PulseSatellite: A tool using human-AI feedback loops for satellite image analysis in humanitarian contexts
This addresses the need for timely and accurate satellite image analysis in humanitarian contexts, such as disaster and conflict response, though it appears incremental as it builds on existing neural network methods.
The authors tackled the problem of satellite image analysis for humanitarian response by developing PulseSatellite, a tool that uses human-AI feedback loops to retrain neural networks on-the-fly, achieving improved accuracy in mapping shelters and floods in case studies.
Humanitarian response to natural disasters and conflicts can be assisted by satellite image analysis. In a humanitarian context, very specific satellite image analysis tasks must be done accurately and in a timely manner to provide operational support. We present PulseSatellite, a collaborative satellite image analysis tool which leverages neural network models that can be retrained on-the fly and adapted to specific humanitarian contexts and geographies. We present two case studies, in mapping shelters and floods respectively, that illustrate the capabilities of PulseSatellite.