The seismic wavefield carries the imprint of material it crossed. We now understand that seismic wavefields alter the material when they pass through it and that these changes are measurable. This is important, because the dynamic response of Earth’s material directly affects our societies: geomaterial alterations are associated with many natural hazards, such as volcanic eruptions, landslides, earthquakes, and the structural health of civil structures such as bridges and buildings. Traditional seismic sensors - global and regional networks of seismometers - provide us with high temporal resolution, but sparse spatial resolution. Right now, new sensing technologies (fiber-optic cables (DAS), large-N arrays, rotation sensors) are emerging that can give us much more detailed spatial information about how the seismic wavefield behaves. This means that we can study changes in local material properties, and investigate complex behavior of materials as they deform under small strain. These sensing technologies are reaching a level of maturity where they can be incorporated into common seismological observation practice. For this new era of seismological instrumentation and observation fundamentally new skills need to be developed. In SPIN, we will train the next generation of scientists to develop novel views about the dynamic behaviour of Earth materials, and in particular how to observe them with the revolutionary new sensing systems at hand. It is currently enigmatic how to combine these sensor types to optimize resolution power. This research and training will impact the way we understand solid Earth processes, how we interrogate the Earth’s geomechanical behavior, and the way we forecast natural hazards.

The Sun is an enigmatic star that produces the most powerful explosive events in our solar system - solar flares and coronal mass ejections. Studying these phenomena can provide a unique opportunity to develop a deeper understanding of fundamental processes on the Sun, and critically, to better forecast space weather. The Active Region Classification and Flare Forecasting (ARCAFF) project will develop a beyond state-of-the-art flare forecasting system utilising end-to-end deep learning (DL) models to significantly improve upon traditional flare forecasting capabilities. ARCAFF will increase the accuracy and timeliness of current operational flare forecast products and create new time series flare forecasts. Furthermore, ARCAFF forecasts will include forecast uncertainties, another major improvement over current systems. The large amount of available space-based solar observations are an ideal candidate for this type of analysis, given DL effectiveness in modelling complex relationships. DL has already been successfully developed and deployed in weather forecasting, financial services, and health care domains, but has not been fully exploited in the solar physics domain. Solar flare forecasts from ARCAFF will be benchmarked against current systems using international community standards, and will demonstrate ARCAFF’s superior forecasting capabilities. The datasets, codes and DNNS developed for ARCAFF will be made openly available to support further research efforts and encourage their re-use. ARCAFF is relevant to the work program as it will exploit currently available data space weather data to train DL models to improve forecast accuracy. DL itself is an innovation enabling technology and analysis of the DL models will improve scientific understanding of solar flares. Through the creation of new forecast products it will develop and mature new concepts for both scientific and monitoring purposes, following the best-practices of meteorological services.