Predictive Modeling of Lake Area Variations Using Machine Learning Techniques

DOI

10.2991/978-94-6239-693-7_71How to use a DOI?

Keywords

Machine Learning; Lake Area Prediction; Regression Models; Environmental Data; Flood Control; Urban Planning; Sustainable Development; Feature Engineering; Performance Metrics

Abstract

Lake areas prediction is a prerequisite for safe and sound environmental management and planning, especially in the regions that are influenced by the changed hydrological regime. This Research displays what machine learning regression methodologies Regression (Linear Regression, Ridge Regression, and Random Forest Regression) can be carried out to predict changes of the lake area in Chennai using the real historical data from the past 35 years. The data set consists of the lake area measurements of Retteri, Kolathur, Ambattur, and Puzhal Lakes for each year along with the respective environmental variables of rainfall, land use, and water flow. The data go through an extensive process that includes the preprocessing step, which consists of cleaning the data and dealing with the missing values replacement, and feature engineering that altogether ensures the data’s consistency and data reliability. The model’s performance is evaluated by criteria such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and the R measure. To confirm the models, cross-validation procedures are used in order to try to ascertain the model’s stability. The results are that the Random Forest Regression model yields the highest accuracy of approximately 92%, outperforming Linear and Ridge Regression models. The proposed approach will predict the area of a lake using changes in environmental conditions that could vary by use for flood control, water resource management, and thus, this research shows that regional spatial integration is strong enough and proper for the purposes of sustainable urban development; it can be a powerful method to improve some accuracy, and coverage of lake area prediction systems is included that easily helps during the process of environmental planning, makes it more proactive, and makes decision- making easier.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. B. KeerthanaSree
AU  - M. Keerthana
AU  - A. Yovan Felix
PY  - 2026
DA  - 2026/06/16
TI  - Predictive Modeling of Lake Area Variations Using Machine Learning Techniques
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 717
EP  - 725
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_71
DO  - 10.2991/978-94-6239-693-7_71
ID  - KeerthanaSree2026
ER  -