Harnessing Explainable AI for Sustainable Agriculture: SHAP-Based Feature Selection in Multi-Model Evaluation of Irrigation Water Quality Indices DOI Open Access
Enas E. Hussein, Bilel Zerouali, Nadjem Bailek

et al.

Water, Journal Year: 2024, Volume and Issue: 17(1), P. 59 - 59

Published: Dec. 29, 2024

Irrigation water quality is crucial for sustainable agriculture and environmental health, influencing crop productivity ecosystem balance globally. This study evaluates the performance of multiple deep learning models in classifying Water Quality Index (IWQI), addressing challenge accurate prediction by examining impact increasing input complexity, particularly through chemical ions derived indices. The tested include convolutional neural networks (CNN), CNN-Long Short-Term Memory (CNN-LSTM), CNN-bidirectional Long (CNN-BiLSTM), Gated Recurrent Unit (CNN-BiGRUs). Feature selection via SHapley Additive exPlanations (SHAP) provided insights into individual feature contributions to model predictions. objectives were compare 16 identify most effective approach IWQI classification. utilized data from 166 wells Algeria’s Naama region, with 70% training 30% testing. Results indicate that CNN-BiLSTM outperformed others, achieving an accuracy 0.94 area under curve (AUC) 0.994. While CNN effectively capture spatial features, they struggle temporal dependencies—a limitation addressed LSTM BiGRU layers, which further enhanced bidirectional processing model. importance analysis revealed index (qi) qi-Na was significant predictor both Model 15 (0.68) (0.67). qi-EC showed a slight decrease importance, 0.19 0.18 between models, while qi-SAR qi-Cl maintained similar levels. Notably, included qi-HCO3 minor score 0.02. Overall, these findings underscore critical role sodium levels predictions suggest areas enhancing performance. Despite computational demands model, results contribute development robust management, thereby promoting agricultural sustainability.

Language: Английский

Typical pollutants in secondary water supply systems: Source, spread, and elimination DOI

Gaolei Liu,

Zhenghao Yan,

Rong Mao

et al.

Journal of Water Process Engineering, Journal Year: 2025, Volume and Issue: 70, P. 106926 - 106926

Published: Jan. 9, 2025

Language: Английский

Citations

1
Alum sludge-driven electro-phytoremediation in constructed wetlands: a novel approach for sustainable nutrient removal DOI Creative Commons
Daryoush Sanaei, Amir Mirshafiee, Amir Adibzadeh

et al.

RSC Advances, Journal Year: 2025, Volume and Issue: 15(4), P. 2947 - 2957

Published: Jan. 1, 2025

In addition to their advantages as promising methods for wastewater treatment, CWs exhibit poor performance in terms of N and P removal efficiency the effluent treatment plants. By focusing on this issue, we designed integrated with a biochar-doped activated carbon cloth (ACC) electrode alum sludge from water plants substrate achieve concomitant organic matter nutrient efficiency. Compared use one layer (CWs-C3) ACC electrodes inserted two layers, which uses sludge, significant improvement was achieved (96% COD; 89% TN; 77% TP). The findings revealed that application potential accompanied by insertion cathode into first beneficial completing nitrification facilitating denitrification anode regions, respectively, resulting increased nutrients. Further evaluation TN-TP synergetic mechanism influenced Fe2+ an electron donor driving force development autotrophic denitrifying bacteria increase nitrate reduction. Additionally, formation FePO4 AlPO4 adsorption through interaction FeOOH AlOOH phosphate constitute main TP wastewater. Another reason CW-C3 reactor greater abundance microbial diversity effectuated regions. summary, strategy simultaneously promoting nutrients utilizing large scale practical applications proposed.

Language: Английский

Citations

0
Date Seed-Derived Activated Carbon: A Comparative Study on Heavy Metal Removal from Aqueous Solutions DOI Creative Commons
Mohammad Shahedur Rahman, Neetu Bansal, Mohammod Hafizur Rahman

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3257 - 3257

Published: March 17, 2025

The presence of heavy metals in groundwater and wastewater has been a concern for health organizations. This study investigated the effectiveness activated carbon derived from various natural precursors, including acorns red oak trees (Quercus rubra), date seeds, peach employing thermal activation method removal aqueous solutions. Batch adsorption tests effects sorbent quantity, pH levels, disinfectant presence, dissolved organic matter (DOM) on efficiency Pb Cu. Characterization prepared was conducted using scanning electron microscopy (SEM). Lead diminished at 7 relative to 3 5, but copper exhibited superior efficiencies compared 5. addition monochloramine 4 parts per million (ppm) effectively eliminated lead solution. A rise free chlorine concentration 2 mg/L led reduction metal water by 20 60%. DOM concentrations 1 6 reduced efficacy mg/L. Date seed-activated carbons underscore their distinctive potential, offering useful insights enhancement treatment systems.

Language: Английский

Citations

0
EFFECT OF THERMAL DRYING ON THE PHYSICO-CHEMICAL AND MICROBIOLOGICAL CHARACTERISTICS OF DRINKING WATER TREATMENT SLUDGE DOI Creative Commons
Juscimara Rodrigues Silva, MHC Carvalho, Amanda Maria Dantas de Jesus

et al.

Cleaner Engineering and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100947 - 100947

Published: March 1, 2025

Language: Английский

Citations

0
Removal of multiple metals from real wastewater combining sludges with carbon black and chitosan: integrating sustainable remediation and waste recycling DOI
Noemi Colozza,

Alessio Mattiello,

Leonardo Duranti

et al.

Journal of environmental chemical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 116660 - 116660

Published: April 1, 2025

Language: Английский

Citations

0
Harnessing Explainable AI for Sustainable Agriculture: SHAP-Based Feature Selection in Multi-Model Evaluation of Irrigation Water Quality Indices DOI Open Access
Enas E. Hussein, Bilel Zerouali, Nadjem Bailek

et al.

Water, Journal Year: 2024, Volume and Issue: 17(1), P. 59 - 59

Published: Dec. 29, 2024

Irrigation water quality is crucial for sustainable agriculture and environmental health, influencing crop productivity ecosystem balance globally. This study evaluates the performance of multiple deep learning models in classifying Water Quality Index (IWQI), addressing challenge accurate prediction by examining impact increasing input complexity, particularly through chemical ions derived indices. The tested include convolutional neural networks (CNN), CNN-Long Short-Term Memory (CNN-LSTM), CNN-bidirectional Long (CNN-BiLSTM), Gated Recurrent Unit (CNN-BiGRUs). Feature selection via SHapley Additive exPlanations (SHAP) provided insights into individual feature contributions to model predictions. objectives were compare 16 identify most effective approach IWQI classification. utilized data from 166 wells Algeria’s Naama region, with 70% training 30% testing. Results indicate that CNN-BiLSTM outperformed others, achieving an accuracy 0.94 area under curve (AUC) 0.994. While CNN effectively capture spatial features, they struggle temporal dependencies—a limitation addressed LSTM BiGRU layers, which further enhanced bidirectional processing model. importance analysis revealed index (qi) qi-Na was significant predictor both Model 15 (0.68) (0.67). qi-EC showed a slight decrease importance, 0.19 0.18 between models, while qi-SAR qi-Cl maintained similar levels. Notably, included qi-HCO3 minor score 0.02. Overall, these findings underscore critical role sodium levels predictions suggest areas enhancing performance. Despite computational demands model, results contribute development robust management, thereby promoting agricultural sustainability.

Language: Английский

Citations

0