AUTHOR=Mall Urs , Kloskowski Daniel , Laserstein Philip 

TITLE=Artificial intelligence in remote sensing geomorphology—a critical study

JOURNAL=Frontiers in Astronomy and Space Sciences

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/astronomy-and-space-sciences/articles/10.3389/fspas.2023.1176325

DOI=10.3389/fspas.2023.1176325

ISSN=2296-987X

ABSTRACT=Planetary geomorphological maps over a wide range of spatial and temporal scales provide important information on landforms and their evolution. The process of producing a geomorphological map is extremely time-consuming and maps are often difficult to reproduce. The success of deep-learning and machine-learning promises to drastically reduce the cost of producing these maps and also to increase their reproducibility. However, deep-learning methods strongly rely on having sufficient ground truth data to be able to recognize the wanted surface features. In this paper, we investigate the results from artificial intelligence (AI) based work-flow to recognize lunar boulders on images taken from a lunar orbiter to produce a global lunar map showing all boulders which left a track in the lunar regolith. We compare the findings from the AI study with the results found by a human analyst (HA) when handed the identical data base of images to identify boulders with track on the images. The comparison involved 181 lunar craters from all over the lunar surface. Our results show that the used AI workflow grossly underestimates the number of identified boulders on the used images. The AI approach found less than a fifth of all boulders identified by a HA. The purpose of this work is not to quantify the absolute sensitivities of the two approaches but to identify causes and origin for the differences which the two approaches deliver, and to make recommendations as to how the machine-learning approach under the given constraints can be improved. Our research makes the case that despite the increasing ease with which deep-learning methods can be applied to existing data sets, a more thorough and critical assessment of the AI results is needed to ensure that future network architectures can produce the reliable geomorphological maps which these methods are capable of delivering.