Travel Time Estimation for Public Transit Reliability at Arbitrary Weather Conditions

Abstract

This research suggests a unique method for calculating trip times in public transport networks in India's wide range of weather scenarios. Reliability of public transport is important for commuters, especially in a nation with a diverse range of climates. Our model takes the influence of weather on transport operations into consideration by combining historical weather data with transit timetables. To forecast changes in journey time brought on by meteorological events like rain, fog, and extremely high or low temperatures, we apply machine learning algorithms. With the use of real-time data from weather forecasting services and transit agencies, our model provides precise and dynamic estimates. By means of comprehensive testing and verification utilising datasets from prominent Indian cities such as Bangalore, Delhi, and Mumbai, we exhibit the efficiency and resilience of our methodology under various meteorological conditions. The suggested methodology offers insightful information to help transport operators and planners improve customer experience, optimise timetables, and lessen the negative effects of bad weather on transit dependability. In the end, our research helps public transport networks in India become more resilient and efficient, which promotes sustainable urban mobility even in the face of climate uncertainty.

Keywords: Travel Time, Public Transit, Reliability, Weather Conditions