A Real-Time Traffic Congestion Prediction System Using Weather and Temporal Data

Read full text Summarise with VIRAT
Authors: D. Thepaak Raajhan, Dr. S. Parthasarathy
Cited by: 0
References: 7

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

Urban traffic congestion directly impacts travel time, fuel consumption, and commuter safety. SmartFlow AI is an intelligent web-based system that predicts traffic congestion levels by integrating machine learning, live weather data, and real-time route mapping. A classification model trained on historical traffic and environmental data predicts congestion as High, Moderate, or Low using inputs such as day of week, time of travel, traffic volume, and weather factors including temperature, humidity, and rainfall. Built on Streamlit, the system accepts source and destination locations, applies Nominatim geocoding, OSRM routing, and OpenWeatherMap for live weather retrieval. When high congestion is detected, alternative routes are automatically recommended and visualized using interactive Folium maps. SmartFlow AI combines traffic prediction, weather analysis, and route optimization into a single accessible platform to enhance commuter decision-making.

Fields of Study & Subjects

Traffic Prediction and Management Techniques Transportation Planning and Optimization Traffic control and management

Publication details

Journal / source
Iconic Research and Engineering Journals
Volume
9
Issue
9
Publication date
25 March 2026
Language
EN