Climate Forecasting Framework for Urban Sustainability and Longevity using Machine Learning Model XGBoost

DOI

10.2991/978-94-6463-831-8_51How to use a DOI?

Keywords

Machine Learning (ML); Weather Forecasting; Time-Series Prediction; Performance Metrics; Urban Sustainability

Abstract

Climate is a chaotic one in nature and its variability incorporates rising temperatures, unpredictable rainfall, storms, and other weather parameters disrupting life, all living beings. Traditional meteorological forecasting methods often struggle to model complex and nonlinear climate patterns, highlighting the need for machine learning (ML) approaches to improve predictive accuracy.This study introduces an ML-based climate prediction framework that integrates XGBoost model. The methodology encompasses data pre-processing, feature engineering, hyper parameter tuning, bias correction, and performance evaluation using key evaluation metrics such as Mean Squared Error (MSE), while Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and finally the R2 Score. A historical weather dataset is used which includes weather parameters so as to train,validate and test the models, with advanced time-series techniques incorporated to enhance forecast precision.Experimental results demonstrate that ML-based models significantly outperform conventional forecasting techniques. XGBoost exhibits superior accuracy in short-term climate predictions, performing more accurately with an R2 score of 0.91.The incorporation of such a Machine Learning based climate prediction system into urban infrastructure helps to reduce health risks for the aging population. Ultimately, this research aligns with global sustainability goals which mainly target a real time, scalable framework for essential services regardless of unpredictable climate for the growing elderly population.

Copyright

© 2025 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  - Anup G. Dakre
AU  - Chaya R. Jadhav
PY  - 2025
DA  - 2025/08/31
TI  - Climate Forecasting Framework for Urban Sustainability and Longevity using Machine Learning Model XGBoost
BT  - Proceeding of the 1st International Conference on Lifespan Innovation (ICLI 2025)
PB  - Atlantis Press
SP  - 420
EP  - 427
SN  - 2468-5739
UR  - https://doi.org/10.2991/978-94-6463-831-8_51
DO  - 10.2991/978-94-6463-831-8_51
ID  - Dakre2025
ER  -