Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models
This study provides a cutting-edge machine learning approach to forecast ammonium (NH4+) levels in River Lee London. Ammonium concentrations were predicted over several time intervals using a complete dataset that includes temperature, turbidity, chlorophyll, dissolved oxygen, conductivity, and pH....
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Cleaner Water |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2950263224000498 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846117512375173120 |
|---|---|
| author | Ali J. Ali Ashraf A. Ahmed |
| author_facet | Ali J. Ali Ashraf A. Ahmed |
| author_sort | Ali J. Ali |
| collection | DOAJ |
| description | This study provides a cutting-edge machine learning approach to forecast ammonium (NH4+) levels in River Lee London. Ammonium concentrations were predicted over several time intervals using a complete dataset that includes temperature, turbidity, chlorophyll, dissolved oxygen, conductivity, and pH. Our technique captures the intricate connections between environmental conditions and ammonium concentrations using developed algorithms, including Temporal Fusion Transformer (TFT), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) levels versus the important factors, considerably improving prediction accuracy. The novel aspect of this study is the utilisation of the TFT model for multi-horizon forecasting, which offers high accuracy and interpretability in hydrological predictions by combining convolutional components with an attention mechanism. The study also demonstrates the effectiveness of the TFT model in capturing short-term fluctuations while retaining accuracy over long time periods, which is a major difficulty in environmental modelling. The models used, have exceptional forecasting skills, predicting 150, 200, 365, 730, and 1095 days based on daily average and 12, 24 and 30 months based on monthly average. This dual-scale model combines flexibility and resilience, making it an effective tool for forecasting both short- and long-term environmental changes. The RF model excelled in long-term forecasts, sustaining high R-squared (R²) (0.97) values and low root mean square error (RMSE) (0.18), and the second best one was the XGBoost with optimiser with R2 of (0.92) and RMSE of (0.25) with forecasting 1095 days. The results also found that whilst the TFT captured the fluctuations in the short-term, it struggled with the longer-term predictions due to data granularity. The XGBoost model did remarkably well in monthly forecasts up to 12 months, maintaining low RSME. The findings also highlight the necessity of proactive water management techniques to reduce the risk of potential ecological effects, including hypoxia and oxygen depletion. The findings support resource managers in addressing prospective ammonium toxicity concerns such as oxygen depletion and ecological stress. |
| format | Article |
| id | doaj-art-a9205124dc034a9fbb011fd1b1df0307 |
| institution | Kabale University |
| issn | 2950-2632 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Cleaner Water |
| spelling | doaj-art-a9205124dc034a9fbb011fd1b1df03072024-12-18T08:55:57ZengElsevierCleaner Water2950-26322024-12-012100051Long-term AI prediction of ammonium levels in rivers using transformer and ensemble modelsAli J. Ali0Ashraf A. Ahmed1Corresponding authors.; Department of Civil and Environmental Engineering, Brunel University London, Uxbridge UB8 3PH, UKCorresponding authors.; Department of Civil and Environmental Engineering, Brunel University London, Uxbridge UB8 3PH, UKThis study provides a cutting-edge machine learning approach to forecast ammonium (NH4+) levels in River Lee London. Ammonium concentrations were predicted over several time intervals using a complete dataset that includes temperature, turbidity, chlorophyll, dissolved oxygen, conductivity, and pH. Our technique captures the intricate connections between environmental conditions and ammonium concentrations using developed algorithms, including Temporal Fusion Transformer (TFT), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) levels versus the important factors, considerably improving prediction accuracy. The novel aspect of this study is the utilisation of the TFT model for multi-horizon forecasting, which offers high accuracy and interpretability in hydrological predictions by combining convolutional components with an attention mechanism. The study also demonstrates the effectiveness of the TFT model in capturing short-term fluctuations while retaining accuracy over long time periods, which is a major difficulty in environmental modelling. The models used, have exceptional forecasting skills, predicting 150, 200, 365, 730, and 1095 days based on daily average and 12, 24 and 30 months based on monthly average. This dual-scale model combines flexibility and resilience, making it an effective tool for forecasting both short- and long-term environmental changes. The RF model excelled in long-term forecasts, sustaining high R-squared (R²) (0.97) values and low root mean square error (RMSE) (0.18), and the second best one was the XGBoost with optimiser with R2 of (0.92) and RMSE of (0.25) with forecasting 1095 days. The results also found that whilst the TFT captured the fluctuations in the short-term, it struggled with the longer-term predictions due to data granularity. The XGBoost model did remarkably well in monthly forecasts up to 12 months, maintaining low RSME. The findings also highlight the necessity of proactive water management techniques to reduce the risk of potential ecological effects, including hypoxia and oxygen depletion. The findings support resource managers in addressing prospective ammonium toxicity concerns such as oxygen depletion and ecological stress.http://www.sciencedirect.com/science/article/pii/S2950263224000498Transformer modelExtreme gradient boostingRandom forest regressorRiver ecosystemToxicityAmmonium |
| spellingShingle | Ali J. Ali Ashraf A. Ahmed Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models Cleaner Water Transformer model Extreme gradient boosting Random forest regressor River ecosystem Toxicity Ammonium |
| title | Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models |
| title_full | Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models |
| title_fullStr | Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models |
| title_full_unstemmed | Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models |
| title_short | Long-term AI prediction of ammonium levels in rivers using transformer and ensemble models |
| title_sort | long term ai prediction of ammonium levels in rivers using transformer and ensemble models |
| topic | Transformer model Extreme gradient boosting Random forest regressor River ecosystem Toxicity Ammonium |
| url | http://www.sciencedirect.com/science/article/pii/S2950263224000498 |
| work_keys_str_mv | AT alijali longtermaipredictionofammoniumlevelsinriversusingtransformerandensemblemodels AT ashrafaahmed longtermaipredictionofammoniumlevelsinriversusingtransformerandensemblemodels |