arXiv subjects

Katherine Deck

Publications and source records attributed to Katherine Deck.

10 recordsLinked to original sources

arXiv2026

A Next-Generation Snow Albedo Parameterization for Climate Modeling using Constrained Machine Learning

We demonstrate a data-driven parameterization for snow albedo using a constrained neural differential equation that directly predicts a range of snow albedo tendencies from standard snow and meteorological inputs. After training with multi-year in-situ and satellite observations from a wide variety of locations, the scheme effectively reproduces daily albedo evolution across diverse climate zones, with median error under 7.5% (RMSE ~0.05), a 10-30% improvement over established models. Furthermore, the model generalizes to sites not seen during training and scales from coarser grids to point locations. The scheme can easily incorporate new features as observational networks expand, offering an adaptive and computationally lightweight framework for next-generation land and climate models.

physics.app-ph↗

arXiv2025

Surface to Seafloor: A Generative AI Framework for Decoding the Ocean Interior State

Understanding subsurface ocean dynamics is essential for quantifying oceanic heat and mass transport, but direct observations at depth remain sparse due to logistical and technological constraints. In contrast, satellite missions provide rich surface datasets-such as sea surface height, temperature, and salinity-that offer indirect but potentially powerful constraints on the ocean interior. Here, we present a probabilistic framework based on score-based diffusion models to reconstruct three-dimensional subsurface velocity and buoyancy fields, including the energetic ocean eddy field, from surface observations. Using a 15-level primitive equation simulation of an idealized double-gyre system, we evaluate the skill of the model in inferring the mean circulation and the mesoscale variability at depth under varying levels of surface information. We find that the generative model successfully recovers key dynamical structures and provides physically meaningful uncertainty estimates, with predictive skill diminishing systematically as the surface resolution decreases or the inference depth increases. These results demonstrate the potential of generative approaches for ocean state estimation and uncertainty quantification, particularly in regimes where traditional deterministic methods are underconstrained or ill-posed.

physics.geo-ph↗

arXiv2024

Toward Routing River Water in Land Surface Models with Recurrent Neural Networks

Machine learning is playing an increasing role in hydrology, supplementing or replacing physics-based models. One notable example is the use of recurrent neural networks (RNNs) for forecasting streamflow given observed precipitation and geographic characteristics. Training of such a model over the continental United States (CONUS) has demonstrated that a single set of model parameters can be used across independent catchments, and that RNNs can outperform physics-based models. In this work, we take a next step and study the performance of RNNs for river routing in land surface models (LSMs). Instead of observed precipitation, the LSM-RNN uses instantaneous runoff calculated from physics-based models as an input. We train the model with data from river basins spanning the globe and test it using historical streamflow measurements. The model demonstrates skill at generalization across basins (predicting streamflow in catchments not used in training) and across time (predicting streamflow during years not used in training). We compare the predictions from the LSM-RNN to an existing physics-based model calibrated with a similar dataset and find that the LSM-RNN outperforms the physics-based model: a gain in median NSE from 0.56 to 0.64 (time-split experiment) and from 0.30 to 0.34 (basin-split experiment). Our results show that RNNs are effective for global streamflow prediction from runoff inputs and motivate the development of complete routing models that can capture nested sub-basis connections.

physics.comp-ph↗

arXiv2024

A Physics-Constrained Neural Differential Equation Framework for Data-Driven Snowpack Simulation

This paper presents a physics-constrained neural differential equation framework for parameterization, and employs it to model the time evolution of seasonal snow depth given hydrometeorological forcings. When trained on data from multiple SNOTEL sites, the parameterization predicts daily snow depth with under 9% median error and Nash Sutcliffe Efficiencies over 0.94 across a wide variety of snow climates. The parameterization also generalizes to new sites not seen during training, which is not often true for calibrated snow models. Requiring the parameterization to predict snow water equivalent in addition to snow depth only increases error to ~12%. The structure of the approach guarantees the satisfaction of physical constraints, enables these constraints during model training, and allows modeling at different temporal resolutions without additional retraining of the parameterization. These benefits hold potential in climate modeling, and could extend to other dynamical systems with physical constraints.

cs.LG↗

arXiv2024

Response Theory via Generative Score Modeling

We introduce an approach for analyzing the responses of dynamical systems to external perturbations that combines score-based generative modeling with the Generalized Fluctuation-Dissipation Theorem (GFDT). The methodology enables accurate estimation of system responses, including those with non-Gaussian statistics. We numerically validate our approach using time-series data from three different stochastic partial differential equations of increasing complexity: an Ornstein-Uhlenbeck process with spatially correlated noise, a modified stochastic Allen-Cahn equation, and the 2D Navier-Stokes equations. We demonstrate the improved accuracy of the methodology over conventional methods and discuss its potential as a versatile tool for predicting the statistical behavior of complex dynamical systems.

physics.data-an↗

arXiv2023

Easing Color Shifts in Score-Based Diffusion Models

Generated images of score-based models can suffer from errors in their spatial means, an effect, referred to as a color shift, which grows for larger images. This paper investigates a previously-introduced approach to mitigate color shifts in score-based diffusion models. We quantify the performance of a nonlinear bypass connection in the score network, designed to process the spatial mean of the input and to predict the mean of the score function. We show that this network architecture substantially improves the resulting quality of the generated images, and that this improvement is approximately independent of the size of the generated images. As a result, this modified architecture offers a simple solution for the color shift problem across image sizes. We additionally discuss the origin of color shifts in an idealized setting in order to motivate the approach.

cs.LG↗

arXiv2023

Unpaired Downscaling of Fluid Flows with Diffusion Bridges

We present a method to downscale idealized geophysical fluid simulations using generative models based on diffusion maps. By analyzing the Fourier spectra of images drawn from different data distributions, we show how one can chain together two independent conditional diffusion models for use in domain translation. The resulting transformation is a diffusion bridge between a low resolution and a high resolution dataset and allows for new sample generation of high-resolution images given specific low resolution features. The ability to generate new samples allows for the computation of any statistic of interest, without any additional calibration or training. Our unsupervised setup is also designed to downscale images without access to paired training data; this flexibility allows for the combination of multiple source and target domains without additional training. We demonstrate that the method enhances resolution and corrects context-dependent biases in geophysical fluid simulations, including in extreme events. We anticipate that the same method can be used to downscale the output of climate simulations, including temperature and precipitation fields, without needing to train a new model for each application and providing a significant computational cost savings.

cs.LG↗

arXiv2017

Mass and Eccentricity Constraints in the WASP-47 Planetary System from a Simultaneous Analysis of Radial Velocities & Transit Timing Variations

Measuring precise planet masses, densities, and orbital dynamics in individual planetary systems is an important pathway toward understanding planet formation. The WASP-47 system has an unusual architecture that motivates a complex formation theory. The system includes a hot Jupiter ("b") neighbored by interior ("e") and exterior ("d") sub-Neptunes, and a long-period eccentric giant planet ("c"). We simultaneously modeled transit times from the Kepler K2 Mission and 118 radial velocities to determine precise masses, densities, and Keplerian orbital elements of the WASP-47 planets. Combining RVs and TTVs provides a better estimate of the mass of planet d (13.6\pm2.0~M_\odot) than obtained with only RVs ($12.75\pm2.70~M_\odot$) or TTVs ($16.1\pm3.8~M_\odot$). Planets e and d have high densities for their size, consistent with a history of photo-evaporation and/or formation in a volatile-poor environment. Through our RV and TTV analysis, we find that the planetary orbits have eccentricities similar to the solar system planets. The WASP-47 system has three similarities to our own solar system: (1) the planetary orbits are nearly circular and coplanar, (2) the planets are not trapped in mean motion resonances, and (3) the planets have diverse compositions. None of the current single-process exoplanet formation theories adequately reproduce these three characteristics of the WASP-47 system (or our solar system). We propose that WASP-47, like the solar system, formed in two stages: first, the giant planets formed in a gas-rich disk and migrated to their present locations, and second, the high-density sub-Neptunes formed in situ in a gas-poor environment.

astro-ph.EP↗

arXiv2016

Transit timing to first order in eccentricity

Characterization of transiting planets with transit timing variations (TTVs) requires understanding how to translate the observed TTVs into masses and orbital elements of the planets. This can be challenging in multi-planet transiting systems, but fortunately these systems tend to be nearly plane-parallel and low eccentricity. Here we present a novel derivation of analytic formulae for TTVs that are accurate to first order in the planet-star mass ratios and in the orbital eccentricities. These formulae are accurate in proximity to first order resonances, as well as away from resonance, and compare well with more computationally expensive N-body integrations in the low eccentricity, low mass-ratio regime when applied to simulated and to actual multi-transiting Kepler planet systems. We make code available for implementing these formulae.

astro-ph.EP↗

arXiv2016

Spitzer Observations of Exoplanets Discovered with The Kepler K2 Mission

We have used the {\it Spitzer Space Telescope} to observe two transiting planetary systems orbiting low mass stars discovered in the \Kepler \Ktwo mission. The system K2-3 (EPIC 201367065) hosts three planets while EPIC 202083828 (K2-26) hosts a single planet. Observations of all four objects in these two systems confirm and refine the orbital and physical parameters of the planets. The refined orbital information and more precise planet radii possible with \Spitzer will be critical for future observations of these and other \Ktwo targets. For K2-3b we find marginally significant evidence for a Transit Timing Variation between the \Ktwo and \Spitzer\ epochs.

astro-ph.EP↗