Adam et al. (2026) Predicting Lake Water Levels: A Comprehensive Survey of ML-Methods

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Idriss Oumar Adam, Daouda Ahmat
• DOI: 10.1007/978-981-95-2878-3_8

Research Groups

• University of N’Djamena, N’Djamena, Chad

Short Summary

This paper presents a comprehensive survey of existing machine learning methods for predicting lake water levels, analyzing 70 selected scientific articles to provide an overview of current models, advances, and challenges in the field.

Objective

• To examine existing machine learning methods for predicting lake water levels to understand and anticipate water level fluctuations for water resource management and preservation.

Study Configuration

• Spatial Scale: Review of studies on various lakes globally.
• Temporal Scale: Review of studies with varying temporal scales (short-term to long-term predictions).

Methodology and Data

• Models used: This is a survey paper reviewing various Machine Learning (ML) and Deep Learning (DL) models, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), hybrid models, and other AI-based approaches for lake water level prediction.
• Data sources: The survey itself is based on a database of 168 scientific articles from Google Scholar, IEEE Xplore, ACM, MDPI, and other open-access libraries, with 70 articles selected for detailed review. The reviewed papers likely use various data sources such as satellite data, in-situ observations, and hydro-meteorological data.

Main Results

• The survey provides a comprehensive overview of the latest machine learning models and methods applied to lake water level prediction.
• It highlights significant advances achieved through these techniques in understanding and anticipating water level fluctuations.
• It identifies and discusses the challenges associated with the application of artificial intelligence in this domain.

Contributions

• This paper offers a comprehensive and systematic review of machine learning methods for lake water level prediction, synthesizing findings from 70 rigorously selected scientific articles.
• It provides a valuable resource for researchers and practitioners by outlining current models, highlighting advances, and identifying key challenges, thereby guiding future research directions in the field of water resource management using AI.

Funding

• Not explicitly mentioned in the provided text.

Citation

@article{Adam2026Predicting,
  author = {Adam, Idriss Oumar and Ahmat, Daouda},
  title = {Predicting Lake Water Levels: A Comprehensive Survey of ML-Methods},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-981-95-2878-3_8},
  url = {https://doi.org/10.1007/978-981-95-2878-3_8}
}