Team Name

Lonely Potato

Team Members

Project Description

"GG ez, will make control breezy"

Gamba Grass is considered a high risk weed threatening native vegetation and causing unnecessary work to remove. Gamba grass is best removed by pulling them out from the root and disposing them.

GG ez, is an application developed to solve this issue. The application focuses on a community driven solution. With the help of open datasets in conjunction with machine learning to predict the most vulnerable areas where Gamba grass will be the most rampant.

A user will use the GG ez mobile web application to report any Gamba grass infestations. A user can also use the map functionality to identify areas that need help to eradicate the grass.

Users who choose to treat infested areas by removing them and disposing them at a waste management facility can be rewarded with government incentives based on the weight of gamba grass removed. By combining our applications with government incentives we strongly believe this solution will reduce the amount of Gamba grass in the NT.

The application will also offer forecasts on where Gamba grass will be the most likely rampant. By combining these datasets we can create a machine learning model which will help with these forecasts.

Data Story

Datasets and their roles:

NR Maps

Will show current infestations of Gamba Grass. This data can be fed into our own application map functionality.

Australia - Landscape Health Database 2001 - Weeds

Will provide data of landscape conditions, as Gamba grass is most rampant under certain conditions.

Climate Data Online

Rainfall data will indicate which areas receive the most rainfall therefore indicating which areas will be most vulnerable to a Gamba grass infestation.

Annual Traffic Report 2020

This data set will show the amount of traffic that is coming inbound and outbound within the NT. If there is a high amount of vehicles traveling, it will indicate a higher chance of a vehicle transporting Gamba grass seeds.

NT Weed Records (points)

Will identify what are the most common weeds and their location are.

By utilising these datasets, we can feed them into a machine learning model to predict high risk areas.

We can also process these sources for operational reporting. We can do this by using Microsoft Power Bi to extract, transform and load (ETL) the data and perform analysis using various DAX queries. We can create dashboards and reports to monitor the population of Gamba grass in the NT.