FishFindr

Visualization: The predictions are sent back to the frontend and displayed on an interactive map for easy interpretation.

Challenges we ran into

Understanding and preprocessing raw satellite data was harder than expected.

Learning backend development from scratch while integrating multiple APIs took time.

Figuring out how to properly connect the Granite AI model to our pipeline required digging through documentation.

Accomplishments that we're proud of

Successfully built a working pipeline from satellite/weather APIs to Granite AI and back to a frontend interface.

What we learned

How to build a full-stack application that connects frontend, backend, and AI models. The importance of data preprocessing when dealing with raw scientific datasets. How to quickly adapt and learn backend concepts as frontend developers.

What's next for FishFindr

Improve prediction accuracy by incorporating more diverse datasets (e.g., ocean currents, salinity, seasonal migration data).

Deploy the system on the cloud so fishermen can access it on mobile devices at sea.

Built With

• css
• html
• javascript
• nasagibs
• nasaoceancolorwebapi
• noaa-erddap
• node.js
• react.js