Self-organizing maps as a way to evaluate optimal strategies for balancing binary class distributions: a methodological approach DOI Creative Commons
Alberto Nogales,

Diego Guadalupe,

Álvaro J. García-Tejedor

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 25, 2025

Abstract Since machine learning algorithms rely on data, the way datasets are collected significantly impacts their performance. Data must be carefully gathered to minimize missing values or class imbalance. However, inherent nature of data tends can sometimes lead such imbalances. An unbalanced dataset biased models, where predictions influenced by majority class. To avoid this problem, balancing strategies applied equalize instances each This paper introduces a methodological approach evaluate which yield best results depending dataset. We leverage self-organizing maps, an unsupervised neural network model, identify strategy generates most suitable balanced synthetic data. By considering topological structure we propose metric that uses trained map measure changes between original and transformed after applying different strategies. is based idea resembling more closely preferable.

Язык: Английский

Developing a novel tool for assessing the groundwater incorporating water quality index and machine learning approach DOI Creative Commons
Abdul Majed Sajib, Mir Talas Mahammad Diganta, Azizur Rahman

и другие.

Groundwater for Sustainable Development, Год журнала: 2023, Номер 23, С. 101049 - 101049

Опубликована: Ноя. 1, 2023

Groundwater plays a pivotal role as global source of drinking water. To meet sustainable development goals, it is crucial to consistently monitor and manage groundwater quality. Despite its significance, there are currently no specific tools available for assessing trace/heavy metal contamination in groundwater. Addressing this gap, our research introduces an innovative approach: the Quality Index (GWQI) model, developed tested Savar sub-district Bangladesh. The GWQI model integrates ten water quality indicators, including six heavy metals, collected from 38 sampling sites study area. enhance precision assessment, employed established machine learning (ML) techniques, evaluating model's performance based on factors such uncertainty, sensitivity, reliability. A major advancement incorporation metals into framework index model. best authors knowledge, marks first initiative develop encompassing heavy/trace elements. Findings assessment revealed that area ranged 'good' 'fair,' indicating most indicators met standard limits set by Bangladesh government World Health Organization. In predicting scores, artificial neural networks (ANN) outperformed other ML models. Performance metrics, root mean square error (RMSE), (MSE), absolute (MAE) training (RMSE = 0.361; MSE 0.131; MAE 0.262), testing 0.001; 0.00; 0.001), prediction evaluation statistics (PBIAS 0.000), demonstrated superior effectiveness ANN. Moreover, exhibited high sensitivity (R2 1.0) low uncertainty (less than 2%) rating These results affirm reliability novel monitoring management, especially regarding metals.

Язык: Английский

Процитировано

61
Innovative approach for predicting daily reference evapotranspiration using improved shallow and deep learning models in a coastal region: A comparative study DOI

Hussam Eldin Elzain,

Osman Abdalla, Mohammed Abdallah

и другие.

Journal of Environmental Management, Год журнала: 2024, Номер 354, С. 120246 - 120246

Опубликована: Фев. 14, 2024

Язык: Английский

Процитировано

21
Comparative Assessment of Machine Learning Models for Groundwater Quality Prediction Using Various Parameters DOI
Majid Niazkar, Reza Piraei, Mohammad Reza Goodarzi

и другие.

Environmental Processes, Год журнала: 2025, Номер 12(1)

Опубликована: Фев. 11, 2025

Язык: Английский

Процитировано

5
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

и другие.

Chemosphere, Год журнала: 2025, Номер 372, С. 144074 - 144074

Опубликована: Янв. 13, 2025

Язык: Английский

Процитировано

3
Evaluation and mapping of predicted future land use changes using hybrid models in a coastal area DOI
Hafez Ahmad, Mohammed Abdallah, Felix Jose

и другие.

Ecological Informatics, Год журнала: 2023, Номер 78, С. 102324 - 102324

Опубликована: Окт. 2, 2023

Язык: Английский

Процитировано

26
Evaluation of groundwater quality indices using multi-criteria decision-making techniques and a fuzzy logic model in an irrigated area DOI
Jamila Hammami Abidi,

Hussam Eldin Elzain,

S. Chidambaram

и другие.

Groundwater for Sustainable Development, Год журнала: 2024, Номер 25, С. 101122 - 101122

Опубликована: Фев. 16, 2024

Язык: Английский

Процитировано

16
An innovative approach for predicting groundwater TDS using optimized ensemble machine learning algorithms at two levels of modeling strategy DOI

Hussam Eldin Elzain,

Osman Abdalla, Hamdi Abdurhman Ahmed

и другие.

Journal of Environmental Management, Год журнала: 2024, Номер 351, С. 119896 - 119896

Опубликована: Янв. 3, 2024

Язык: Английский

Процитировано

15
Enhancing groundwater vulnerability assessment: Comparative study of three machine learning models and five classification schemes for Cuddalore district DOI
Subbarayan Saravanan, Thiyagarajan Saranya, Shankar Karuppannan

и другие.

Environmental Research, Год журнала: 2023, Номер 242, С. 117769 - 117769

Опубликована: Ноя. 28, 2023

Язык: Английский

Процитировано

18
Interpretable machine learning for predicting the fate and transport of pentachlorophenol in groundwater DOI Creative Commons
Mehran Naseri-Rad,

Azra Abtahi,

Ronny Berndtsson

и другие.

Environmental Pollution, Год журнала: 2024, Номер 345, С. 123449 - 123449

Опубликована: Янв. 24, 2024

Pentachlorophenol (PCP) is a commonly found recalcitrant and toxic groundwater contaminant that resists degradation, bioaccumulates, has potential for long-range environmental transport. Taking proper actions to deal with the pollutant accounting life cycle consequences requires better understanding of its behavior in subsurface. We recognize huge enhancing decision-making at contaminated sites arrival machine learning (ML) techniques applications. used ML enhance dynamics PCP transport properties subsurface, determine key hydrochemical hydrogeological drivers affecting fate. demonstrate how this complementary knowledge, provided by data-driven methods, may enable more targeted planning monitoring remediation two highly Swedish sites, where method was validated. evaluated 6 interpretable 3 linear regressors non-linear (i.e., tree-based) regressors, predict concentration groundwater. The modeling results indicate simple models were be useful prediction observations datasets without any missing values, while tree-based suitable containing values. Considering values are common collected during site investigations, could significant importance planners managers, ultimately reducing investigation costs. Furthermore, we interpreted proposed using SHAP (SHapley Additive exPlanations) approach decipher different simulation critical hydrogeochemical variables. Among these, sum chlorophenols highest significance analyses. Setting aside from model, tetra chlorophenols, dissolved organic carbon, conductivity importance. Accordingly, methods potentially improve contamination dynamics, filling gaps knowledge remain when sophisticated deterministic approaches.

Язык: Английский

Процитировано

7
An Optimized Approach for Predicting Water Quality Features and A Performance evaluation for Mapping Surface Water Potential Zones Based on Discriminant Analysis (DA), Geographical Information System (GIS) and Machine Learning (ML) Models in Baitarani River Basin, Odisha DOI Creative Commons

Abhijeet Das

Desalination and Water Treatment, Год журнала: 2025, Номер 321, С. 101039 - 101039

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1