Planet Four: A Neural Network's Search For Polar Spring-time Fans On Mars

TL;DR

This study employs deep convolutional neural networks to automatically identify and delineate seasonal dark deposits on Mars' south pole, outperforming traditional clustering methods and revealing additional deposits missed by citizen science efforts.

Contribution

The paper introduces CNN-based methods for detecting Martian seasonal deposits, demonstrating improved accuracy over existing clustering techniques and complementing citizen science data.

Findings

CNNs outperformed ISODATA clustering in predicting deposits

CNNs detected 27% more deposit area than Planet Four catalog

Some deposits missed by citizen science were identified by CNNs

Abstract

Dark deposits visible from orbit appear in the Martian south polar region during the springtime. These are thought to form from explosive jets of carbon dioxide gas breaking through the thawing seasonal ice cap, carrying dust and dirt which is then deposited onto the ice as dark 'blotches', or blown by the surface winds into streaks or 'fans'. We investigate machine learning (ML) methods for automatically identifying these seasonal features in High Resolution Imaging Science Experiment (HiRISE) satellite imagery. We designed deep Convolutional Neural Networks (CNNs) that were trained and tested using the catalog generated by Planet Four, an online citizen science project mapping the south polar seasonal deposits. We validated the CNNs by comparing their results with those of ISODATA (Iterative Self-Organizing Data Analysis Technique) clustering and as expected, the CNNs were significantly better at predicting the results found by Planet Four, in both the area of predicted seasonal deposits and in delineating their boundaries. We found neither the CNNs or ISODATA were suited to predicting the source point and directions of seasonal fans, which is a strength of the citizen science approach. The CNNs showed good agreement with Planet Four in cross-validation metrics and detected some seasonal deposits in the HiRISE images missed in the Planet Four catalog; the total area of seasonal deposits predicted by the CNNs was 27% larger than that of the Planet Four catalog, but this aspect varied considerably on a per-image basis.