to NO₃. The reliable findings of this present study will help the management authorities and policymakers in taking preventive measures in reducing the vulnerability of water resources and corresponding health risks.

Pre- and post-dam river water temperature alteration prediction using advanced machine learning models

Dams significantly impact river hydrology by changing the timing, size, and frequency of low and high flows, resulting in a hydrologic regime that differs significantly from the natural flow regime before the impoundment. For precise planning and judicious use of available water resources for agricultural operations and aquatic habitats, it is critical to assess the dam water's temperature accurately. The building of dams, particularly several dams in rivers, can significantly impact downstream water. In this study, we predict the daily water temperature of the Yangtze River at Cuntan. Thus, this work reveals the potential of machine learning models, namely, M5 Pruned (M5P), Random Forest (RF), Random Subspace (RSS), and Reduced Error Pruning Tree (REPTree). The best and effective input variables combinations were determined based on the correlation coefficient. The outputs of the various machine learning algorithm models were compared with recorded daily water temperature data using goodness-of-fit criteria and graphical analysis to arrive at a final comparison. Based on a number of criteria, numerical comparison between the models revealed that M5P model performed superior (R2 = 0.9920, 0.9708; PCC = 0.9960, 0.9853; MAE = 0.2387, 0.4285; RMSE = 0.3449, 0.4285; RAE = 6.2573, 11.5439; RRSE = 8.0288, 13.8282) in pre-impact and post-impact spam, respectively. These findings suggest that a huge wave of dam construction in the previous century altered the hydrologic regimes of large and minor rivers. This study will be helpful for the ecologists and river experts in planning new reservoirs to maintain the flows and minimize the water temperature concerning spillway operation. Finally, our findings revealed that these algorithms could reliably estimate water temperature using a day lag time input in water level. They are cost-effective techniques for forecasting purposes.

Assessing the Impact of Groundwater Extraction on the Performance of Fractured Concrete Subsurface Dam in Controlling Seawater Intrusion in Coastal Aquifers

Among the well-known approaches for controlling seawater intrusion during extensive freshwater abstraction from coastal aquifers is the construction of subsurface dams. In the current research, the SEAWAT code is being implemented to examine the impact of groundwater extraction on the effectiveness of a damaged subsurface dam for controlling saltwater intrusion. Simulations were performed numerically to check impact of the subsurface dam height, dam location, well height, well location, abstraction rate, fracture aperture, fracture location, seawater density and fracture dimension on the effectiveness of subsurface dam as a countermeasure to prevent saltwater intrusion in coastal aquifers. Increasing the abstraction rate from 1 × 10−6 to 5 × 10−6 m3/s caused the seawater to advance more into the freshwater, and the loss of effectiveness increased. The minimum and maximum value of loss of subsurface dam effectiveness was recorded to be 34.6% to 93%, respectively, for the abstraction rates from the well equal 1 × 10−6 and 5 × 10−6 m3/s, consequentially. When the dimensionless value of well height location Lw/Ld is increased from 1.0 to 2.0, the effectiveness of the subsurface dam is reduced by around 20%. The findings demonstrate that the well location, well depth, abstraction rate, location of the dam, fracture aperture, and density of saltwater all affect the effectiveness impairment of the fractured subsurface dam for controlling saltwater intrusion. Decision makers could use findings of this research to better manage groundwater resources in coastal aquifers.

Computational assessment of groundwater salinity distribution within coastal multi-aquifers of Bangladesh

The rising salinity trend in the country’s coastal groundwater has reached an alarming rate due to unplanned use of groundwater in agriculture and seawater seeping into the underground due to sea-level rise caused by global warming. Therefore, assessing salinity is crucial for the status of safe groundwater in coastal aquifers. In this research, a rigorous hybrid neurocomputing approach comprised of an Adaptive Neuro-Fuzzy Inference System (ANFIS) hybridized with a new meta-heuristic optimization algorithm, namely Aquila optimization (AO) and the Boruta-Random forest feature selection (FS) was developed for estimating the salinity of multi-aquifers in coastal regions of Bangladesh. In this regard, 539 data samples, including ten water quality indices, were collected to provide the predictive model. Moreover, the individual ANFIS, Slime Mould Algorithm (SMA), and Ant Colony Optimization for Continuous Domains (ACOR) coupled with ANFIS (i.e., ANFIS-SMA and ANFIS-ACOR) and LASSO regression (Lasso-Reg) schemes were examined to compare with the primary model. Several goodness-of-fit indices, such as correlation coefficient (R), the root mean squared error (RMSE), and Kling-Gupta efficiency (KGE) were used to validate the robustness of the predictive models. Here, the Boruta-Random Forest (B-RF), as a new robust tree-based FS, was adopted to identify the most significant candidate inputs and effective input combinations to reduce the computational cost and time of the modeling. The outcomes of four selected input combinations ascertained that the ANFIS-OA regarding the best accuracy in terms of (R = 0.9450, RMSE = 1.1253 ppm, and KGE = 0.9146) outperformed the ANFIS-SMA (R = 0.9406, RMSE = 1.1534 ppm, and KGE = 0.8793), ANFIS-ACOR (R = 0.9402, RMSE = 1.1388 ppm, and KGE = 0.8653), Lasso-Reg (R = 0.9358), and ANFIS (R = 0.9306) models. Besides, the first candidate input combination (C1) by three inputs, including Cl⁻ (mg/l), Mg²⁺ (mg/l), Na⁺ (mg/l), yielded the best accuracy among all alternatives, implying the role importance of (B-RF) feature selection. Finally, the spatial salinity distribution assessment in the study area ascertained the high predictability potential of the ANFIS-OA hybrid with B-RF feature selection compared to other paradigms. The most important novelty of this research is using a robust framework comprised of the non-linear data filtering technique and a new hybrid neuro-computing approach, which can be considered as a reliable tool to assess water salinity in coastal aquifers.

Neurocomputing Modelling of Hydrochemical and Physical Properties of Groundwater Coupled with Spatial Clustering, GIS, and Statistical Techniques

Groundwater (GW) is a critical freshwater resource for billions of individuals worldwide. Rapid anthropogenic exploitation has increasingly deteriorated GW quality and quantity. Reliable estimation of complex hydrochemical properties of GW is crucial for sustainable development. Real field and experimental studies in an agricultural area from the significant sandstone aquifers (Wajid Aquifer) were conducted. For the modelling purpose, three types of computational models, including the emerging Hammerstein–Wiener (HW), back propagation neural network (BPNN), and statistical multi-variate regression (MVR), were developed for the multi-station estimation of total dissolved solids (TDS) (mg/L) and total hardness (TH) (mg/L). A geographic information system (GIS) was used for the spatial variability assessment of 32 hydrochemical and physical properties of the GW aquifer. A comprehensive visualized literature review spanning several decades was conducted in order to gain an understanding of the existing research and debates relevant to a particular GW and artificial intelligence (AI) study. The experimental data, pre-processing, and feature selection were conducted to determine the most dominant variables for AI-based modelling. The estimation results were evaluated using determination coefficient (DC), mean bias error (MBE), mean square error (MSE), and root mean square error (RMSE). The outcomes proved that TDS (mg/L) and TH (mg/L) correlated more than 90% and 70–85% with Ca2+, Cl−, Br−, NO3−, and Fe, and Na+, SO42−, Mg2+, and F− combinations, respectively. HW-M1 justified promising among all the models with MBE = 1.41 × 10−11, 1.14 × 10−14, and MSE = 7.52 × 10−2, 3.88 × 10−11 for TDS (mg/L), TH (mg/L), respectively. The accuracy proved merit for the overall development of and practical estimation of hydrochemical variables (TDS, TH) (mg/L) and decision-making benchmarks.

Delineating groundwater contamination risks in southern coastal metropoles through implementation of geochemical and socio-environmental data in decision-tree and geographical information system

Due to global warming and local anthropogenic pressures, sustainable groundwater resource exploitation in coastal cities is increasingly threatened. For example, the fifth largest Brazilian city, Recife, is considered as a representative hot spot for these issues and illustrates the great challenges facing many urban areas in the southern hemisphere. There, recharge as well as surface water and groundwater quality are altered by frequent droughts and poorly planned environmental management since decades. To maintain access to water, thousands of private wells were dug in order to pump water from the multi-layered aquifer system found under the city. This massive exploitation is causing a chronic lowering of the water levels, as well as seawater intrusion and contaminations by wastewater or polluted surface waters. Through hydrochemical characterization, mainly Cl/Br ratio and Cl concentrations, of wells sampled throughout the metropole, this study first characterizes the main environmental impacts on the resource, i.e. waste waters and seawater. Combining this evaluation with lithological, land-use and socio-environmental data, it was then possible to build decision trees identifying combinations of multiple factors possibly having an impact on contamination types. The well and population densities, the waste and sewage management, as well as the absence of sanitary facilities in houses appeared as critical parameters to target in order to reduce the risk of contamination of the water resource and ensure its preservation. Based on these factors, we created a risk map for contamination types that should help in identifying areas where groundwater resource may present an environmental (and then health) issue for people. Besides, this study shows that the combination of hydrochemical, geomorphological and socio-environmental characterizations of these urban systems featuring very contrasted situations between neighborhoods is a relevant tool to propose further groundwater management strategies.

The assessment of emerging data-intelligence technologies for modeling Mg+2 and SO4-2 surface water quality

The concentration of soluble salts in surface water and rivers such as sodium, sulfate, chloride, magnesium ions, etc., plays an important role in the water salinity. Therefore, accurate determination of the distribution pattern of these ions can improve better management of drinking water resources and human health. The main goal of this research is to establish two novel wavelet-complementary intelligence paradigms so-called wavelet least square support vector machine coupled with improved simulated annealing (W-LSSVM-ISA) and the wavelet extended Kalman filter integrated with artificial neural network (W-EKF- ANN) for accurate forecasting of the monthly), magnesium (Mg⁺²), and sulfate (SO₄^-2) indices at Maroon River, in Southwest of Iran. The monthly River flow (Q), electrical conductivity (EC), Mg⁺², and SO₄^-2 data recorded at Tange-Takab station for the period 1980-2016. Some preprocessing procedures consisting of specifying the number of lag times and decomposition of the existing original signals into multi-resolution sub-series using three mother wavelets were performed to develop predictive models. In addition, the best subset regression analysis was designed to separately assess the best selective combinations for Mg⁺² and SO₄^-2. The statistical metrics and authoritative validation approaches showed that both complementary paradigms yielded promising accuracy compared with standalone artificial intelligence (AI) models. Furthermore, the results demonstrated that W-LSSVM-ISA-C1 (correlation coefficient (R) = 0.9521, root mean square error (RMSE) = 0.2637 mg/l, and Kling-Gupta efficiency (KGE) = 0.9361) and W-LSSVM-ISA-C4 (R = 0.9673, RMSE = 0.5534 mg/l and KGE = 0.9437), using Dmey mother that outperformed the W-EKF-ANN for predicting Mg⁺² and SO4^-2, respectively.