Timezone: »
The Moon is an archive for the history of the Solar System, as it has recorded and preserved physical events that have occurred over billions of years. NASA's Lunar Reconnaissance Orbiter (LRO) has been studying the lunar surface for more than 13 years, and its datasets contain valuable information about the evolution of the Moon. However, the vast amount of data collected by LRO makes the extraction of scientific insights very challenging - in the past, the majority of analyses relied on human review. Here, we present NEPHTHYS, an automated solution for discovering thermophysical changes on the surface using one of LRO's largest datasets: the thermal data collected by its Diviner instrument. Specifically, NEPHTHYS is able to perform systematic, efficient, and large-scale change detection of present-day impact craters on the surface. With further work, it could enable more comprehensive studies of lunar surface impact flux rates and surface evolution rates, providing critical new information for future missions.
Author Information
Jose Delgado-Centeno (University of Luxembourg)
Silvia Bucci (Politecnico di Torino)
She is a Ph.D. student at Polytechnic University of Turin (Italy). She received her master degree in Artificial Intelligence and Robotics from Sapienza University of Rome in 2018. During the Ph.D. she has been a member of the Visual and Multimodal Applied Learning of the Italian Institute of Technology. Her research interest lies in the field of Machine Learning, Deep Learning, and Computer Vision applied to robotic systems. In particular, she focuses on the development of Domain Adaptation, Domain Generalization and Anomaly Detection algorithms for Object Recognition.
Ziyi Liang (University of Southern California)
Ben Gaffinet (RSS-Hydro)
**Ben Gaffinet** is an applied physicist and holds a Master degree from École Polytechnique Fédérale de Lausanne. In his early career he worked in the field of plasma physics, more specifically electrical discharges. During his two years at the European Space Agency he applied this knowledge to make spaceborne instruments safe from said harmful discharges and took his first steps towards downstream Earth Observation Applications. Since 2020 he is working for RSS-Hydro on Machine Learning applications that exploit freely available satellite data, which includes FloodSENS. In Summer 2022 he participated in the FDL USA program. The work revolved around exploiting the thermal data of the Lunar Reconnaissance Orbiter to perform change detection on the Moon.
Valentin T. Bickel (ETH Zurich)
Ben Moseley (University of Oxford)
Miguel Olivares (Universidad de Luxemburgo)
More from the Same Authors
-
2021 : Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images »
Jose Delgado-Centeno · Paula Harder · Ben Moseley · Valentin Bickel · Siddha Ganju · Miguel Olivares · Alfredo Kalaitzis -
2021 : Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images »
Jose Delgado-Centeno · Paula Harder · Ben Moseley · Valentin Bickel · Siddha Ganju · Miguel Olivares · Freddie Kalaitzis -
2021 : Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images »
Jose Delgado-Centeno · Paula Harder · Ben Moseley · Valentin Bickel · Siddha Ganju · Miguel Olivares · Alfredo Kalaitzis -
2021 : Scaling physics-informed neural networks to large domains by using domain decomposition »
Ben Moseley · Andrew Markham