veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection System
This work addresses safety-critical verification for real-world wildfire detection systems, but it is incremental as it describes ongoing efforts to apply academic tools to industrial contexts.
The paper tackles the problem of verifying the reliability of a deep learning-based wildfire detection system, focusing on verifying its consistency in correctly classifying inputs as wildfire intensity increases, as part of an industry-academia collaboration.
In this short paper, we present our ongoing work on the veriFIRE project -- a collaboration between industry and academia, aimed at using verification for increasing the reliability of a real-world, safety-critical system. The system we target is an airborne platform for wildfire detection, which incorporates two deep neural networks. We describe the system and its properties of interest, and discuss our attempts to verify the system's consistency, i.e., its ability to continue and correctly classify a given input, even if the wildfire it describes increases in intensity. We regard this work as a step towards the incorporation of academic-oriented verification tools into real-world systems of interest.