GROUNDWATER POTENTIAL ASSESSMENT IN GIA LAI PROVINCE (VIETNAM) USING MACHINE LEARNING, REMOTE SENSING AND GIS DOI Open Access
Huu Duy Nguyen,

Van Trong Giang,

Quang-Hai TRUONG

et al.

Geographia Technica, Journal Year: 2024, Volume and Issue: 19(2/2024), P. 13 - 32

Published: May 15, 2024

Population growth, urbanization and rapid industrial development increase the demand for water resources.Groundwater is an important resource in sustainable socio-economic development.The identification of regions with probability existence groundwater necessary helping decision makers to propose effective strategies management this resource.The objective study construct maps potential groundwater, based on machine learning algorithms, namely deep neural networks (DNNs), XGBoost (XGB), CatBoost (CB), Gia Lai province Vietnam.In study, 12 conditioning factors, elevation, aspect, curvature, slope, soil type, river density, distance road, land use/land cover (LULC), Normalized Difference Vegetation Index (NDVI), Normal Built-up (NDBI), Water (NDWI), rainfall were used, along 181 inventory points, models.The proposed models evaluated using receiver operating characteristic (ROC) curve, area under curve (AUC), root-mean-square error (RMSE), mean absolute (MAE).The results showed that predictions most accurate XGB model; CB came second, DNN was performed least well.About 4,990 km² found be category very low potential; 3,045 category; 2,426 classified as moderate, 2,665 high, 2,007 high.The methodology used creating maps.This approach, can provide valuable information factors influencing assist decisionmakers or developers managing resources sustainably.It also supports territory, including tourism.This other geographic a small change input data.

Language: Английский

Machine learning predictive insight of water pollution and groundwater quality in the Eastern Province of Saudi Arabia DOI Creative Commons
Abdulhayat M. Jibrin,

Mohammad Al-Suwaiyan,

Ali Aldrees

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 28, 2024

This study presents an innovative approach for predicting water and groundwater quality indices (WQI GWQI) in the Eastern Province of Saudi Arabia, addressing critical challenges scarcity pollution arid regions. Recent literature highlights increasing attention towards WQI based on index (WPI) GWQI as essential tools simplifying complex hydrogeological data, thereby facilitating effective management protection. Unlike previous works, present research introduces a novel hybrid method that integrates non-parametric kernel Gaussian learning (GPR), adaptive neuro-fuzzy inference system (ANFIS), decision tree (DT) algorithms. marks first application prediction offering significant advancement field. Through laboratory analysis combination various machine (ML) techniques, this enhances capabilities, particularly unmonitored sites semi-arid The study's objectives include feature engineering dependency sensitivity to identify most influential variables affecting GWQI, development predictive models using ANFIS, GPR, DT both indices. Furthermore, it aims assess impact different data portions predictions, exploring divisions such (70% / 30%), (60% 40%), (80% 20%) training testing phase, respectively. By filling gap resource management, offers implications regions facing similar environmental challenges. its methodology comprehensive analysis, contributes broader effort managing protecting resources areas. result proved GPR-M1 exhibited exceptional phase accuracy with RMSE = 0.0169 GWQI. Similarly, WPI, ANFIS-M1 achieved high skills 0.0401. results emphasize role quantity enhancing model robustness precision assessment.

Language: Английский

Citations

13
Integrating experimental-based vulnerability mapping with intelligent identification of multi-aquifer groundwater salinization DOI Creative Commons
Mohamed A. Yassin, Sani I. Abba, A. G. Usman

et al.

Next Sustainability, Journal Year: 2025, Volume and Issue: 5, P. 100115 - 100115

Published: Jan. 1, 2025

Language: Английский

Citations

1
Water, Resources, and Resilience: Insights from Diverse Environmental Studies DOI Open Access
Katarzyna Pietrucha-Urbanik, J. Rak

Water, Journal Year: 2023, Volume and Issue: 15(22), P. 3965 - 3965

Published: Nov. 15, 2023

Water is our most precious resource, and its responsible management utilization are paramount in the face of ever-growing environmental challenges [...]

Language: Английский

Citations

21
Application of machine learning techniques to predict groundwater quality in the Nabogo Basin, Northern Ghana DOI Creative Commons

Joseph Nzotiyine Apogba,

Geophrey K. Anornu,

Arthur B. Koon

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e28527 - e28527

Published: March 30, 2024

The main objective of this study was to map the quality groundwater for domestic use in Nabogo Basin, a sub-catchment White Volta Basin Ghana, by applying machine learning techniques. conducted Random Forest (RF) algorithm predict quality, utilizing factors that influence occurrence and such as Elevation, Topographical Wetness Index (TWI), Slope length (LS), Lithology, Soil type, Normalize Different Vegetation (NDVI), Rainfall, Aspect, Slope, Plan Curvature (PLC), Profile (PRC), Lineament density, Distance faults, Drainage density. area predicted building model based on computed Arithmetic Water Quality Indices (WQI) (as dependent variable) existing boreholes, serve an indicator quality. WQI shows it ranges from 9.51 69.99%. This implied 21.97 %, 74.40 3.63 % had respectively likelihood excellent. models were found perform much better with RMSE 23.03 R2 value 0.82. highlighted essential understanding area, paving way further studies policy development management.

Language: Английский

Citations

7
Groundwater quality assessment using machine learning models: a comprehensive study on the industrial corridor of a semi-arid region DOI

Loganathan Krishnamoorthy,

V. Lakshmanan

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: unknown

Published: July 4, 2024

Language: Английский

Citations

4
Detection of concha bullosa using deep learning models in cone-beam computed tomography images: a feasibility study DOI Open Access
Shishir Shetty, Auwalu Saleh Mubarak, Leena R. David

et al.

Archives of Craniofacial Surgery, Journal Year: 2025, Volume and Issue: 26(1), P. 19 - 28

Published: Feb. 20, 2025

Pneumatization of turbinates, also known as concha bullosa (CB), is associated with nasal septal deviation and sinonasal pathologies. This study aims to evaluate the performance deep learning models in detecting CB coronal cone-beam computed tomography (CBCT) images. Standardized images were obtained from 203 CBCT scans (83 119 without CB) radiology archives a dental teaching hospital. These underwent preprocessing through hybridized contrast enhancement (CE) method using discrete wavelet transform (DWT). Of images, 162 randomly assigned training set 41 testing set. Initially, enhanced CE technique before being input into pre-trained models, namely ResNet50, ResNet101, MobileNet. The features extracted by each model then flattened random forest (RF) classifier. In subsequent phase, was refined incorporating DWT. CE-DWT-ResNet101-RF demonstrated highest performance, achieving an accuracy 91.7% area under curve (AUC) 98%. contrast, CE-MobileNet-RF recorded lowest at 82.46% AUC 92%. precision, recall, F1 score (all 92%) observed for CE-DWT-ResNet101-RF. Deep high However, confirm these results, further studies involving larger sample sizes various are required.

Language: Английский

Citations

0
Assessing Levels of Safety Integrity in Tap Water Quality - A Case Study Approach DOI Creative Commons
Barbara Tchórzewska-Cieślak, Katarzyna Pietrucha-Urbanik, J. Rak

et al.

Desalination and Water Treatment, Journal Year: 2025, Volume and Issue: unknown, P. 101093 - 101093

Published: March 1, 2025

Language: Английский

Citations

0
Hydrological simulation and forecasting of monthly groundwater levels using innovative artificial intelligence techniques for making policy decisions DOI
N. R. Patel,

M. Rao Vasala,

Prakash Chandra Swain

et al.

International Journal of Energy and Water Resources, Journal Year: 2025, Volume and Issue: unknown

Published: April 10, 2025

Language: Английский

Citations

0
A Hybrid Numerical Method Incorporating Machine Learning into Groundwater Level Model for Improving Simulation Accuracy DOI
Lin Zhu, Shuai Li, Huili Gong

et al.

ACS ES&T Water, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Language: Английский

Citations

0
Insightful Analysis and Prediction of SCOD Component Variation in Low-Carbon/Nitrogen-Ratio Domestic Wastewater via Machine Learning DOI Open Access
Xuyuan Zhang, Ying‐Qing Guo, Haoran Luo

et al.

Water, Journal Year: 2024, Volume and Issue: 16(7), P. 1018 - 1018

Published: April 1, 2024

The rapid identification of the amount and characteristics chemical oxygen demand (COD) in influent water is critical to operation wastewater treatment plants (WWTPs), especially for WWTPs face with a low carbon/nitrogen (C/N) ratio. Given that, this study carried out batch kinetic experiments soluble (SCOD) nitrogen degradation three established machine learning (ML) models accurate prediction variation SCOD. results indicate that four different kinds components were identified via parallel factor (PARAFAC) analysis. C1 (Ex/Em = 235 nm 275/348 nm, tryptophan-like substances/soluble microbial by-products) contributes majority internal carbon sources endogenous denitrification, whereas C4 (230 275/350 tyrosine-like substances) crucial readily biodegradable SCOD composition according models. Furthermore, gradient boosting decision tree (GBDT) algorithm achieved higher interpretability generalizability describing relationship between source components, an R2 reaching 0.772. A Shapley additive explanations (SHAP) analysis GBDT further validated above result. Undoubtedly, provided novel insights into utilizing ML predict through measurements excitation–emission matrix (EEM) specific Ex Em positions. could help us identify transformation species process, thus provide guidance optimized WWTPs.

Language: Английский

Citations

2