Training AI models to deliver better human outcomes
For an outcome create two AI models based on contrasting incentive systems and examine the differing impacts on the defined outcome.
Go to Challenge | 12 teams have entered this challenge.
SmartMaps
Project Info
Team Name
BeFrank
Team Members
Aqeel and 3 other members with unpublished profiles.
Project Description
Our solution comes in two parts: a React frontend application for displaying map visualisations, and a backend Python API service for data retrieval and developers.
Given a mode of transport, our app provides you with human centric data about possible routes between your location and another. In particular, it measures the urban heat and greenery coverage and provides a selection of the best routes. Empowering you to make informed pathing decisions.
The datasets Urban Heat & Green Cover dataset(s) from the SEED portal provide heat deviation and amount of green cover. Combining this georeferenced data with Google Maps APIs, we integrated routing information to quantify the amount of heat deviation and vegetation cover that can be experienced along a route.
Displaying the metrics for a route and also providing a rich visualisation and interactive display options for the data can help provide members of the public with a better understanding and options of possible routes.
Since our solution makes it very easy for integration with other arbitrary datasets with geographic position information, other open datasets — such as the Canberra’s street light location dataset — can be included to provide further options for route customisation. For example, this data could be used for determining a well lit route for commuting safety at night.
The API enables quick and easy querying of the joined Government and Maps datasets. Further, the queries made by users can be anonymised and stored by the backend. This provides a live feed of locations in the city that are in need of attention.
Data Story
To provide routing information, we used the Google Maps API to first geocode the user specified origin and destination locations into geographic coordinates which we could then integrate with the Graphhopper service to provide possible routes. This allows us to still optimise for distance and duration, while taking heat and green cover as additional heuristics.
To retrieve data for the expected temperature deviation and green cover, we integrated with the ArcGIS MapServer REST API. Using a list of geographic coordinates along the route, we query the GIS dataset to retrieve temperature and green cover data. In particular, we used the following fields:
- Mean Urban Heat Index temperature deviation from vegetated areas
- Percentage of green cover on a block area
- Ratio of green cover to block area
in addition to geographical data about the area the data applies to.
Once we have retrieved the data, this is aggregated for each route alternative, and metrics such as the average is calculated.
Team DataSets
NSW Urban Vegetation Cover to Modified Mesh Block 2016
Description of Use Uesd as a metric for green cover.
NSW Urban Heat Island to Modified Mesh Block 2016
Description of Use Extracted from REST API on demand. Used as a metric for heat.
Challenge Entries
🌟 What's the coolest way to travel across the city?
Using datasets which map urban heat and green cover across Greater Sydney, we challenge you to develop a tool which visualises green routes through the city. Help people avoid urban heat and move across the city in comfort by mapping out green streets and pathways which connect shopping centres, public transport stops and public spaces.
Go to Challenge | 18 teams have entered this challenge.
🌟 Canberra 2029 – Inclusive; Progressive; Connected
How do we use data from the past to predict a better future for Canberra? How do we best support the diversity of our community? Optimise the way we travel and transport goods throughout our city? Predict the jobs of the future – and the skills needed for them? Connect our citizens with their environment?
Go to Challenge | 21 teams have entered this challenge.
🌟 The three C’s of innovation – combination, collaboration, and chance.
How can we combine and use environmental data to gain new insights into New South Wales and tell a story of our diverse landscape?
Go to Challenge | 14 teams have entered this challenge.
🌟 Pedestrian and Air Quality Sensor Data
How might we improve users’ experience of their city by using data from pedestrian and vehicle counters and/or air quality sensors?
Go to Challenge | 15 teams have entered this challenge.