arXiv subjects

Jeremy Vila

Publications and source records attributed to Jeremy Vila.

6 recordsLinked to original sources

arXiv2026

Partial recovery of meter-scale surface weather

Near-surface weather varies over tens to hundreds of meters, yet remains unresolved in analyses and forecasts. We test whether this variation can be inferred without resolving atmospheric dynamics. Combining sparse weather stations, high-resolution Earth observation, and coarse atmospheric dynamics, we infer temperature, dewpoint, and wind at 30-m resolution across the contiguous United States. Against measurements held out in space and time, estimates reduce error by 11-28\% relative to the strongest baseline. Within held-out $0.25^\circ$ grid cells, we recover more spatial variance than baselines, explaining nearly half of temperature variability in the median cell. The method captures time-varying differences between locations and produces coherent patterns associated with topography and land cover. Beyond weather, our findings illustrate how sparse observations of a dynamical system can be combined with dense observations of persistent environmental structure to recover otherwise unresolved spatial variability.

cs.LG↗

arXiv2025

Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data

Urgent applications like wildfire management and renewable energy generation require precise, localized weather forecasts near the Earth's surface. However, forecasts produced by machine learning models or numerical weather prediction systems are typically generated on large-scale regular grids, where direct downscaling fails to capture fine-grained, near-surface weather patterns. In this work, we propose a multi-modal transformer model trained end-to-end to downscale gridded forecasts to off-grid locations of interest. Our model directly combines local historical weather observations (e.g., wind, temperature, dewpoint) with gridded forecasts to produce locally accurate predictions at various lead times. Multiple data modalities are collected and concatenated at station-level locations, treated as a token at each station. Using self-attention, the token corresponding to the target location aggregates information from its neighboring tokens. Experiments using weather stations across the Northeastern United States show that our model outperforms a range of data-driven and non-data-driven off-grid forecasting methods. They also reveal that direct input of station data provides a phase shift in local weather forecasting accuracy, reducing the prediction error by up to 80% compared to pure gridded data based models. This approach demonstrates how to bridge the gap between large-scale weather models and locally accurate forecasts to support high-stakes, location-sensitive decision-making.

cs.LG↗

arXiv2019

Accelerating Least Squares Imaging Using Deep Learning Techniques

Wave equation techniques have been an integral part of geophysical imaging workflows to investigate the Earth's subsurface. Least-squares reverse time migration (LSRTM) is a linearized inversion problem that iteratively minimizes a misfit functional as a function of the model perturbation. The success of the inversion largely depends on our ability to handle large systems of equations given the massive computation costs. The size of the system almost exponentially increases with the demand for higher resolution images in complicated subsurface media. We propose an unsupervised deep learning approach that leverages the existing physics-based models and machine learning optimizers to achieve more accurate and cheaper solutions. We compare different optimizers and demonstrate their efficacy in mitigating imaging artifacts. Further, minimizing the Huber loss with mini-batch gradients and Adam optimizer is not only less memory-intensive but is also more robust. Our empirical results on synthetic, densely sampled datasets suggest faster convergence to an accurate LSRTM result than a traditional approach.

physics.comp-ph↗

arXiv2015

Hyperspectral Unmixing via Turbo Bilinear Approximate Message Passing

The goal of hyperspectral unmixing is to decompose an electromagnetic spectral dataset measured over M spectral bands and T pixels into N constituent material spectra (or "end-members") with corresponding spatial abundances. In this paper, we propose a novel approach to hyperspectral unmixing based on loopy belief propagation (BP) that enables the exploitation of spectral coherence in the endmembers and spatial coherence in the abundances. In particular, we partition the factor graph into spectral coherence, spatial coherence, and bilinear subgraphs, and pass messages between them using a "turbo" approach. To perform message passing within the bilinear subgraph, we employ the bilinear generalized approximate message passing algorithm (BiG-AMP), a recently proposed belief-propagation-based approach to matrix factorization. Furthermore, we propose an expectation-maximization (EM) strategy to tune the prior parameters and a model-order selection strategy to select the number of materials N. Numerical experiments conducted with both synthetic and real-world data show favorable unmixing performance relative to existing methods.

cs.IT↗

arXiv2014

Adaptive Damping and Mean Removal for the Generalized Approximate Message Passing Algorithm

The generalized approximate message passing (GAMP) algorithm is an efficient method of MAP or approximate-MMSE estimation of $x$ observed from a noisy version of the transform coefficients $z = Ax$. In fact, for large zero-mean i.i.d sub-Gaussian $A$, GAMP is characterized by a state evolution whose fixed points, when unique, are optimal. For generic $A$, however, GAMP may diverge. In this paper, we propose adaptive damping and mean-removal strategies that aim to prevent divergence. Numerical results demonstrate significantly enhanced robustness to non-zero-mean, rank-deficient, column-correlated, and ill-conditioned $A$.

cs.IT↗

arXiv2014

An Empirical-Bayes Approach to Recovering Linearly Constrained Non-Negative Sparse Signals

We propose two novel approaches to the recovery of an (approximately) sparse signal from noisy linear measurements in the case that the signal is a priori known to be non-negative and obey given linear equality constraints, such as simplex signals. This problem arises in, e.g., hyperspectral imaging, portfolio optimization, density estimation, and certain cases of compressive imaging. Our first approach solves a linearly constrained non-negative version of LASSO using the max-sum version of the generalized approximate message passing (GAMP) algorithm, where we consider both quadratic and absolute loss, and where we propose a novel approach to tuning the LASSO regularization parameter via the expectation maximization (EM) algorithm. Our second approach is based on the sum-product version of the GAMP algorithm, where we propose the use of a Bernoulli non-negative Gaussian-mixture signal prior and a Laplacian likelihood, and propose an EM-based approach to learning the underlying statistical parameters. In both approaches, the linear equality constraints are enforced by augmenting GAMP's generalized-linear observation model with noiseless pseudo-measurements. Extensive numerical experiments demonstrate the state-of-the-art performance of our proposed approaches.

cs.IT↗