# Unlocking the Use of Raw Multispectral Earth Observation Imagery for Onboard Artificial Intelligence

arXiv: https://arxiv.org/abs/2305.11891 · HTML: https://mlsanity.com/paper/2305.11891/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 53 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 6 of 6)

- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery](https://mlsanity.com/paper/2106.15281/) (2021)
- [Automatic Dataset Builder for Machine Learning Applications to Satellite Imagery](https://mlsanity.com/paper/2008.01578/) (2020)

## Built on by (most cited first, 14 of 14)

- [HyperspectralViTs: General Hyperspectral Models for On-board Remote Sensing](https://mlsanity.com/paper/2410.17248/) (2024)
- [Lossy Neural Compression for Geospatial Analytics: A Review](https://mlsanity.com/paper/2503.01505/) (2025)
- [Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis](https://mlsanity.com/paper/2411.03403/) (2024)
- [Explaining raw data complexity to improve satellite onboard processing](https://mlsanity.com/paper/2510.06858/) (2025)
- [Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach](https://mlsanity.com/paper/2604.12807/) (2026)
- [Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search](https://mlsanity.com/paper/2410.05425/) (2024)
- [TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection](https://mlsanity.com/paper/2609.08659/) (2026)
- [Compress-Align-Detect: onboard change detection from unregistered images](https://mlsanity.com/paper/2507.15578/) (2025)
- [Towards Methane Detection Onboard Satellites](https://mlsanity.com/paper/2509.00626/) (2025)
- [Thermal Anomaly Detection using Physics Aware Neuromorphic Networks: Comparison between Raw and L1C Sentinel-2 Data](https://mlsanity.com/paper/2604.18606/) (2026)
- [ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink](https://mlsanity.com/paper/2608.06942/) (2026)
- [Methane Detection On Board Satellites from Unorthorectified Imagery](https://mlsanity.com/paper/2609.04906/) (2026)
- [RSPDBench: Benchmarking Vision Foundation Models on Earth Observation Tasks Under Physically Grounded Remote-Sensing Product Degradations](https://mlsanity.com/paper/2609.23427/) (2026)
- [Raw Imagery Impacting Your AI: Should You Care?](https://mlsanity.com/paper/2609.38265/) (2026)

## Abstract (arXiv)

Nowadays, there is growing interest in applying Artificial Intelligence (AI) on board Earth Observation (EO) satellites for time-critical applications, such as natural disaster response. However, the unavailability of raw satellite data currently hinders research on lightweight pre-processing techniques and limits the exploration of end-to-end pipelines, which could offer more efficient and accurate extraction of insights directly from the source data. To fill this gap, this work presents a novel methodology to automate the creation of datasets for the detection of target events (e.g., warm thermal hotspots) or objects (e.g., vessels) from Sentinel-2 raw data and other multispectral EO pushbroom raw imagery. The presented approach first processes the raw data by applying a pipeline consisting of spatial band registration and georeferencing of the raw data pixels. Then, it detects the target events by leveraging event-specific state-of-the-art algorithms on the Level-1C products, which are mosaicked and cropped on the georeferenced correspondent raw granule area. The detected events are finally re-projected back onto the corresponding raw images. We apply the proposed methodology to realize THRawS (Thermal Hotspots in Raw Sentinel-2 data), the first dataset of Sentinel-2 raw data containing warm thermal hotspots. THRawS includes 1090 samples containing wildfires, volcanic eruptions, and 33,335 event-free acquisitions to enable thermal hotspot detection and general classification applications. This dataset and associated toolkits provide the community with both an immediately useful resource as well as a framework and methodology acting as a template for future additions. With this work, we hope to pave the way for research on energy-efficient pre-processing algorithms and AI-based end-to-end processing systems on board EO satellites.