Squeezing Data from a Rock: Machine Learning for Martian Science

Data analysis methods have scarcely kept pace with the rapid increase in Earth observations, spurring the development of novel algorithms, storage methods, and computational techniques. For scientists interested in Mars, the problem is always the same: there is simultaneously never enough of the right data and an overwhelming amount of data in total. Finding sufficient data needles in a haystack to test a hypothesis requires hours of manual data screening, and more needles and hay are added constantly. To date, the vast majority of Martian research has been focused on either one-off local/regional studies or on hugely time-consuming manual global studies. Machine learning in its numerous forms can be helpful for future such work. Machine learning has the potential to help map and classify a large variety of both features and properties on the surface of Mars and to aid in the planning and execution of future missions. Here, we outline the current extent of machine learning as applied to Mars, summarize why machine learning should be an important tool for planetary geomorphology in particular, and suggest numerous research avenues and funding priorities for future efforts. We conclude that: (1) moving toward methods that require less human input (i.e., self- or semi-supervised) is an important paradigm shift for Martian applications, (2) new robust methods using generative adversarial networks to generate synthetic high-resolution digital terrain models represent an exciting new avenue for Martian geomorphologists, (3) more effort and money must be directed toward developing standardized datasets and benchmark tests, and (4) the community needs a large-scale, generalized, and programmatically accessible geographic information system (GIS).

Revealing Active Mars with HiRISE Digital Terrain Models

Many discoveries of active surface processes on Mars have been made due to the availability of repeat high-resolution images from the High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter. HiRISE stereo images are used to make digital terrain models (DTMs) and orthorectified images (orthoimages). HiRISE DTMs and orthoimage time series have been crucial for advancing the study of active processes such as recurring slope lineae, dune migration, gully activity, and polar processes. We describe the process of making HiRISE DTMs, orthoimage time series, DTM mosaics, and the difference of DTMs, specifically using the ISIS/SOCET Set workflow. HiRISE DTMs are produced at a 1 and 2 m ground sample distance, with a corresponding estimated vertical precision of tens of cm and ∼1 m, respectively. To date, more than 6000 stereo pairs have been acquired by HiRISE and, of these, more than 800 DTMs and 2700 orthoimages have been produced and made available to the public via the Planetary Data System. The intended audiences of this paper are producers, as well as users, of HiRISE DTMs and orthoimages. We discuss the factors that determine the effective resolution, as well as the quality, precision, and accuracy of HiRISE DTMs, and provide examples of their use in time series analyses of active surface processes on Mars.

Blocks Size Frequency Distribution in the Enceladus Tiger Stripes Area: Implications on Their Formative Processes

We study the size frequency distribution of the blocks located in the deeply fractured, geologically active Enceladus South Polar Terrain with the aim to suggest their formative mechanisms. Through the Cassini ISS images, we identify ~17,000 blocks with sizes ranging from ~25 m to 366 m, and located at different distances from the Damascus, Baghdad and Cairo Sulci. On all counts and for both Damascus and Baghdad cases, the power-law fitting curve has an index that is similar to the one obtained on the deeply fractured, actively sublimating Hathor cliff on comet 67P/Churyumov-Gerasimenko, where several non-dislodged blocks are observed. This suggests that as for 67P, sublimation and surface stresses favor similar fractures development in the Enceladus icy matrix, hence resulting in comparable block disaggregation. A steeper power-law index for Cairo counts may suggest a higher degree of fragmentation, which could be the result of localized, stronger tectonic disruption of lithospheric ice. Eventually, we show that the smallest blocks identified are located from tens of m to 20–25 km from the Sulci fissures, while the largest blocks are found closer to the tiger stripes. This result supports the ejection hypothesis mechanism as the possible source of blocks.

Particle Size-Frequency Distributions of the OSIRIS-REx Candidate Sample Sites on Asteroid (101955) Bennu

We manually mapped particles ranging in longest axis from 0.3 cm to 95 m on (101955) Bennu for the Origins, Spectral Interpretation, Resource Identification, and Security–Regolith Explorer (OSIRIS-REx) asteroid sample return mission. This enabled the mission to identify candidate sample collection sites and shed light on the processes that have shaped the surface of this rubble-pile asteroid. Building on a global survey of particles, we used higher-resolution data from regional observations to calculate particle size-frequency distributions (PSFDs) and assess the viability of four candidate sites for sample collection (presence of unobstructed particles ≤ 2 cm). The four candidate sites have common characteristics: each is situated within a crater with a relative abundance of sampleable material. Their PSFDs, however, indicate that each site has experienced different geologic processing. The PSFD power-law slopes range from −3.0 ± 0.2 to −2.3 ± 0.1 across the four sites, based on images with a 0.01-m pixel scale. These values are consistent with, or shallower than, the global survey measurements. At one site, Osprey, the particle packing density appears to reach geometric saturation. We evaluate the uncertainty in these measurements and discuss their implications for other remotely sensed and mapped particles, and their importance to OSIRIS-REx sampling operations.

Surface boulder banding indicates Martian debris-covered glaciers formed over multiple glaciations

Significant debate exists whether the global population of Martian debris-covered glacier deposits formed continuously over the past 300 to 800 Ma, or whether they formed during punctuated episodes of ice accumulation during obliquity maxima (lasting ∼10–100 ka). We show that, like ancient debris-covered glaciers on Earth, boulder banding on Martian glacial deposits indicates multiple episodes of ice accumulation and advance. In our analysis, glacial periods are followed by ice removal from the glacier accumulation zone, forming debris bands. We report a median of five to six glacial/interglacial transitions recorded on Martian debris-covered glaciers, suggesting the cadence of glaciation on Mars is set by orbital forcing over tens to hundreds of Ma, not individual ∼120 ka obliquity cycles.

Glacial landforms, including lobate debris aprons, are a global water ice reservoir on Mars preserving ice from past periods when high orbital obliquity permitted nonpolar ice accumulation. Numerous studies have noted morphological similarities between lobate debris aprons and terrestrial debris-covered glaciers, an interpretation supported by radar observations. On Earth and Mars, these landforms consist of a core of flowing ice covered by a rocky lag. Terrestrial debris-covered glaciers advance in response to climate forcing driven by obliquity-paced changes to ice mass balance. However, on Mars, it is not known whether glacial landforms emplaced over the past 300 to 800 formed during a single, long deposition event or during multiple glaciations. Here, we show that boulders atop 45 lobate debris aprons exhibit no evidence of monotonic comminution but are clustered into bands that become more numerous with increasing latitude, debris apron length, and pole-facing flow orientation. Boulder bands are prominent at glacier headwalls, consistent with debris accumulation during the current Martian interglacial. Terrestrial glacier boulder bands occur near flow discontinuities caused by obliquity-driven hiatuses in ice accumulation, forming internal debris layers. By analogy, we suggest that Martian lobate debris aprons experienced multiple cycles of ice deposition, followed by ice destabilization in the accumulation zone, leading to boulder-dominated lenses and subsequent ice deposition and continued flow. Correlation between latitude and boulder clustering suggests that ice mass-balance works across global scales on Mars. Lobate debris aprons may preserve ice spanning multiple glacial/interglacial cycles, extending Mars climate records back hundreds of millions of years.

Photogeologic Map of the Perseverance Rover Field Site in Jezero Crater Constructed by the Mars 2020 Science Team

The Mars 2020 Perseverance rover landing site is located within Jezero crater, a ∼ 50 km diameter impact crater interpreted to be a Noachian-aged lake basin inside the western edge of the Isidis impact structure. Jezero hosts remnants of a fluvial delta, inlet and outlet valleys, and infill deposits containing diverse carbonate, mafic, and hydrated minerals. Prior to the launch of the Mars 2020 mission, members of the Science Team collaborated to produce a photogeologic map of the Perseverance landing site in Jezero crater. Mapping was performed at a 1:5000 digital map scale using a 25 cm/pixel High Resolution Imaging Science Experiment (HiRISE) orthoimage mosaic base map and a 1 m/pixel HiRISE stereo digital terrain model. Mapped bedrock and surficial units were distinguished by differences in relative brightness, tone, topography, surface texture, and apparent roughness. Mapped bedrock units are generally consistent with those identified in previously published mapping efforts, but this study's map includes the distribution of surficial deposits and sub-units of the Jezero delta at a higher level of detail than previous studies. This study considers four possible unit correlations to explain the relative age relationships of major units within the map area. Unit correlations include previously published interpretations as well as those that consider more complex interfingering relationships and alternative relative age relationships. The photogeologic map presented here is the foundation for scientific hypothesis development and strategic planning for Perseverance's exploration of Jezero crater.

Photogeologic Map of the Perseverance Rover Field Site in Jezero Crater Constructed by the Mars 2020 Science Team

The Mars 2020 Perseverance rover landing site is located within Jezero crater, a ∼ 50 km diameter impact crater interpreted to be a Noachian-aged lake basin inside the western edge of the Isidis impact structure. Jezero hosts remnants of a fluvial delta, inlet and outlet valleys, and infill deposits containing diverse carbonate, mafic, and hydrated minerals. Prior to the launch of the Mars 2020 mission, members of the Science Team collaborated to produce a photogeologic map of the Perseverance landing site in Jezero crater. Mapping was performed at a 1:5000 digital map scale using a 25 cm/pixel High Resolution Imaging Science Experiment (HiRISE) orthoimage mosaic base map and a 1 m/pixel HiRISE stereo digital terrain model. Mapped bedrock and surficial units were distinguished by differences in relative brightness, tone, topography, surface texture, and apparent roughness. Mapped bedrock units are generally consistent with those identified in previously published mapping efforts, but this study's map includes the distribution of surficial deposits and sub-units of the Jezero delta at a higher level of detail than previous studies. This study considers four possible unit correlations to explain the relative age relationships of major units within the map area. Unit correlations include previously published interpretations as well as those that consider more complex interfingering relationships and alternative relative age relationships. The photogeologic map presented here is the foundation for scientific hypothesis development and strategic planning for Perseverance's exploration of Jezero crater.

PlaNet: A Neural Network for Detecting Transverse Aeolian Ridges on Mars

Transverse aeolian ridges (TARs) are unusual bedforms on the surface of Mars. TARs are common but sparse on Mars; TAR fields are small, rarely continuous, and scattered, making manual mapping impractical. There have been many efforts to automatically classify the Martian surface, but they have never explicitly located TARs successfully. Here, we present a simple adaptation of the off-the-shelf neural network RetinaNet that is designed to identify the presence of TARs at a 50-m scale. Once trained, the network was able to identify TARs with high precision (92.9%). Our model also shows promising results for applications to other surficial features like ripples and polygonal terrain. In the future, we hope to apply this model more broadly and generate a large database of TAR distributions on Mars.

Assessment of InSight Landing Site Predictions

Comprehensive analysis of remote sensing data used to select the Interior Exploration using Seismic Investigations, Geodesy and Heat Transport (InSight) landing site correctly predicted the atmospheric temperature and pressure profile during entry and descent, the safe landing surface, and the geologic setting of the site. The smooth plains upon which the InSight landing site is located were accurately predicted to be generally similar to the Mars Exploration Rover Spirit landing site with relatively low rock abundance, low slopes, and a moderately dusty surface with a 3-10 m impact fragmented regolith over Hesperian to Early Amazonian basaltic lava flows. The deceleration profile and surface pressure encountered by the spacecraft during entry, descent, and landing compared well (within 1σ) of the envelope of modeled temperature profiles and the expected surface pressure. Orbital estimates of thermal inertia are similar to surface radiometer measurements, and materials at the surface are dominated by poorly consolidated sand as expected. Thin coatings of bright atmospheric dust on the surface were as indicated by orbital albedo and dust cover index measurements. Orbital estimates of rock abundance from shadow measurements in high-resolution images and thermal differencing indicated very low rock abundance and surface counts show 1-4% area covered by rocks. Slopes at 100 to 5 m length scale measured from orbital topographic and radar data correctly indicated a surface comparably smooth and flat as the two smoothest landing sites (Opportunity and Phoenix). Thermal inertia and radar data indicated the surface would be load bearing as found.

Geology of the InSight landing site on Mars

The Interior Exploration using Seismic Investigations, Geodesy and Heat Transport (InSight) spacecraft landed successfully on Mars and imaged the surface to characterize the surficial geology. Here we report on the geology and subsurface structure of the landing site to aid in situ geophysical investigations. InSight landed in a degraded impact crater in Elysium Planitia on a smooth sandy, granule- and pebble-rich surface with few rocks. Superposed impact craters are common and eolian bedforms are sparse. During landing, pulsed retrorockets modified the surface to reveal a near surface stratigraphy of surficial dust, over thin unconsolidated sand, underlain by a variable thickness duricrust, with poorly sorted, unconsolidated sand with rocks beneath. Impact, eolian, and mass wasting processes have dominantly modified the surface. Surface observations are consistent with expectations made from remote sensing data prior to landing indicating a surface composed of an impact-fragmented regolith overlying basaltic lava flows.

The InSight spacecraft landed on Mars on November 2018. Here, the authors characterize the surficial geology of the landing site and compare with observations and models derived from remote sensing data prior to landing and from ongoing in situ geophysical investigations of the subsurface.

Field trial of a dual-wavelength fluorescent emission (L.I.F.E.) instrument and the Magma White rover during the MARS2013 Mars analog mission

Abstract We have developed a portable dual-wavelength laser fluorescence spectrometer as part of a multi-instrument optical probe to characterize mineral, organic, and microbial species in extreme environments. Operating at 405 and 532 nm, the instrument was originally designed for use by human explorers to produce a laser-induced fluorescence emission (L.I.F.E.) spectral database of the mineral and organic molecules found in the microbial communities of Earth's cryosphere. Recently, our team had the opportunity to explore the strengths and limitations of the instrument when it was deployed on a remote-controlled Mars analog rover. In February 2013, the instrument was deployed on board the Magma White rover platform during the MARS2013 Mars analog field mission in the Kess Kess formation near Erfoud, Morocco. During these tests, we followed tele-science work flows pertinent to Mars surface missions in a simulated spaceflight environment. We report on the L.I.F.E. instrument setup, data processing, and performance during field trials. A pilot postmission laboratory analysis determined that rock samples acquired during the field mission exhibited a fluorescence signal from the Sun-exposed side characteristic of chlorophyll a following excitation at 405 nm. A weak fluorescence response to excitation at 532 nm may have originated from another microbial photosynthetic pigment, phycoerythrin, but final assignment awaits development of a comprehensive database of mineral and organic fluorescence spectra. No chlorophyll fluorescence signal was detected from the shaded underside of the samples.