Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
The Science of the total environment
2025
|
| Subjects: | |
| Online Access: | https://pubmed.ncbi.nlm.nih.gov/41260044/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1868266125094027264 |
|---|---|
| author | Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah |
| author_facet | Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah |
| collection | PubMed - marine biology |
| contents | Advanced machine learning models for accurate water quality classification and WQI prediction: Implications for aquatic disease risk management. Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah Machine Learning Water Quality Environmental Monitoring Risk Management Aquaculture Accurate classification of water quality and precise prediction of the Water Quality Index (WQI) are essential for safeguarding aquatic ecosystems and mitigating disease risks in aquaculture. This study systematically evaluates multiple machine learning models including LightGBM, XGBoost, Random Forest, and Support Vector Machines using grid search optimization to enhance performance. Results show that ensemble models, particularly LightGBM and XGBoost, achieved superior accuracy in water quality classification (up to 99.65 %). For WQI prediction, XGBoost regression delivered the highest performance with an R of 0.9685. SHAP (SHapley Additive exPlanations) analysis was employed to interpret model predictions and quantify feature contributions. Dissolved oxygen and BOD emerged as the most influential predictors, followed by turbidity, nitrate, and electrical conductivity, aligning with known risk factors for aquatic disease outbreaks. These findings underscore the potential of combining advanced machine learning with explainable AI techniques and real-time water quality data to enable proactive monitoring and early warning systems for sustainable aquatic health management. |
| format | Artículo científico |
| id | pubmed_41260044 |
| institution | PubMed |
| language | en |
| publishDate | 2025 |
| publisher | The Science of the total environment |
| record_format | pubmed |
| spellingShingle | Advanced machine learning models for accurate water quality classification and WQI prediction: Implications for aquatic disease risk management. Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah Machine Learning Water Quality Environmental Monitoring Risk Management Aquaculture Advanced machine learning models for accurate water quality classification and WQI prediction: Implications for aquatic disease risk management. Hridoy, Md Abdullah Al Mamun Shawkat, Abdullah Ibna Bordin, Chiara Acharjee, Mahima Ranjan Masood, Andleeb Baki, Azeez Olalekan Al Mamun, Md Abdullah Machine Learning Water Quality Environmental Monitoring Risk Management Aquaculture Accurate classification of water quality and precise prediction of the Water Quality Index (WQI) are essential for safeguarding aquatic ecosystems and mitigating disease risks in aquaculture. This study systematically evaluates multiple machine learning models including LightGBM, XGBoost, Random Forest, and Support Vector Machines using grid search optimization to enhance performance. Results show that ensemble models, particularly LightGBM and XGBoost, achieved superior accuracy in water quality classification (up to 99.65 %). For WQI prediction, XGBoost regression delivered the highest performance with an R of 0.9685. SHAP (SHapley Additive exPlanations) analysis was employed to interpret model predictions and quantify feature contributions. Dissolved oxygen and BOD emerged as the most influential predictors, followed by turbidity, nitrate, and electrical conductivity, aligning with known risk factors for aquatic disease outbreaks. These findings underscore the potential of combining advanced machine learning with explainable AI techniques and real-time water quality data to enable proactive monitoring and early warning systems for sustainable aquatic health management. |
| title | Advanced machine learning models for accurate water quality classification and WQI prediction: Implications for aquatic disease risk management. |
| topic | Machine Learning Water Quality Environmental Monitoring Risk Management Aquaculture |
| url | https://pubmed.ncbi.nlm.nih.gov/41260044/ |