Satellite Evidence in the Courtroom
Satellite imagery can show when a crime leaves a mark on the landscape – a village destroyed, a lake drained, a forest cleared. However, whether a court will accept satellite evidence remains an open question. The 'Earth Observation for Human Rights and Legal Accountability Mechanisms' project, co-funded by the Discovery element of ESA's Basic Activities and the Centre for Sustainable Development at the University of Strathclyde, examined how Earth observation data can be systematically analysed and presented to meet the evidentiary standards required in legal proceedings.
Forensic science has always had to earn its place in the courtroom. Fingerprints, DNA analysis, and digital forensics each had to establish standards, survive challenges, and build credibility with judges and juries before becoming accepted tools of justice. Satellite imagery is going through that same process now – and AI-processed satellite imagery represents the next frontier, with no established legal precedents and significant practical challenges still to overcome.
The first stage of this research was to understand the current state of the field. Working with UN human rights indicators, doctoral researcher Seonaid Rapach conducted a systematic review that assessed how satellite imagery has already been used in human rights investigations and legal proceedings. The results, published in the journal Science and Justice, revealed that of 547 UN human rights sub-indicators, 50 can be monitored using satellite imagery to some extent – across areas as varied as the right to adequate housing, the right to water, the right to life, and the right to freedom of peaceful assembly – a finding that clarifies both the potential and the limits of the technology in this context.
The review also identified three analytical approaches that have been used to present satellite imagery as court evidence: multi-temporal change detection, which compares before-and-after images of an event; multispectral analysis, which uses different wavelengths of light to detect specific activity on the ground; and cross-referencing with non-imagery data such as eyewitness accounts or ground surveys. Of these, the most common approach has been the simplest – visual inspection of before-and-after images – which, while useful, falls well short of what modern satellite analysis can deliver.
The second strand of the research examined what satellite evidence needs to look like at each stage of the criminal justice process, from initial data collection through to courtroom presentation. This 'crime scene to courtroom' framework identified the analytical processing stage as the critical weak link: the methods currently used in legal investigations lag far behind both the capabilities of the technology and the analytical standards applied in other fields.
Working with Police Scotland, the team developed a practical application of this framework, using satellite thermal imagery to help identify potential sites of interest for investigation. The tool is designed not as courtroom evidence in itself, but as a way of helping investigators prioritise and focus their work before a case ever reaches the courtroom.
The framework also provided the foundation for a series of practical case studies, each of which highlighted the same underlying challenge: producing analytical outputs that are not just scientifically sound, but robust enough to withstand legal scrutiny.
"We want legal practitioners to feel empowered to use new technologies, such as advanced satellite data analysis, because excluding them can risk key evidence being overlooked," says project lead Seonaid Rapach. "However, if such evidence is considered without proper scrutiny, errors or false classifications can weaken the evidence or lead to wrongful convictions, undermining fairness and trust in the legal system."
The most technically novel element of the project addressed a challenge that courts have not yet had to grapple with directly: what happens when the evidence has been processed by an artificial intelligence? Machine learning and deep learning are powerful tools for analysing satellite imagery, but they introduce the possibility of misclassification – and a misclassification in a legal context could mean inadmissible evidence, or worse, a wrongful conviction.
The team's solution borrowed a concept from legal practice. ‘Hot-tubbing' is a process used in some court systems in which two expert witnesses are required to set out, jointly, what they agree on and what they disagree on – a structured way of handling scientific evidence that is genuinely disputed. Rapach and her colleagues applied the same logic to their AI model, running it in two configurations: one steered to be cautious about false positives, as a prosecution model might need to be, and one steered to be cautious about false negatives, as a defence model might require. By comparing the outputs of the two, it becomes possible to identify which classifications both models agree on – and those are the classifications that carry the greatest evidential weight. Areas of disagreement are flagged explicitly, allowing legal practitioners to focus further scrutiny where it is needed.
"Errors in AI-analysis evidence can lead to different predictions of the same evidence," says Rapach. "The hot-tubbing approach, inspired by established legal practice, directly addresses this by steering the model to its extremes and establishes consensus in these extremes. This not only makes it easier for the court to identify where experts could agree and disagree, but also strengthens the reliability, and ultimately legal weight, of agreed conclusions."
The project originated as an idea submitted through ESA's Open Space Innovation Platform, seeking out promising new concepts for space research, and was funded as a co-sponsored research project by the Discovery element of ESA's Basic Activities. As well as supporting the research directly, ESA enabled Rapach to present her work at a range of international events, including the International Astronautical Congress, the Living Planet Symposium, and ESA's own Environmental Crimes Workshop, and to contribute to training courses on the use of satellite data in security and legal contexts.
"Supporting PhD researchers and academic teams across Europe is central to what Discovery is for," says Moritz Fontaine, Discovery & Preparation Officer and ESA's technical lead for the activity. "Projects like this one show why that matters: it takes a researcher willing to work across remote sensing, law, and human rights to make real progress on questions that no single discipline can answer alone, and strengthening those competences across European universities is how the wider space sector grows."
The work has produced a published framework, a set of practical tools, and – perhaps most valuably – a clearer picture of what still needs to be done before satellite imagery, and AI-processed satellite imagery in particular, can take its place alongside DNA and digital forensics as a trusted and standardised form of evidence in courts around the world.
Related publications:
Rapach, S. and Riccardi, A. (2023) 'A framework for mapping Earth observation capabilities to the OHCHR indicators', International Astronautical Congress 2023 (IAC), 14th–18th October 2023, Baku, Azerbaijan.
Rapach, S., Riccardi, A. and Wheate, R. (2024) 'Earth observation technology's alignment with OHCHR indicators for strengthening human rights breach investigations and adjudication', Science and Justice, 64(6), pp. 710–727.
Rapach, S., Riccardi, A., Wheate, R., Nemeth, V. and Samuel, E. (2024) 'Navigating legal challenges in Earth observation: a case study of Lake Ziway', IEEE International Humanitarian Technologies Conference 2024, 27th–30th November 2024, Bari, Italy.
Rapach, S., Riccardi, A. and Wheate, R. (2025) 'Integrating AI in legal analysis of satellite imagery: a focused approach using transformer models to guide classification', Living Planet Symposium 2025, 23rd–27th November 2025, Vienna, Austria.
Rapach, S., Wheate, R. and Riccardi, A. (2025) 'Crime scene to courtroom: evaluating EO as forensic evidence in criminal justice', International Astronautical Congress 2025, 29th September–3rd October 2025, Sydney, Australia.
Vielen Dank, dass Sie den Artikel gelesen haben! Beobachten Sie uns unter Google Nachrichten.
