Team Name

Siyani

Team Members

Project Description

Sustainable Transport Insights and LGA Analysis

**Warning: The prod version of the site is quite slow due to Data processing and using free services to host the site with slow free DB instance online aswell. Please wait for 15-20 seconds if the instance is in hibernate mode.

**All data is actual data from the sources and no use of mock data is implemented

Project Overview

This project focuses on analyzing transportation sustainability across various Local Government Areas (LGAs). Using data-driven insights, the application evaluates and ranks LGAs based on key transportation metrics such as public transport efficiency, infrastructure density, and sustainable transport usage (e.g., walking, public transport). The goal is to support urban planners, policymakers, and citizens by providing actionable insights to improve transportation sustainability and infrastructure planning.

Objective

The primary objective of this project is to calculate and provide insights into sustainable transport across different LGAs. These insights are designed to:
- Help policymakers understand the current transport infrastructure and usage.
- Highlight areas for improvement by suggesting additional infrastructure (bus/train stops).
- Rank LGAs based on sustainability metrics, allowing stakeholders to compare performance and identify best practices.

Key Features

1. Data Aggregation:

   • Gathers data from various sources (e.g., population, transport usage, infrastructure) and combines them into a unified view for each LGA.
   • Data includes bus/train stop counts, population, public transport users, and walkers within the LGA.

2. Sustainability Metrics:

   • Public Transport Efficiency: Calculates the percentage of the population using bus and train services.
   • Sustainable Ratio: Measures the percentage of the population using sustainable transport modes (bus, train, walking).
   • Infrastructure Density: Evaluates the number of public transport stops relative to population size to assess infrastructure adequacy.

3. Statewide Comparisons:

   • Calculates state averages for sustainable transport usage, public transport efficiency, and infrastructure density, offering benchmarks for each LGA's performance.
   • Ranks LGAs based on their sustainability metrics.

4. LGA-Level Insights:

   • Provides detailed reports on each LGA, including sustainability scores, infrastructure needs, and recommendations for additional bus/train stops to improve transport efficiency.
   • Users can select an LGA to view relevant data and suggestions for sustainable improvements.

Technologies Used

• Laravel (PHP): Backend framework handling data processing and calculations.
• Database: Integrates data from various datasets into a relational database for efficient querying.
• API Integration: Allows for integration with external APIs for additional data (e.g., geocoding services to link postcodes to LGAs).

Impact

This project contributes to more sustainable urban planning by offering data-backed insights into transportation infrastructure and usage. By highlighting areas for improvement and enabling comparisons between LGAs, it supports more informed decisions regarding resource allocation, infrastructure investments, and long-term planning for sustainable transport.

Data Story

Building a Sustainable Transport Score Using Geospatial and Survey Data
This project leverages a combination of demographic, infrastructure, geospatial, and survey datasets to generate a sustainability score for Local Government Areas (LGAs) in Victoria, Australia, based on transport efficiency. Here's how the data-driven process unfolded:

Step 1: Population Data Integration

Using the Digital Atlas of Australia, I downloaded both current and predicted population data for various LGAs. These datasets provided a foundation for understanding how populations are distributed across regions and how they might change in the future.

Step 2: Geospatial Data from VIC Data

All geospatial data, including the location of bus stops and train stops, was sourced from VIC Data, a platform providing open data for Victoria. This geospatial data was crucial in analyzing transport infrastructure within each LGA. I converted these geospatial files into CSV format, making it easier to integrate them into my database for further analysis.

Step 3: Combining Geospatial Data with VISTA Survey

I incorporated insights from the Victorian Integrated Survey of Travel and Activity (VISTA), which provided valuable information about travel behavior across Victoria. VISTA allowed me to gather averages and percentages on vehicle and public transport dependency for each LGA. By combining VISTA data with the geospatial data from VIC, I was able to assess both the infrastructure and the actual usage of public transport and private vehicles in each region.

Step 4: LGA Conversion

Using latitude and longitude data, I mapped the bus stops, train stops, and vehicle registrations to their respective LGAs. This process ensured that the analysis was localized, grouping all relevant data for each LGA.

Step 5: Data Integration

In addition to geospatial and VISTA data, several other datasets were integrated into the analysis:

Vehicle Registrations: Data on vehicle ownership within each LGA.
Annual Patronage of Train Services: Information on how many people use train services annually.
Bus and Train Stop Density: Public transport infrastructure within each area.

For some data I chose to use the API while for other data that required further analysis I saved them against the DB to avoid multiple API calls.

Major Pain point was data not available in the same geo format: some data had long and lat given but some had postcodes and other with LGAs. Therefore standardise of data was the majority part of the project. Utilised Open Source APIs to convert Geo values to LGAs. (https://geo.abs.gov.au/arcgis/rest/services/ASGS2021/LGA....)
Used this site from ABS to convert the data to LGAs where required.

Step 6: AI-Assisted Scoring Function

Instead of manually building an AI model, I provided the available datasets and sustainability metrics to an AI tool and asked it to help generate an artificial scoring function for each LGA. This scoring function takes into account:

The ratio of public transport users to total population (from VISTA data).
The density of public transport infrastructure.
Predicted population growth and its implications on future transport needs.
By using AI to assist in formulating the scoring logic, I was able to derive a Sustainable Transport Score for each LGA. These scores enable policymakers to identify which LGAs are leading in sustainable transport and which require more investment to reduce private vehicle dependency.