The NASA Planetary Data System hosts millions of images acquired from the planet Mars. To help users quickly find images of interest, we have developed and deployed content-based classification and search capabilities for Mars orbital and surface images. The deployed systems are publicly accessible using the PDS Image Atlas. We describe the process of training, evaluating, calibrating, and deploying updates to two CNN classifiers for images collected by Mars missions. We also report on three years of deployment including usage statistics, lessons learned, and plans for the future.

In this work, we demonstrate an instrumented wheel concept which utilizes a 2D pressure grid, an electrochemical impedance spectroscopy (EIS) sensor and machine learning (ML) to extract meaningful metrics from the interaction between the wheel and surface terrain. These include continuous slip/skid estimation, balance, and sharpness for engineering applications. Estimates of surface hydration, texture, terrain patterns, and regolith physical properties such as cohesion and angle of internal friction are additionally calculated for science applications. Traditional systems rely on post-processing of visual images and vehicle telemetry to estimate these metrics. Through in-situ sensing, these metrics can be calculated in near real time and made available to onboard science and engineering autonomy applications. This work aims to provide a deployable system for future planetary exploration missions to increase science and engineering capabilities through increased knowledge of the terrain.

Algorithms for soil moisture estimation from radars conventionally use substantial amounts of ancillary data to parametrize complex electromagnetic models. In contrast, we describe radar data of a vegetated scene as a linear function of soil moisture. This eliminates the dependence on ancillary data while providing reasonable global soil moisture estimates. We derive two polarization dependent coefficients of a linear model on the basis of spatial and temporal similarity at a global scale from nearly 4 years of L-band Aquarius radar and radiometer derived soil moisture data. These global coefficients are then used to derive soil moisture from 2.5 months of L-band SMAP radar data. The resulting soil moisture estimates are evaluated with the SMAP Level 2 radiometer-only soil moisture product.

Mapping localized spectral features in complex scenes demands sensitive and robust detection algorithms. This letter investigates two aspects of large images that can harm matched filter (MF) detection performance. First, multimodal backgrounds may violate normality assumptions. Second, outlier features can trigger false detections due to large projections onto the target vector. We review two state-of-the-art methods designed to resolve these issues. The background clustering of Funkmodels multimodal backgrounds, and the mixture-tuned (MT) MF of Boardman and Kruse addresses outliers. We demonstrate that combining the two methods has additional performance benefits. An MT cluster MF shows effective performance on simulated and airborne data sets. We demonstrate target detection scenarios that evidence multimodality, outliers, and their combination. These experiments explore the performance of the component algorithms and the practical circumstances that can favor a combined approach.

Orbital remote sensing provides a powerful way to efficiently survey targets such as the Earth and other planets and moons for features of interest. One such feature of astrobiological relevance is the presence of surface sulfur deposits. These deposits have been observed to be associated with microbial activity at the Borup Fiord glacial springs in Canada, a location that may provide an analogue to other icy environments such as Europa. This article evaluates automated classifiers for detecting sulfur in remote sensing observations by the hyperion spectrometer on the EO-1 spacecraft. We determined that a data-driven machine learning solution was needed because the sulfur could not be detected by simply matching observations to sulfur lab spectra. We also evaluated several methods (manual and automated) for identifying the most relevant attributes (spectral wavelengths) needed for successful sulfur detection. Our findings include (1) the Borup Fiord sulfur deposits were best modeled as containing two sub-populations: sulfur on ice and sulfur on rock; (2) as expected, classifiers using Gaussian kernels outperformed those based on linear kernels, and should be adopted when onboard computational constraints permit; and (3) Recursive Feature Elimination selected sensible and effective features for use in the computationally constrained environment onboard EO-1. This study helped guide the selection of algorithm parameters and configuration for the classification system currently operational on EO-1. Finally, we discuss implications for a similar onboard classification system for a future Europa orbiter.

Superpixels are homogeneous image regions comprised of multiple contiguous pixels. Superpixel representations can reduce noise in hyperspectral images by exploiting the spatial contiguity of scene features. This paper combines superpixels with endmember extraction to produce concise mineralogical summaries that assist in browsing large image catalogs. First, a graph-based agglomerative algorithm oversegments the image. We then use segments' mean spectra as input to existing statistical endmember detection algorithms such as sequential maximum angle convex cone (SMACC) and N-FINDR. Experiments compare automatically detected endmembers to target minerals in an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) scene of Cuprite, Nevada. We also consider a planetary science data set from the Compact Reconnaissance Imaging Spectrometer (CRISM) instrument that benefits from spatial averaging due to higher noise. In both cases, superpixel representations significantly reduce the computational complexity of later processing while improving endmembers' match to the target spectra.