Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management
The scheme of water resources management is necessary for reducing water scarcity in arid areas and improving water availability in general. However, water leak detection and irrigation scheduling traditional AI models are often computationally intensive and require complex hyperparameter tuning, ma...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11008568/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839629764693852160 |
|---|---|
| author | Mahmoud Badee Rokaya Mahmoud Dalia Ismaeil Ibrahim Hemdan Samah Hazzaa Alajmani Raneem Yousif Alyami Ghada Elmarhomy Hassan Hashim El-Sayed Atlam |
| author_facet | Mahmoud Badee Rokaya Mahmoud Dalia Ismaeil Ibrahim Hemdan Samah Hazzaa Alajmani Raneem Yousif Alyami Ghada Elmarhomy Hassan Hashim El-Sayed Atlam |
| author_sort | Mahmoud Badee Rokaya Mahmoud |
| collection | DOAJ |
| description | The scheme of water resources management is necessary for reducing water scarcity in arid areas and improving water availability in general. However, water leak detection and irrigation scheduling traditional AI models are often computationally intensive and require complex hyperparameter tuning, making them less scalable. This study presents an artificial intelligence-based optimization framework that improves forecasting accuracy, computational speed, and real-time adaptability. The architecture combines the ensemble-learning algorithms (XGBoost, LightGBM), hybrid AIs (XGBoost + Autoencoder), and metaheuristic feature selection (GA, PSO, SA) for making intelligent decisions. Moreover, ontology-based feature structuring enhances interpretability, while hyperparameter tuning (GridSearchCV, Bayesian Optimization) and model compression techniques (pruning, quantization, knowledge distillation) ensure computational efficiency. A large number of experiments on real-world IoT sensor data testify to the effectiveness of the framework. It achieves 0.992 AUC-ROC scores for leak detection, an RMSE of 0.227 hours for irrigation scheduling, and an overall accuracy of 94.8%. Additional performance measures comprise precision (89.0%), recall (95.2%), F1-score (0.92), and inference speed (0.003 ms/sample). Although quantization has reduced the computational overhead, we still see a 13.02% increase in the model size as seen in Experiment 6, leading to a trade-off that needs to be optimized further. This study offers a deployable AI-based model for sustainable water management by tackling the issues of scalability, computational cost, and limitations in benchmark evaluation. By virtue of the empirical validation and comparative analysis of the framework, it has been shown to perform better than the regular methods, proving that the methodology can act as a step forward in the field of real-time, AI-assisted irrigation and leak detection systems. |
| format | Article |
| id | doaj-art-d49db9cfea6f4f7d93c77a5a47e67b82 |
| institution | Matheson Library |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d49db9cfea6f4f7d93c77a5a47e67b822025-07-14T23:00:27ZengIEEEIEEE Access2169-35362025-01-0113976289764610.1109/ACCESS.2025.357206711008568Optimized AI and IoT-Driven Framework for Intelligent Water Resource ManagementMahmoud Badee Rokaya Mahmoud0https://orcid.org/0000-0003-2975-7827Dalia Ismaeil Ibrahim Hemdan1https://orcid.org/0000-0002-5550-9301Samah Hazzaa Alajmani2https://orcid.org/0009-0000-7152-9559Raneem Yousif Alyami3https://orcid.org/0000-0002-3711-5106Ghada Elmarhomy4https://orcid.org/0000-0003-3678-9333Hassan Hashim5https://orcid.org/0009-0006-6724-7499El-Sayed Atlam6https://orcid.org/0000-0002-4728-590XDepartment of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaDepartment of Food Science and Nutrition, Faculty of Science, Taif University, Taif, Saudi ArabiaDepartment of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaDepartment of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Engineering, Taibah University, Yanbu, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Engineering, Taibah University, Yanbu, Saudi ArabiaDepartment Computer Science, Faculty of Science, Tanta University, Tanta, EgyptThe scheme of water resources management is necessary for reducing water scarcity in arid areas and improving water availability in general. However, water leak detection and irrigation scheduling traditional AI models are often computationally intensive and require complex hyperparameter tuning, making them less scalable. This study presents an artificial intelligence-based optimization framework that improves forecasting accuracy, computational speed, and real-time adaptability. The architecture combines the ensemble-learning algorithms (XGBoost, LightGBM), hybrid AIs (XGBoost + Autoencoder), and metaheuristic feature selection (GA, PSO, SA) for making intelligent decisions. Moreover, ontology-based feature structuring enhances interpretability, while hyperparameter tuning (GridSearchCV, Bayesian Optimization) and model compression techniques (pruning, quantization, knowledge distillation) ensure computational efficiency. A large number of experiments on real-world IoT sensor data testify to the effectiveness of the framework. It achieves 0.992 AUC-ROC scores for leak detection, an RMSE of 0.227 hours for irrigation scheduling, and an overall accuracy of 94.8%. Additional performance measures comprise precision (89.0%), recall (95.2%), F1-score (0.92), and inference speed (0.003 ms/sample). Although quantization has reduced the computational overhead, we still see a 13.02% increase in the model size as seen in Experiment 6, leading to a trade-off that needs to be optimized further. This study offers a deployable AI-based model for sustainable water management by tackling the issues of scalability, computational cost, and limitations in benchmark evaluation. By virtue of the empirical validation and comparative analysis of the framework, it has been shown to perform better than the regular methods, proving that the methodology can act as a step forward in the field of real-time, AI-assisted irrigation and leak detection systems.https://ieeexplore.ieee.org/document/11008568/AI-driven optimizationIoT sensor datasustainable water managementensemble learningirrigation schedulingleak detection |
| spellingShingle | Mahmoud Badee Rokaya Mahmoud Dalia Ismaeil Ibrahim Hemdan Samah Hazzaa Alajmani Raneem Yousif Alyami Ghada Elmarhomy Hassan Hashim El-Sayed Atlam Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management IEEE Access AI-driven optimization IoT sensor data sustainable water management ensemble learning irrigation scheduling leak detection |
| title | Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management |
| title_full | Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management |
| title_fullStr | Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management |
| title_full_unstemmed | Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management |
| title_short | Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management |
| title_sort | optimized ai and iot driven framework for intelligent water resource management |
| topic | AI-driven optimization IoT sensor data sustainable water management ensemble learning irrigation scheduling leak detection |
| url | https://ieeexplore.ieee.org/document/11008568/ |
| work_keys_str_mv | AT mahmoudbadeerokayamahmoud optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT daliaismaeilibrahimhemdan optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT samahhazzaaalajmani optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT raneemyousifalyami optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT ghadaelmarhomy optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT hassanhashim optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement AT elsayedatlam optimizedaiandiotdrivenframeworkforintelligentwaterresourcemanagement |