Evaluation of water quality indexes with novel machine learning and SHapley Additive ExPlanation (SHAP) approaches

Journal of Water Process Engineering, Год журнала: 2024, Номер 58, С. 104789 - 104789

Опубликована: Янв. 17, 2024

Язык: Английский

---

Predicting lake water quality index with sensitivity-uncertainty analysis using deep learning algorithms

Journal of Cleaner Production, Год журнала: 2023, Номер 406, С. 136885 - 136885

Опубликована: Апрель 3, 2023

Язык: Английский

---

Ensemble learning methods using the Hodrick–Prescott filter for fault forecasting in insulators of the electrical power grids

International Journal of Electrical Power & Energy Systems, Год журнала: 2023, Номер 152, С. 109269 - 109269

Опубликована: Июнь 6, 2023

Electrical power grid insulators installed outdoors are exposed to environmental conditions, such as the accumulation of contaminants on their surface. The increase surface conductivity insulators, increasing leakage current until there is a flashover. Evaluating in relation contamination level one way determine insulation condition. This paper evaluates time series from high-voltage laboratory experiment using porcelain pin-type insulators. Time forecasting performed with collection machine learning models known ensemble approaches, which include blending, bootstrap aggregation (bagging), sequential (boosting), random subspace, and stacked generalization. According this paper's findings, applying these approaches useful for enhancing performance occurrence breakdowns electrical system. Hodrick–Prescott filter reduces root mean square error metric (to be minimized) by 2.69 times subspace approach. results paper, proposed method stable, low variance when statistical analysis performed, being superior long short-term memory neural network.

Язык: Английский

---

Prediction of weighted arithmetic water quality index for urban water quality using ensemble machine learning model

Chemosphere, Год журнала: 2024, Номер 352, С. 141393 - 141393

Опубликована: Фев. 5, 2024

Язык: Английский

---

Forecasting the strength of graphene nanoparticles-reinforced cementitious composites using ensemble learning algorithms

Results in Engineering, Год журнала: 2024, Номер 21, С. 101837 - 101837

Опубликована: Фев. 6, 2024

Contemporary infrastructure requires structural elements with enhanced mechanical strength and durability. Integrating nanomaterials into concrete is a promising solution to improve However, the intricacies of such nanoscale cementitious composites are highly complex. Traditional regression models encounter limitations in capturing these intricate compositions provide accurate reliable estimations. This study focuses on developing robust prediction for compressive (CS) graphene nanoparticle-reinforced (GrNCC) through machine learning (ML) algorithms. Three ML models, bagging regressor (BR), decision tree (DT), AdaBoost (AR), were employed predict CS based comprehensive dataset 172 experimental values. Seven input parameters, including graphite nanoparticle (GrN) diameter, water-to-cement ratio (wc), GrN content (GC), ultrasonication (US), sand (SC), curing age (CA), thickness (GT), considered. The trained 70 % data, remaining 30 data was used testing models. Statistical metrics as mean absolute error (MAE), root square (RMSE) correlation coefficient (R) assess predictive accuracy DT AR demonstrated exceptional accuracy, yielding high coefficients 0.983 0.979 training, 0.873 0.822 testing, respectively. Shapley Additive exPlanation (SHAP) analysis highlighted influential role positively impacting CS, while an increased (w/c) negatively affected CS. showcases efficacy techniques accurately predicting nanoparticle-modified concrete, offering swift cost-effective approach assessing nanomaterial impact reducing reliance time-consuming expensive experiments.

Язык: Английский

---

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

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

Опубликована: Янв. 13, 2025

Язык: Английский

---

An Interpretable XGBoost-SHAP Machine Learning Model for Reliable Prediction of Mechanical Properties in Waste Foundry Sand-Based Eco-Friendly Concrete

Results in Engineering, Год журнала: 2025, Номер unknown, С. 104307 - 104307

Опубликована: Фев. 1, 2025

Язык: Английский

---

Novel Groundwater Quality Index (GWQI) model: A Reliable Approach for the Assessment of Groundwater

Results in Engineering, Год журнала: 2025, Номер unknown, С. 104265 - 104265

Опубликована: Фев. 1, 2025

Язык: Английский

---

Predicting water quality variables using gradient boosting machine: global versus local explainability using SHapley Additive Explanations (SHAP)

Earth Science Informatics, Год журнала: 2025, Номер 18(3)

Опубликована: Фев. 27, 2025

Язык: Английский

---

Prediction models for marshall mix parameters using bio-inspired genetic programming and deep machine learning approaches: A comparative study

Case Studies in Construction Materials, Год журнала: 2022, Номер 18, С. e01774 - e01774

Опубликована: Дек. 14, 2022

This research study utilizes four machine learning techniques, i.e., Multi Expression programming (MEP), Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Ensemble Decision Tree Bagging (DT-Bagging) for the development of new advanced models prediction Marshall Stability (MS), Flow (MF) asphalt mixes. A comprehensive detailed database 343 data points was established both MS MF. The predicting variables were chosen among most influential, easy-to-determine parameters. trained, tested, validated, outcomes newly developed compared with actual outcomes. root squared error (RSE), Nash-Sutcliffe efficiency (NSE), mean absolute (MAE), square (RMSE), relative (RRMSE), regression coefficient (R2), correlation (R), all used to evaluate performance models. sensitivity analysis (SA) revealed that in case MS, rising order input significance bulk specific gravity compacted aggregate, Gmb (38.56%) > Percentage Aggregates, Ps (19.84%) Bulk Specific Gravity Aggregate, Gsb (19.43%) maximum paving mix, Gmm (7.62%), while MF followed was: (36.93%) (14.11%) (10.85%) (10.19%). parametric (PA) consistency results relation previous findings. DT-Bagging model outperformed other values 0.971 0.980 16.88 0.24 28.27 0.36 0.069 0.041 0.020 0.032 0.010 0.016 (PI), 0.931 0.959 MF, respectively. comparison showed ANN, ANFIS, MEP, are effective reliable approaches estimation MEP-derived mathematical expressions represent novelty MEP relatively simple reliable. Roverall >MEP >ANFIS >ANN exceeding permitted range 0.80 Hence, modeling higher performance, possessed high generalization predication capabilities, assess parameters findings this would assist safer, faster, sustainable from standpoint resources time required perform tests.

Язык: Английский

---