Evaluating the influencing factors of groundwater evolution in rapidly urbanizing areas using long-term evidence DOI
Fengjie Li, Yang Liu, Nusrat Nazir

et al.

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 136, P. 103728 - 103728

Published: Sept. 6, 2024

Language: Английский

Prediction of Nitrate Concentration and the Impact of Land Use Types on Groundwater in the Nansi Lake Basin DOI
Javed Iqbal, Chunli Su, Hasnain Abbas

et al.

Journal of Hazardous Materials, Journal Year: 2025, Volume and Issue: 487, P. 137185 - 137185

Published: Jan. 14, 2025

Language: Английский

Citations

4
Optimizing Machine Learning Algorithms for Landslide Susceptibility Mapping along the Karakoram Highway, Gilgit Baltistan, Pakistan: A Comparative Study of Baseline, Bayesian, and Metaheuristic Hyperparameter Optimization Techniques DOI Creative Commons

Farkhanda Abbas,

Feng Zhang, Muhammad Ismail

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(15), P. 6843 - 6843

Published: Aug. 1, 2023

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match specific task at hand. The selection configuration directly impact performance models. Achieving optimal hyperparameter settings often requires a deep understanding underlying models appropriate optimization techniques. While there are many automatic techniques available, each with its own advantages disadvantages, this article focuses on well-known It explores cutting-edge methods such as metaheuristic algorithms, learning-based optimization, Bayesian quantum our paper focused mainly provides guidance applying them different algorithms. also presents real-world applications by conducting tests spatial data collections landslide susceptibility mapping. Based experiment's results, both showed promising compared baseline For instance, algorithm boosted random forest model's overall accuracy 5% 3%, respectively, from GS RS, 4% 2% GA PSO. Additionally, like KNN SVM, Gaussian processes had good results. When RS GS, model was enhanced BO-TPE 1% 11%, BO-GP 12%, respectively. outperformed 6% terms performance, while improved results 5%. thoroughly discusses reasons behind efficiency By successfully identifying configurations, research aims assist researchers, analysts, industrial users developing more effectively. findings insights provided can contribute enhancing applicability various domains.

Language: Английский

Citations

26
A comparative hydrochemical assessment of groundwater quality for drinking and irrigation purposes using different statistical and ML models in lower gangetic alluvial plain, eastern India DOI

Sribas Kanji,

Subhasish Das,

Chandi Rajak

et al.

Chemosphere, Journal Year: 2025, Volume and Issue: 372, P. 144074 - 144074

Published: Jan. 13, 2025

Language: Английский

Citations

1
Pollution indicators and human health risk assessment of fluoride contaminated drinking groundwater in southern Pakistan DOI Creative Commons

Shakeel Ahmed Talpu,

Muhammad Rashad, Aziz Ahmed

et al.

HydroResearch, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

Citations

6
Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications DOI Creative Commons
Anam Nigar, Yang Li, Muhammad Yousuf Jat Baloch

et al.

Frontiers in Environmental Science, Journal Year: 2024, Volume and Issue: 12

Published: May 28, 2024

Classifying land use and cover (LULC) is essential for various environmental monitoring geospatial analysis applications. This research focuses on classification in District Sukkur, Pakistan, employing the comparison between machine deep learning models. Three satellite indices, namely, NDVI, MNDWI, NDBI, were derived from Landsat-8 data utilized to classify four primary categories: Built-up Area, Water Bodies, Barren Land, Vegetation. The main objective of this study evaluate compare effectiveness models including Random Forest achieved an overall accuracy 91.3% a Kappa coefficient 0.90. It accurately classified 2.7% area as 1.9% 54.8% 40.4% While slightly less accurate, Decision Tree model provided reliable classifications. Deep showed significant accuracy, Convolutional Neural Networks (CNN) Recurrent (RNN). CNN impressive 97.3%, excelling classifying Bodies with User Producer Accuracy exceeding 99%. RNN model, 96.2%, demonstrated strong performance categorizing These findings offer valuable insights into potential applications perfect classifications, implications management analysis. rigorous validation comparative these contribute advancing remote sensing techniques their utilization tasks. presents contribution field underscores importance precise context sustainable conservation.

Language: Английский

Citations

4
Emerging from the depth: preliminary clues on groundwater upsurge in the coastal city of Zliten, Libya DOI Creative Commons
Majid Nazeer, Gomal Amin, Man Sing Wong

et al.

Geomatics Natural Hazards and Risk, Journal Year: 2025, Volume and Issue: 16(1)

Published: March 10, 2025

Language: Английский

Citations

0
Comprehensive analysis of groundwater hydrochemistry and nitrate health risks in the Baiquan basin, Northern China DOI Creative Commons
Bo Li, Di Wu,

Dalu Yu

et al.

PeerJ, Journal Year: 2025, Volume and Issue: 13, P. e19233 - e19233

Published: April 15, 2025

Groundwater is a crucial water source and strategic resource, essential for sustaining both urban rural livelihoods, supporting economic social development, maintaining ecological balance. This study investigates the hydrochemical properties controlling factors of groundwater in Baiquan basin (BQB) by analyzing quality data collected during dry wet periods. Additionally, suitability drinking agricultural irrigation was evaluated. The findings reveal that BQB generally weakly alkaline primarily consists hard-fresh water. Although there are seasonal variations main ion concentrations, HCO 3 − Ca 2+ predominant anions cations, respectively. Consequently, type mainly -Ca⋅Mg type, with secondary classification SO 4 ⋅Cl-Ca ⋅ Mg. composition influenced dissolution carbonate silicate minerals, as well cation exchange processes. it affected anthropogenic inputs, particularly from use fertilizers. assessment results indicated all samples classified either good or moderate, significant majority falling into category. northern section exhibited lower entropy weight index (EWQI) values season comparison to season. For irrigated agriculture, serves high-quality throughout rainy seasons. Furthermore, non-carcinogenic risks notably concentrated north-western south-eastern regions area. Health associated nitrates elevated Notably, infants were significantly high across seasons substantially exceeded those children adults. These provide valuable scientific insights management development resources BQB.

Language: Английский

Citations

0
Hydrogeochemistry and prediction of arsenic contamination in groundwater of Vehari, Pakistan: comparison of artificial neural network, random forest and logistic regression models DOI
Javed Iqbal, Chunli Su, Maqsood Ahmad

et al.

Environmental Geochemistry and Health, Journal Year: 2023, Volume and Issue: 46(1)

Published: Dec. 26, 2023

Language: Английский

Citations

7
Evaluating the influencing factors of groundwater evolution in rapidly urbanizing areas using long-term evidence DOI
Fengjie Li, Yang Liu, Nusrat Nazir

et al.

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 136, P. 103728 - 103728

Published: Sept. 6, 2024

Language: Английский

Citations

0