NASA fdl 2019 challenge areas
The FDL yearly cycle starts with challenge definition. Early in the year, we bring together some of the brightest and best minds we can find, from space science, AI and technology, and on/off-Earth applications to explore our challenge areas. During the course of our day-long Big Think events in Europe and the US, we aim to identify some broad challenges, which the FDL research teams could tackle in the summer.
Through a process of iteration with a PI (principal investigator) leading each challenge, we refine and narrow those challenge areas until we have identified one, or several, tightly articulated questions to resolve.
FDL challenges must represent a clear and present scientific problem, for which there is available data, that could be significantly advanced by AI tools and techniques. It is these challenges that the research teams further narrow in the opening weeks of the FDL research sprint to refine their own particular concept approach. The broad challenge areas we start the year with move from provisional to confirmed as we understand how, and when, they meet these criteria. Our challenge areas for 2019 are:
Living with Our Star
How can AI improve our ability to predict solar activity - especially energetic solar phenomena?
EXPANDING THE CAPABILITIES OF NASA’S SOLAR DYNAMICS OBSERVATORY
The Solar Dynamics Observatory (SDO) has greatly expanded our understanding of the Sun, but can we use AI to enhance the value of the SDO even more? By using a prepared “AI-ready” SDO dataset, this challenge aims to transform Helioseismic and Magnetic Imager (HMI) data into extreme ultraviolet (EUV) images. This will help the reduced instrumentation strategy that will be central to the success of future SmallSat missions. Using the same dataset, this challenge will also identify spatial patterns on the Sun to determine the calibration factor that would correct for SDO EUV instrument degradation, which would help to avoid the cost of regular suborbital launches to obtain calibration data.
SUPER-RESOLUTION MAPS OF SOLAR MAGNETIC FIELD COVERING 40 YEARS OF SPACE WEATHER EVENTS
Predicting geoeffective space-weather events is challenged by the time limited coverage of SDO data (2010-present). This challenge proposes to address this problem by using deep learning solutions to upscale lower resolution images from earlier missions, thereby allowing for a second neural net to normalize and combine a much longer temporally composited data product from multiple solar observation missions.
ENHANCES PREDICTABILITY OF GNSS DISTURBANCES
Last year, the Space Weather Team discovered that spatial variations of the ionosphere are unexpectedly significant to predicting GNSS scintillations.
This challenge will build on this work to involve data sources that specifically image these spatial variations (such as all-sky images of aurora and TEC maps) to improve the predictability of GNSS disturbances.
The Moon for Good
How might AI support the goal of establishing a permanent presence on the Moon?
LUNAR RESOURCE MAPPING / SUPER RESOLUTION
How might we use data fusion and emerging super-resolution techniques to develop high-resolution lunar resource maps for the coming era of mission planners looking to locate resources for future robotic and human lunar missions.
Mission Control for Earth
How might we utilise AI and Earth observation data to support improved decision making to protect the planet?
DISASTER PREVENTION, PROGRESS AND RESPONSE
How can AI improve our capabilities to forecast and respond to natural disasters using orbital imagery, coupled with ground observations and social data?
How can AI support medical care in space?
GENERATION OF SIMULATED BIOSENSOR DATA
NASA deep space missions will require advanced medical capabilities, including continuous monitoring of astronaut vital signs to ensure optimal crew health. Can we use biosensor data collected from NASA analog missions to train AI models to simulate various medical conditions that might affect astronauts?
You can read about the FDL Europe 2019 challenges by following this link.