Publications

Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D). II. A Physics-informed Machine Learning Method for 3D Solar Photosphere Reconstruction

11 Dec 2025

Abstract Inferring the three-dimensional (3D) solar atmospheric structures from observations is a critical task for advancing our understanding of the magnetic-fields and electric currents that drive solar activity. In this work, we introduce a novel, physics-informed machine learning method to...

Connecting the Dots: A Machine Learning Ready Dataset for Ionospheric Forecasting Models

06 Dec 2025

Abstract Operational forecasting of the ionosphere remains a critical space weather challenge due to sparse observations, complex coupling across geospatial layers, and a growing need for timely, accurate predictions that support Global Navigation Satellite System (GNSS), communications, aviation safety, as...

Forecasting the Ionosphere from Sparse GNSS Data with Temporal-Fusion Transformers

06 Dec 2025

Abstract 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),...

IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics

06 Dec 2025

Abstract The ionosphere is a critical component of near-Earth space, shaping GNSS accuracy, high-frequency communications, and aviation operations. For these reasons, accurate forecasting and modeling of ionospheric variability has become increasingly relevant. To address this gap, we present IonCast, a...

Neural Surrogate HMC: On Using Neural Likelihoods for Hamiltonian Monte Carlo in Simulation-Based Inference

01 Dec 2025

Abstract Bayesian inference methods such as Markov Chain Monte Carlo (MCMC) typically require repeated computations of the likelihood function, but in some scenarios this is infeasible and alternative methods are needed. Simulation-based inference (SBI) methods address this problem by using...

WV-Net: A Foundation Model for SAR Ocean Satellite Imagery

10 Oct 2025

Abstract The European Space Agency’s Sentinel-1 (S-1) satellite mission has captured more than 10 million images of the ocean surface using C-band synthetic aperture radar (SAR WV mode). While machine learning is a promising approach for detecting and quantifying various...

NeuralHMC: Accelerated Hamiltonian Monte Carlo with a Neural Network Surrogate Likelihood

15 Dec 2023

Abstract Bayesian Inference with Markov Chain Monte Carlo requires efficient computation of the likelihood function. In some scientific applications, the likelihood must be computed by numerically solving a partial differential equation, which can be prohibitively expensive. We demonstrate that some...

The Stars Kepler Missed: Investigating the Kepler Target Selection Function Using Gaia DR2

23 Apr 2021

Abstract The Kepler Mission revolutionized exoplanet science and stellar astrophysics by obtaining highly precise photometry of over 200,000 stars over 4 yr. A critical piece of information to exploit Kepler data is its selection function, since all targets had to...

SEARCH: SEgmentation of polAR Coronal Holes

02 Mar 2021

Abstract The identification of solar coronal holes (CHs) observed in Extreme Ultraviolet (EUV) intensity images of the Sun is key in improving our understanding of their association with solar magnetic fields and heliophysics. In particular, CHs at the poles of...