ML Framework for Real-Time Weather Forecasting

Read full text Summarise with VIRAT
Authors: Badrinarayanan P S, Vignesh V, Mrs. Elavarasi R, Dr.G.A.Senthil
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This research presents an integrated Machine Learning-Based Weather Prediction and Travel Decision-Making Recommendation System to enhance the accuracy of short-term weather forecasts and improve decision-making in travel planning. The proposed system integrates real-time weather data into several machine learning algorithms, including Random Forests, Gradient Boosting, and Long Short-Term Memory (LSTM) networks, to generate adaptive and location-specific forecasts. Random Forest and Gradient Boosting algorithms capture complex nonlinear relationships between meteorological variables, while LSTM networks effectively model the temporal dependencies in sequential weather data, enabling robust time-series forecasting. Real-time data are collected through weather application programming interfaces (APIs) and continuously fused with extensive historical datasets to improve model accuracy and reliability. The system’s recommendation module analyses predictive results to provide users with weather-informed travel suggestions, outdoor activity options, and optimized itineraries, allowing dynamic adjustment based on changing weather conditions. Experimental results demonstrate that this hybrid model delivers superior accuracy and lower mean error rates compared to conventional approaches, showing faster responsiveness to extreme weather situations. Beyond assisting travellers in making informed choices, the system supports tourism authorities in resource management, risk mitigation, and safety planning. Overall, the research highlights how integrating machine learning and real-time data fusion enables smarter, sustainable, and context-aware tourism planning.

Fields of Study & Subjects

Hydrological Forecasting Using AI Forecasting Techniques and Applications Traffic Prediction and Management Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
22 March 2026
Language
EN
Document type
Book