Nebula Public Library

The “SaaSy ML” idea will provide experimenters with on-board Machine Learning (ML) functionalities that any app can subscribe to via a Software as a Service (SaaS) app hosted on the Satellite Experimental Processing Platform (SEPP). The ML features provided by the SaaS app will cover both training and prediction operations. The JSAT open-source java library for ML will be re-used thus making accessible over 100 training algorithms on-board a flying mission. Re-using the JSAT library will ensure the development to focus on the idea's novel aspect: a spacecraft SaaS app for in-orbit ML.

‘STARCOP’ is an initiative to use ML and multiple satellites of diverse detection capabilities to quickly detect methane leaks onboard and notify them in near-real-time. In this project we have developed ML models for automatic detection of methane in hyperspectral and multispectral imagery. Our hyperspectral model (HyperSTARCOP) is able to capture more than 90% of plumes in our test data while reducing the false positive rate by 39% when compared to state-of-the-art models.

The MBSE and Space to Ground ICD activity started with the goal of applying MBSE practices to the preparation of the Space to Ground ICD (S2GICD). This study involves the following main steps:

The main purpose of this project, as mentioned in the SoW, was to analyse historical mission data and search for new features which would be useful in the telemetry checking, command verification and procedure writing process in the future.
Features of a signal (or parameter in this context) are defined as characteristics that can be measured or calculated over a given time window (such as mean, standard deviation or minimum of a signal).