On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery

TL;DR

This paper presents a feasibility study and prototype of onboard satellite AI models using CNNs for rapid volcanic eruption detection from multispectral imagery, aiming for immediate alerts and interventions.

Contribution

It introduces two CNN architectures optimized for onboard satellite deployment to detect volcanic eruptions from multispectral data.

Findings

Effective CNN models for eruption detection are designed and tested.

Models are adaptable to onboard hardware constraints.

The approach enables swift eruption alerts from space-based sensors.

Abstract

In recent years, the growth of Machine Learning (ML) algorithms has raised the number of studies including their applicability in a variety of different scenarios. Among all, one of the hardest ones is the aerospace, due to its peculiar physical requirements. In this context, a feasibility study and a first prototype for an Artificial Intelligence (AI) model to be deployed on board satellites are presented in this work. As a case study, the detection of volcanic eruptions has been investigated as a method to swiftly produce alerts and allow immediate interventions. Two Convolutional Neural Networks (CNNs) have been proposed and designed, showing how to efficiently implement them for identifying the eruptions and at the same time adapting their complexity in order to fit on board requirements.