Inspiration
Urban public transportation systems often leave underserved regions without efficient options, creating bottlenecks and limiting access for low-income communities. We wanted to build a solution that helps policymakers and city planners quickly identify where new routes could improve equity and reduce congestion while making the planning process faster and more data-driven.
What it does
Transit Stations Map is an AI-powered route suggestion tool that leverages geospatial data, traffic patterns, and socioeconomic indicators to detect underserved areas and recommend new transit routes. These recommendations are displayed on an interactive Google Maps interface, giving planners a clear and actionable starting point to enhance transportation access and efficiency.
How we built it
We began by collecting public datasets related to traffic, income levels, and transit accessibility. These datasets were cleaned and processed to manage the complexity of large-scale geospatial information. We then used Gemini to analyze this data and generate optimized transit route recommendations. Finally, we integrated the results with Google Maps to create a user-friendly, interactive visualization for exploring and evaluating suggested routes.
Challenges we ran into
Integrating multiple complex datasets and aligning geospatial data with socioeconomic information was a major challenge. Generating complete path visualizations that accurately followed roads also proved difficult. Additionally, AI-generated route suggestions sometimes required manual review and refinement to ensure their real-world applicability.
Accomplishments that we're proud of
We built a functional AI pipeline capable of analyzing urban transit data and producing actionable insights. Successfully integrating this with Google Maps for real-time visualization was a key technical achievement. Most importantly, we created a tool that supports equitable transit planning and has the potential to improve public transportation access for underserved communities.
What we learned
We gained experience in handling and analyzing large-scale geospatial data, integrating AI into mapping applications, and designing for real-world use cases like policy planning. We also learned the importance of building solutions that balance technical innovation with practical utility for decision-makers and community impact.
What's next for Transit Stations Map
Next, we plan to add user personalization features, enabling users to input preferences or provide feedback on route suggestions. We also aim to incorporate additional datasets, such as existing policy plans and urban development projects, to add more context to our recommendations. Lastly, we will improve our mapping capabilities to generate complete, road-aligned route visualizations that closely match real-world transit infrastructure.
Log in or sign up for Devpost to join the conversation.