Umaa Rebbapragada

Mirali Purohit, Bimal Gajera, Irish Mehta et al.

We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel to 100 m/pixel. Central to our method is our novel Equal Validation Loss (EVL) strategy, which aligns checkpoints across sensors based on validation loss similarity before fusion via task arithmetic. This ensures models are merged at compatible convergence stages, leading to improved stability and generalization. We train MOMO on a large-scale, high-quality corpus of $\sim 12$ million samples curated from Mars orbital data and evaluate it on 9 downstream tasks from Mars-Bench. MOMO achieves better overall performance compared to ImageNet pre-trained, earth observation foundation model, sensor-specific pre-training, and fully-supervised baselines. Particularly on segmentation tasks, MOMO shows consistent and significant performance improvement. Our results demonstrate that model merging through an optimal checkpoint selection strategy provides an effective approach for building foundation models for multi-resolution data. The model weights, pretraining code, pretraining data, and evaluation code are available at: https://github.com/kerner-lab/MOMO.

Giacomo Acciarini, Simone Mestici, Halil Kelebek et al.

The ionosphere critically influences Global Navigation Satellite Systems (GNSS), satellite communications, and Low Earth Orbit (LEO) operations, yet accurate prediction of its variability remains challenging due to nonlinear couplings between solar, geomagnetic, and thermospheric drivers. Total Electron Content (TEC), a key ionospheric parameter, is derived from GNSS observations, but its reliable forecasting is limited by the sparse nature of global measurements and the limited accuracy of empirical models, especially during strong space weather conditions. In this work, we present a machine learning framework for ionospheric TEC forecasting that leverages Temporal Fusion Transformers (TFT) to predict sparse ionosphere data. Our approach accommodates heterogeneous input sources, including solar irradiance, geomagnetic indices, and GNSS-derived vertical TEC, and applies preprocessing and temporal alignment strategies. Experiments spanning 2010-2025 demonstrate that the model achieves robust predictions up to 24 hours ahead, with root mean square errors as low as 3.33 TECU. Results highlight that solar EUV irradiance provides the strongest predictive signals. Beyond forecasting accuracy, the framework offers interpretability through attention-based analysis, supporting both operational applications and scientific discovery. To encourage reproducibility and community-driven development, we release the full implementation as the open-source toolkit \texttt{ionopy}.

Mirali Purohit, Bimal Gajera, Vatsal Malaviya et al.

Foundation models have enabled rapid progress across many specialized domains by leveraging large-scale pre-training on unlabeled data, demonstrating strong generalization to a variety of downstream tasks. While such models have gained significant attention in fields like Earth Observation, their application to Mars science remains limited. A key enabler of progress in other domains has been the availability of standardized benchmarks that support systematic evaluation. In contrast, Mars science lacks such benchmarks and standardized evaluation frameworks, which have limited progress toward developing foundation models for Martian tasks. To address this gap, we introduce Mars-Bench, the first benchmark designed to systematically evaluate models across a broad range of Mars-related tasks using both orbital and surface imagery. Mars-Bench comprises 20 datasets spanning classification, segmentation, and object detection, focused on key geologic features such as craters, cones, boulders, and frost. We provide standardized, ready-to-use datasets and baseline evaluations using models pre-trained on natural images, Earth satellite data, and state-of-the-art vision-language models. Results from all analyses suggest that Mars-specific foundation models may offer advantages over general-domain counterparts, motivating further exploration of domain-adapted pre-training. Mars-Bench aims to establish a standardized foundation for developing and comparing machine learning models for Mars science. Our data, models, and code are available at: https://mars-bench.github.io/.

Kyongsik Yun, Rishi Verma, Umaa Rebbapragada

The Deep Space Network is NASA's international array of antennas that support interplanetary spacecraft missions. A track is a block of multi-dimensional time series from the beginning to end of DSN communication with the target spacecraft, containing thousands of monitor data items lasting several hours at a frequency of 0.2-1Hz. Monitor data on each track reports on the performance of specific spacecraft operations and the DSN itself. DSN is receiving signals from 32 spacecraft across the solar system. DSN has pressure to reduce costs while maintaining the quality of support for DSN mission users. DSN Link Control Operators need to simultaneously monitor multiple tracks and identify anomalies in real time. DSN has seen that as the number of missions increases, the data that needs to be processed increases over time. In this project, we look at the last 8 years of data for analysis. Any anomaly in the track indicates a problem with either the spacecraft, DSN equipment, or weather conditions. DSN operators typically write Discrepancy Reports for further analysis. It is recognized that it would be quite helpful to identify 10 similar historical tracks out of the huge database to quickly find and match anomalies. This tool has three functions: (1) identification of the top 10 similar historical tracks, (2) detection of anomalies compared to the reference normal track, and (3) comparison of statistical differences between two given tracks. The requirements for these features were confirmed by survey responses from 21 DSN operators and engineers. The preliminary machine learning model has shown promising performance (AUC=0.92). We plan to increase the number of data sets and perform additional testing to improve performance further before its planned integration into the track visualizer interface to assist DSN field operators and engineers.