Ensemble Deep Learning Approach for Turbidity Prediction of Dooskal Lake Using Remote Sensing Data
- Title
- Ensemble Deep Learning Approach for Turbidity Prediction of Dooskal Lake Using Remote Sensing Data
- Creator
- Ramesh J.V.N.; Patibandla P.R.; Shanbhog M.; Ambala S.; Ashraf M.; Kiran A.
- Description
- The summer season in India is marked by a severe shortage of water, which poses significant challenges for daily usage and agricultural practices. With unpredictable weather patterns and irregular rainfall, it is crucial to monitor and maintain water bodies such as domestic ponds and lakes in urban areas to ensure they provide clean and safe water for regular use, free from industrial pollutants. In this research paper, we propose an innovative ensemble deep learning approach (e-DLA) that leverages deep learning models to predict the turbidity of Dooskal Lake, located in Telangana, India, using remote sensing data. The proposed approach utilizes various deep learning models, including bagging, boosting, and stacking, to analyze the complex relationships between remote sensing data and turbidity levels in the lake. The study aims to provide accurate and efficient predictions of turbidity levels, which can aid in the management and conservation of water resources in the region. Hyperparameter tuning is employed, and dynamic climatic features are extracted and integrated with the ensemble learning global protective intelligent algorithm to reveal the complex relationship between in situ and measured values of turbidity during the measuring timeline. The proposed approach provides accurate predictions of turbidity levels, enabling the implementation of effective control measures to maintain water quality standards. Experimental results demonstrate that the proposed approach significantly reduces prediction errors compared to existing deep learning models. Overall, this research highlights the potential of machine learning techniques in monitoring and maintaining water resources, particularly in urban areas, to support sustainable water management and usage, and addresses an urgent and pressing issue in India and around the world. 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
- Source
- Remote Sensing in Earth Systems Sciences, Vol-6, No. 45750, pp. 146-155.
- Date
- 2023-01-01
- Publisher
- Springer Nature
- Subject
- Deep learning models; Ensemble learning; Remote sensing data; Turbidity; Water resources
- Coverage
- Ramesh J.V.N., Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur Dist, Andhra Pradesh, Vaddeswaram, 522502, India; Patibandla P.R., Department of Electronics & Communication Engineering, Dhanekula Institute of Engineering & Technology, Ganguru, Vijayawada, 521139, India; Shanbhog M., School of Sciences, CHRIST (Deemed to be University), Ghaziabad, Delhi NCR, 201003, India; Ambala S., Computer Engineering Department, Pimpri Chinchwad College of Engineering, Maharastra, Pune, India; Ashraf M., Computer Science & Engineering, School of Technology, Maulana Azad National Urdu University, TS, Hyderabad, India; Kiran A., Department of Computer Science and Engineering, MLR Institute of Technology, Dundigal, Telangana, Hyderabad, 500043, India
- Rights
- Restricted Access
- Relation
- ISSN: 25208195
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Ramesh J.V.N.; Patibandla P.R.; Shanbhog M.; Ambala S.; Ashraf M.; Kiran A., “Ensemble Deep Learning Approach for Turbidity Prediction of Dooskal Lake Using Remote Sensing Data,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 27, 2025, https://archives.christuniversity.in/items/show/13912.