kaizenics

SeaSense
Back to works

Project Case Study

SeaSense

SeaSense helps anglers find productive fishing spots using sea-surface temperature, sensor data, and ML-based fish classification.

React NativeTailwind CSSFirebaseQGISTensorFlowArduino

Overview

SeaSense is a mobile experience for discovering fishing spots, checking local conditions, and understanding fish behavior. It combines environmental data with on-site temperature sensing to guide anglers toward higher-probability locations.

The Problem

Fishing decisions are often based on guesswork. Without reliable surface temperature data and species signals, anglers waste time exploring low-probability areas and miss short windows of activity.

The Solution

SeaSense unifies satellite sea-surface temperature (SST), on-site temperature sensor readings, and a machine-learning model to predict likely fish presence. The app surfaces the best spots and explains why they are promising.

How It Works

  1. Collect temperature data SST data provides a broad signal, while a temperature sensor captures local conditions on the water.
  2. Run the SNN model A spiking neural network (SNN) evaluates temperature patterns to classify likely fish presence.
  3. Visualize the result The app highlights recommended zones and provides context for forecasts and behavior trends.

Outcome

SeaSense replaces intuition-first decisions with data-backed guidance, helping anglers spend more time in productive areas and less time searching.

Technical Stack

  • React Native for the mobile experience
  • Firebase for data services and storage
  • QGIS for geospatial analysis
  • TensorFlow for model development
  • Arduino-based temperature sensor integration