Journal Article

Deriving Surface Ages on Mars Using Automated Crater Counting

Anderson, S., Benedix, G. K., Lagain, A., Paxman, J., Norman, C., Bland, P. A., Tan, T., Meka, S., Chai, K., Towner, M. C.

2020

Overview

Impact craters on solar system bodies are used to determine the relative ages of surfaces. The smaller the limiting primary crater size, the higher the spatial resolution in surface/resurfacing age dating. A manually counted database (Robbins & Hynek, 2012, https://doi.org/10.1029/2011JE003966) of >384,000 craters on Mars >1 km in diameter exists. But because crater size scales as a power law, the number of impact craters in the size range 10 m to 1 km is in the tens of millions, a number making precise analysis of local variations of age, over an entire surface, impossible to perform by manual counting. To decode this crater size population at a planetary scale, we developed an automated Crater Detection Algorithm based on the You Only Look Once v3 object detection system. The algorithm was trained by annotating images of the controlled Thermal Emission Imaging System daytime infrared data set. This training data set contains 7,048 craters that the algorithm used as a learning benchmark. The results were validated against the manually counted database as the ground truth data set. We applied our algorithm to the Thermal Emission Imaging System global mosaic between ±65° of latitude, returning a true positive detection rate of 91% and a diameter estimation error (~15%) consistent with typical manual count variation. Importantly, although a number of automated crater counting algorithms have been published, for the first time we demonstrate that automatic counting can be routinely used to derive robust surface ages. Plain Language Summary Crater counting is the traditional method of determining the surface ages of planets throughout the solar system. This method, up to now, has used data that have been painstakingly counted by hand. The current published database for Mars contains hundreds of thousands of craters for diameters larger than 1 km. If we can count craters smaller than this, we will be able to target specific areas of interest to date. But the rate of impacts on planetary surfaces follows a power law such that the number of small (less than 1 km) craters is exponentially higher than the number of large craters. To count these requires an automated tool. Here we show that we have developed such a tool. We have validated the results against current manual databases. Importantly, and for the first time, we demonstrate that an automated crater counting tool can deliver geologically meaningful ages. Key Points We built a library of 7,048 craters to train a Crater Detection Algorithm (CDA) that we developed based on a neural network architecture We applied our algorithm to the Mars global THEMIS mosaic, generating results comparable to manual counting We applied the CDA to higher‐resolution images generating model ages indistinguishable (within error) from literature ages

• Publisher: John Wiley & Sons, Inc,American Geophysical Union (AGU)
• Subject: Age / Algorithms / automated crater detection algorithm / Automation / crater counting / Datasets / geochronology / Geology / isochron / machine leaning / Machine learning / Mars / Meteors & meteorites / Moon / Solar system