Back to Projects

Team Name:

Alternative Engineers


Team Members:


Evidence of Work

* Flow-Sense AI *

Project Info

Alternative Engineers thumbnail

Team Name


Alternative Engineers


Team Members


Logan , David Khoury , Samuel Kropp , Hayden

Project Description


Flow-Sense AI

Introduction

Historically, managing water quality data has been a slow and inefficient process, relying heavily on manual input and delayed responses. Flow-Sense AI is set to revolutionize this by leveraging cutting-edge artificial intelligence to automate data management, analysis, and reporting. This innovative tool dramatically speeds up the process, enabling real-time monitoring and predictive insights that were previously unattainable. By integrating AI into water quality management, Flow-Sense AI not only improves accuracy but also empowers decision-makers to act quickly and efficiently, making it a game-changer for environmental governance and sustainability.

What is Flow-Sense AI?

Flow-Sense AI is an intelligent data management system that given raw data water quality inputs, the AI analyses the data to produce standardized scores that are related to optimal quality control levels. The standardized scores for water quality measures are further cumulated into an executive 'quality score', a single value that summarizes water quality in various sensor locations.

The Application:

Flow-Sense AI will be integrated into an application that visualizes water quality along the Pine River through a color-coded heat map. Each sensor location is linked to a quality score, which is represented by colors on the map, making it easy to see how water quality changes along the river. Users can click on any section of the river to view detailed information from the nearest sensor, including individual parameters like pH and ammonia, which are color-coded based on their proximity to optimal levels. The AI can detect significant changes in water quality and trigger alerts, pinpointing the affected location on the map. By analyzing current data against historical trends, the system can recommend control measures to help achieve consistent optimal water quality.

How will the application improve water quality management?

The streamlined process of sorting, analyzing, and visually presenting water Quality will result in several benefits including:
-Real-time monitoring - since data can be taken and analyzed without human intervention, data
from sensors can be obtained in real time.

-Trend Identification - The user of the application can see real-time data along with
historical data to identify trends and patterns in water quality parameters. Predictive
extrapolation through the use of AI can also be used to predict future quality levels.

-Early detection of contaminants and dumping - Greater governance ability

- The option to easily expand the AI to other bodies of water through the implementation
of more sensors and location-specific objective quality parameters.


#ai #data integration #water quality monitoring #environmental governance #unity water #machine learning #data management #river health #water sensors #environmental sustainability #real-time data #catchment management #ai solutions #data analytics #pine rivers catchment #ecological data #community engagement #environmental protection #water governance #gis mapping #cumulative scores #water quality scoring #sensor networks #ai-driven decision making #environmental ai applications #river monitoring

Data Story


Flow-Sense Data Story

Defining the problem

In the context of water governance, several challenges were identified that impacted data integration, reporting, and community collaboration. Specifically, water quality data analysis faced key issues, including inconsistent data readings (often with weeks between them), unorganized data, and a lack of comprehensive parameters to assess overall water quality effectively. These gaps made it difficult for stakeholders to monitor trends, make timely decisions, and take corrective actions when necessary.

Generating a solution - Cumulative Scores for decision making

To address these problems, we developed the "Flow-Sense AI" application. Flow-Sense AI can analyze real-time water quality data and generate standardized scores for key parameters by comparing them to objective values specific to the Pine River. This solution aggregates various water quality measures into cumulative scores, offering a clear and comprehensive view of the river's health, which simplifies decision-making for environmental managers.

Visualising Data with GIS Integration

To make the data even more intuitive, we integrated the sensor data into a Geographic Information System (GIS). This allows users to visualize water quality across specific locations along the river through a color-coded heat map. The map highlights overall quality levels, with more detailed information—such as pH, ammonia concentration, and other technical measures—accessible by clicking on specific points along the river. This integration improves trend identification and pattern recognition, empowering stakeholders to respond quickly and make data-driven decisions.


Evidence of Work

Video

Homepage

Project Image

Team DataSets

Ecosystem Health Monitoring Program - Estuarine Marine Water Quality data

Description of Use Was sorted and arranged into a system where key quality parameters were sorted. A standardized score was assigned to each sensor recording representing overall water quality

Data Set

Pine River and Redcliffe Creeks Environmental Values and Water Quality Objectives

Description of Use Was used as a control reference for developing standardized data based on deviation from optimal values.

Data Set

Unitywater - Mid-Field Monitoring program

Data Set

Challenge Entries

Collaborative Intelligence for Clean Waters

How might AI enhance environmental governance in the Pine Rivers catchment through improved data management, integration, and reporting? How might we integrate diverse datasets and identify trends to improve decision-making and foster collaboration to support community and environmental wellbeing?

Go to Challenge | 9 teams have entered this challenge.

Moreton Bay Greening as We Grow (QLD)

How might we harness the power of the everyday citizen to help protect our diverse flora and fauna as we grow our region, creating a diverse and flourishing planet for generations to come?

#Living better together

Eligibility: Open to everyone, preference will be given to those providing solutions using at least one local Moreton Bay region (City of Moreton Bay) data set. . Employees of City of Moreton Bay with a direct working relationship with members of the local Moreton Bay Gov Hack node organising committee are ineligible to apply for this prize. If unsure, please feel welcome to check and discuss via Slack channels upon commencement of the event.

Go to Challenge | 16 teams have entered this challenge.