Answers are grounded in this paper and cite their sources.
Situational awareness during a catastrophic natural disaster, such as a flood, wildfire, tsunami or earthquake is often described by disaster responders as an information ‘fog’ as once trusted systems break down and confusion and panic rise during rapidly changing circumstances. Indeed in many catastrophic events, severe loss of life happens in the days after the event itself. Satellites have already played a key role in disasters, however the advent of on-board intelligence, paired with terrestrial digital twins on the ground opens up a phase-change in the efficacy of space data to support both disaster resilience and response - which we have been calling ‘live twinning’. Over the past three years, Trillium with support from Frontier Development Lab and commercial partners has been running numerous experiments in onboard machine learning with flight-proven examples of machine learning (software) payloads showing the potential of novel observation approaches - particularly in the realm of providing greater insight during catastrophic events. In parallel, we have been experimenting with surrogate models of complex terrestrial phenomena. Live-twinning applies onboard ML and Earth system models to improve insights for rapid responses during natural catastrophes.
No takes yet. Share an insight, caveat, or question.
Parr et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: