HiPredict restores missing Mars HiRISE colour channel with machine learning
HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning
Machine Learning
Summary
HiRISE is a camera on a Mars orbiter that takes detailed colour pictures using several detectors. One detector started failing in 2023, which meant half the colour information was lost. The authors made a machine-learning method called HiPredict that uses data from other detectors to predict the missing colour channel more accurately than the previous simple method. This helps recover better colour images of Mars, showing important surface features more clearly. They also made their code publicly available so others can use and improve it.
What this means in practice
- •For planetary mission operators: Restore missing colour data in Mars imagery when individual camera detectors fail to maintain continuous scientific observations.
- •For satellite image analysts: Produce more accurate synthetic colour channels for Mars images to better identify geological and surface conditions.
Authors
Ardan Suphi, Ben Moseley, Gareth S Collins, Valentin T Bickel, Vidhya G Rangarajan
Abstract
The High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter (MRO) acquires imagery of Mars at 25--30 cm/pixel, supporting studies of martian geology, climate history, and landing-site characterization. Its 14-detector focal plane assembly includes several overlapping detectors that enable the acquisition of three-channel colour-infrared images, which are important for identifying compositional variations and studying active surface processes. In 2023, a detector in the center of the focal plane assembly (RED4) began failing intermittently, creating a gap in acquired imagery and reducing the instrument's colour-imaging capability by half. The HiRISE processing pipeline provides a synthetic red (SYN4) channel obtained by linearly scaling the co-located infrared (IR10) channel. However, this approach cannot capture observed non-linear relationships between the colour channels, limiting its accuracy and applicability. Here, we present HiPredict, a machine-learning framework that reconstructs RED4 from co-located IR10 and blue-green (BG12) imagery, neighbouring red-channel observations, and acquisition metadata. The model employs a U-Net architecture to learn non-linear spatiotemporal-spectral relationships between these inputs and is trained on 81,717 training samples, representing 13,625 observations. Evaluated on 23,348 test samples, representing 3,892 pre-failure observations, HiPredict reconstructs RED4 with a Normalised Mean Absolute Error of 1.1%, substantially outperforming SYN4 (3.1%). The reconstructed products improve colour image recovery and more closely represent features of interest such as icy craters, stratigraphy exposed along ridge crests and chloride deposits. We release HiPredict as an open software tool. This work demonstrates the potential of machine learning to mitigate data loss as planetary missions age and naturally degrade.