DeGaP: A Deep Gaussian Process Surrogate Model for Cleaning Data from Spatially Distributed Sensor Networks

The DeGaP model addresses the critical challenge of cleaning, gap-filling, and quantifying uncertainty in real-time magnetic field data. Developed as a Deep Gaussian Process (GP) surrogate model, DeGaP preserves high-frequency geophysical signals while removing noise and filling data gaps In Phase I, the DeGaP model successfully filled data gaps in high-frequency magnetic field measurements from the MagStar network, preserving essential geophysical features while quantifying uncertainty in the filled-in data. The model leveraged a novel spatiotemporal GP kernel that integrated a Spectral Mixture Kernel for capturing temporal complexities and a Radial Basis Function Kernel for spatial dependencies. Results showed that DeGap model accuracy in reconstructing high frequency components in magnetic field data under diverse geomagnetic conditions. Phase 2 will enhance and operationalize DeGaP by: 1. Advancing DeGaP by integrating it into real-time data processing workflows, delivering cleaned and gap-filled magnetic field data to NASA, NOAA, and other stakeholders. 2. Enhancements will include improved computational efficiency using GPU-accelerated techniques, expanded robustness to handle extended data gaps and noisy inputs, and an embedded anomaly detection module powered by GP uncertainty estimates. 3. The project will also develop user-friendly visualization tools for accessing cleaned data, uncertainty metrics enabling rapid decision-making for the subject matter expert in the loop to engage in ensuring data quality of the cleaned magnetic field data. The project will deliver a real-time, gap-filled magnetic field data stream with validated robustness under diverse geomagnetic conditions. DeGaP will directly support NASA’s heliophysics missions, model validation efforts, and space weather monitoring programs by ensuring reliable, high-quality data for scientific analysis and operational decision-making.

NASA has a significant need for high-quality magnetic field data to support its space weather modeling, mission planning, and scientific research. The DeGaP data product can directly enhance multiple NASA programs by providing validated, gap-filled magnetometer data that improves model accuracy and predictive capabilities. One key potential user is the NASA Community Coordinated Modeling Center (CCMC), which operates the Space Weather Modeling Framework (SWMF). This framework integrates various space weather models to predict geomagnetic storms, assess risks to satellites and astronauts, and forecast disruptions to GPS and communication systems. High-accuracy magnetic field data from DeGaP would be instrumental in model validation, reducing uncertainties in space weather predictions. Additionally, NASA’s Heliophysics Division could integrate DeGaP data into its efforts to improve understanding of the Sun-Earth connection. DeGaP’s ability to refine ground-based magnetometer data aligns with the division’s focus on improving space weather forecasting, satellite operations, and planetary exploration. Another application is within NOAA-SWPC’s World Magnetic Model (WMM), which NASA relies on for navigation, satellite operations, and geophysical mapping. The DeGaP data product can enhance WMM by improving ground-truth data quality, reducing discrepancies between observed and modeled magnetic fields. By collaborating with NASA centers such as Goddard Space Flight Center (GSFC) and Jet Propulsion Laboratory (JPL), DeGaP data could be integrated into broader heliophysics and planetary science missions. Expanding these partnerships would strengthen DeGaP’s role in space weather research and operational applications. The DeGaP model offers significant potential beyond NASA, addressing critical needs across industries and agencies that rely on high-quality magnetic field data for operational and hazard mitigation purposes. Its ability to clean, gap-fill, and quantify uncertainty in real-time makes it invaluable for several non-NASA applications, including the following: 1. Satellite Operations and Space Weather Services Space weather poses significant risks to satellite operations, impacting communication, navigation, and Earth observation systems. Solar flares, coronal mass ejections (CMEs), and geomagnetic storms can disrupt satellite electronics, degrade GPS accuracy, and even cause orbital decay in low Earth orbit. Organizations like NOAA’s Space Weather Prediction Center (SWPC) and private forecasting companies benefit from DeGaP’s reliable magnetic field data as a critical input for improving prediction accuracy and timeliness of space weather hazards. DeGaP’s ability to deliver real-time, high-fidelity magnetic field data with quantified uncertainties provides a critical advantage in mitigating these risks. 2. Geomagnetic Hazard Mitigation for Power Grids Power Grid Monitoring and Protection: Geomagnetically induced currents (GICs) are a major concern for electric utilities and grid operators worldwide. These currents, triggered by space weather events such as geomagnetic storms, can overload transformers, disrupt grid operations, and even lead to widespread blackouts. DeGaP improves the reliability of data inputs used in GIC forecasting models by filling gaps and removing noise from ground-based magnetometer readings. This allows grid operators to predict and respond to geomagnetic disturbances with higher confidence, mitigating the risk of cascading failures in power systems.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.