In-Orbit Demonstration of Artificial Intelligence applied to hyperspectral and thermal sensing from space

cosine Remote Sensing is leading the first ever demonstration of on-board Artificial Intelligence (AI) applied to the combination of hyperspectral and thermal imaging. The sensing device is a miniaturized reflective optical instrument equipped with unprecedented processing capabilities. The European Space Agency (ESA) has contracted cosine Remote Sensing to highly integrate Thermal Infrared (TIR) technologies into a miniaturized Visible-Near-InfraRed (VNIR) hyperspectral imager and to fit the combined spectral channels in a volume of less than two litres. The imager is named HyperScout-2 as it will use the HyperScout-1 platform, that has flight heritage, as building block to further integrate spectral channels. HyperScout-2 is equipped with a hybrid processing platform composed of a CPU, GPU and VPU. The VPU is a state of art vision processing unit developed by Intel and is for the first time flew in space as part of HyperScout-2. HyperScout-2 will enable experimental programs to investigate the use of Artificial Intelligence for a variety of applications in the field of object detection and data inference. The first application that will be run on is cloud screening. HyperScout-2 will be used as in-orbit test-bed to benchmark the performance of such a miniaturized class of systems as well as to perform hands-on investigations to forecast the benefits of combining frequent coregistrated measurements in the VNIR and TIR from nanosatellites, with less frequent but very accurate measurements performed by institutional satellites such as the Copernicus fleet. This initiative is named PhiSat-1 and is part of the ESA EOP initiative to leverage small satellites to foster technology breakthrough developments. This contribution reports on a general description of HyperScout-2 as well as about the fast track program in which is implemented. We will also highlight the way the space asset will be exploited especially regarding the understanding of the potential of small systems deployed within small satellites constellation if integrated into ecosystems made of small and large systems. The PhiSat-1 is implemented as an enhancement of the FSSCat mission in a 6U cubesat based on Tyvak International platform integrating cosine Remote Sensing hyperspectral/thermal system. The cloud screening application is led by cosine Remote Sensing and supported by Sinergise, Ubotica and University of Pisa.