IgniSense

Inspiration:

Wildfires have become more frequent and devastating, especially in North America. Existing detection methods, like aerial drones, often identify fires too late. The need to preserve our ecosystem and environment inspired us to create a proactive solution using soil-based smart sensors.

What it does:

Our solution involves ML-powered soil sensors that monitor soil moisture, temperature, CO₂ levels, and particulate matter to predict wildfire risks before ignition. It sends alerts to fire departments and environmental agencies for early intervention.

How we built it

Challenges we ran into:

We faced challenges in integrating multiple sensors into a single system, ensuring reliable real-time data transmission, and optimizing power consumption with solar panels. Budget constraints and assembling the device are also a challenge.

Accomplishments that we're proud of:

We successfully developed a working prototype with real-time wildfire risk prediction using MLP (Multi-Layer Perceptron) models.

What we learned:

We gained hands-on experience in buisness devolepment. Furthermore, we had to chance to implement our knowledge in machine learning for predictive analysis and sustainable hardware development. Additionally, we learned how to optimize wildfire detection while maintaining affordability.

What's next for IgniSense:

Our next steps involve refining our prototype, conducting real-world testing in wildfire-prone areas, and seeking partnerships with environmental agencies to deploy the system at scale.

Built With

• mlp
• processors
• sensors
• solarpanels