Mapping of groundwater productivity potential with machine learning algorithms: A case study in the provincial capital of Baluchistan, Pakistan

Rasool, Umair; Yin, Xia; Xu, Zongxue; Rasool, Muhammad Awais; Senapathi, Venkatramanan; Hussain, Mureed; Siddique, Jamil; Trabucco, Juan Carlos

doi:10.1016/j.chemosphere.2022.135265

Cited by 28 publications

(7 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AI-based ML models have been applied in a number of hydrogeological studies such as for surface and subsurface water quality monitoring [76], flood and landslide hazard mapping [78], groundwater potential zoning [63,79], etc. However, the DL models such as CNN and DNN were used only in a few studies [25,80].…”

Section: Discussionmentioning

confidence: 99%

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

Alshehri

Rahman

2023

Water

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

Alshehri

Rahman

2023

Water

View full text Add to dashboard Cite

show abstract

“…There are many different network types for the ANN model. Compared to other prediction techniques, ANN has the benefit of using less training data to provide better results (Rasool et al, 2022).…”

Section: Regressionmentioning

confidence: 99%

“…The XGBoost model combines numerous weak learners (per tree) to produce a strong learner through additive learning. It enhances the workout, avoids over fitting, and reduces the loss function (Rasool et al, 2022).…”

Section: Regressionmentioning

confidence: 99%

“…Another algorithm that has been utilized is the Support Vector Machines (SVM), which is used for both classification and regression tasks. SVM is a generalized linear classifier that is a supervised learning approach for classification and regression issues (Rasool et al, 2022). It finds an optimal hyperplane that maximally separates data points of different classes or predicts the value of a continuous variable based on support vectors.…”

Section: Regressionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Geological and Climatic Variables in Groundwater Availability Prediction in Africa: Machine Learning Approaches

Touré,

Boateng,

Gidigasu

et al. 2024

Preprint

View full text Add to dashboard Cite

Groundwater is crucial for Africa's potable water supply, agriculture, and economic development. However, the continent faces challenges with groundwater scarcity due to factors like population growth, climate change, and over exploitation. Over the past ten years, machine learning has been increasingly and successfully used in groundwater level prediction across the world. This review paper explores the application of machine learning techniques in predicting groundwater levels in Africa. The methodology involved downloading relevant papers, identifying and categorizing the machine learning algorithms employed, and quantifying their use. Geological and climatic variables were also identified, analyzed and categorized to measure their usage frequency. The different algorithms and input variables extracted from each paper are graphically represented in this document highlighting the most employed ones. The findings suggest that the available literature on this topic in Africa is limited compared to the rest of the world. Tree-based algorithms are commonly used in machine learning in Africa, and the most employed input variables are related to geomorphology and temperature. The study highlights the potential of machine learning in improving water resource management and decision-making in the region.

show abstract

“…Due to its accuracy and low cost perspectives the use of ML alongside geospatial tools have become popular over the years in many developing countries especially in the South Asian countries. Ensemble Modelling Framework for groundwater level 2 prediction in Bihar 19 , groundwater Arsenic and health risk prediction model using ML in Pakistan 28 , mapping of groundwater productivity potential with ML algorithms in the provincial capital of Baluchistan, Pakistan 29 , water quality analysis with the help of ML algorithms in Sri Lanka by 30 shows the growing interest of ML algorithms in these countries to detect the groundwater modeling. Prediction of groundwater level changes has been done in several circumstances 31 , 32 ,.…”

Section: Introductionmentioning

confidence: 99%

Future groundwater potential mapping using machine learning algorithms and climate change scenarios in Bangladesh

Sarkar,

Rudra,

Talukdar

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The aim of the study was to estimate future groundwater potential zones based on machine learning algorithms and climate change scenarios. Fourteen parameters (i.e., curvature, drainage density, slope, roughness, rainfall, temperature, relative humidity, lineament density, land use and land cover, general soil types, geology, geomorphology, topographic position index (TPI), topographic wetness index (TWI)) were used in developing machine learning algorithms. Three machine learning algorithms (i.e., artificial neural network (ANN), logistic model tree (LMT), and logistic regression (LR)) were applied to identify groundwater potential zones. The best-fit model was selected based on the ROC curve. Representative concentration pathways (RCP) of 2.5, 4.5, 6.0, and 8.5 climate scenarios of precipitation were used for modeling future climate change. Finally, future groundwater potential zones were identified for 2025, 2030, 2035, and 2040 based on the best machine learning model and future RCP models. According to findings, ANN shows better accuracy than the other two models (AUC: 0.875). The ANN model predicted that 23.10 percent of the land was in very high groundwater potential zones, whereas 33.50 percent was in extremely high groundwater potential zones. The study forecasts precipitation values under different climate change scenarios (RCP2.6, RCP4.5, RCP6, and RCP8.5) for 2025, 2030, 2035, and 2040 using an ANN model and shows spatial distribution maps for each scenario. Finally, sixteen scenarios were generated for future groundwater potential zones. Government officials may utilize the study’s results to inform evidence-based choices on water management and planning at the national level.

show abstract

Mapping of groundwater productivity potential with machine learning algorithms: A case study in the provincial capital of Baluchistan, Pakistan

Cited by 28 publications

References 60 publications

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

A Review of Geological and Climatic Variables in Groundwater Availability Prediction in Africa: Machine Learning Approaches

Future groundwater potential mapping using machine learning algorithms and climate change scenarios in Bangladesh

Contact Info

Product

Resources

About