Unitywater - Collaborative Intelligence for Clean Waters
Description of Use
Tailoring Responses with Unity Water Data
Our project at GovHack 2024 involved utilizing Unity Water's extensive datasets to deliver highly specific responses to community inquiries about environmental data. By tapping into diverse datasets such as mid-field monitoring data and estuarine marine data, we created a sophisticated AI-driven platform that could analyze and provide insights into environmental changes and trends.
**The Challenge:**
The main challenge was to integrate and process varied datasets to respond accurately to specific questions regarding environmental health and changes, such as water quality fluctuations in specific rivers or estuarine systems over a set period.
**Our Approach:**
We developed a system that could parse natural language questions and match them to the relevant datasets, extracting and analyzing the required information to provide precise answers. For instance, when prompted with the question about the water quality changes in the North Pine River between July 2018 and July 2023, the AI would:
1. **Identify the Relevant Dataset:** Based on the keywords in the question, such as "water quality" and "North Pine river," the AI determined that `unity_water_mid-field_monitoring_data` was the most appropriate dataset to use.
2. **Filter and Analyze the Data:** The AI used specific fields from the dataset that related to water quality indicators, such as Dissolved Oxygen, pH, E. coli, Chlorophyll a, and Total Phosphorus as P. It filtered the data to include only those entries from July 2018 to July 2023.
**Implementation Example:**
Here's a Python code snippet that demonstrates how the AI would filter the dataset to retrieve and analyze the required information:
**Outcome:**
Our system provided a detailed overview of how water quality parameters have changed over time at specific locations, aiding in environmental monitoring and community awareness. This tailored approach not only increased engagement but also encouraged data-driven community actions towards environmental stewardship.
### Conclusion
Through the integration of context-aware AI and detailed environmental datasets, we successfully created a tool that offers precise and relevant responses to community inquiries, thereby enhancing the relationship between data science and community service. This project stands as a testament to the potential of AI in fostering a more informed and proactive community.
Data Set