arXiv subjects

Karan Jakhar

Publications and source records attributed to Karan Jakhar.

6 recordsLinked to original sources

arXiv2026

Prediction of Extreme Events in Multiscale Simulations of Geophysical Turbulence using Reinforcement Learning

Accurate subgrid-scale closures are essential for weather/climate models, where predicting extreme events is critical. Traditional closures have structural errors, e.g., producing excessive diffusion that dampens extremes. Artificial intelligence has gained attention for closure modeling, but the prediction of extreme events remains challenging. Supervised offline learning needs abundant high-fidelity training data and can lead to instabilities. Online learning algorithms are emerging as an alternative, but reliance on differentiable numerical solvers or scalable optimizers hinders broad use. Here, we introduce SMARL to develop closures for canonical prototypes of atmospheric/oceanic turbulence, using only the enstrophy spectrum, estimated from a few high-fidelity samples, as reward. This reward ensures that the model captures the cascades of scales in these simulations. These online-learned closures enable stable simulations, with up to five orders of magnitude fewer degrees of freedom, that reproduce high-fidelity simulation statistics and capture in particular extremes. We interpret the closures by analyzing the SMARL policy and demonstrate generalization to other flows. The results highlight SMARL as a potent tool for developing closures capable of capturing extremes in atmospheric/oceanic flows, opening new capabilities for effective climate modeling.

physics.geo-ph↗

arXiv2025

An Analytical and AI-discovered Stable, Accurate, and Generalizable Subgrid-scale Closure for Geophysical Turbulence

By combining AI and fluid physics, we discover a closed-form closure for 2D turbulence from small direct numerical simulation (DNS) data. Large-eddy simulation (LES) with this closure is accurate and stable, reproducing DNS statistics including those of extremes. We also show that the new closure could be derived from a 4th-order truncated Taylor expansion. Prior analytical and AI-based work only found the 2nd-order expansion, which led to unstable LES. The additional terms emerge only when inter-scale energy transfer is considered alongside standard reconstruction criterion in the sparse-equation discovery.

physics.ao-ph↗

arXiv2025

Hierarchical Implicit Neural Emulators

Neural PDE solvers offer a powerful tool for modeling complex dynamical systems, but often struggle with error accumulation over long time horizons and maintaining stability and physical consistency. We introduce a multiscale implicit neural emulator that enhances long-term prediction accuracy by conditioning on a hierarchy of lower-dimensional future state representations. Drawing inspiration from the stability properties of numerical implicit time-stepping methods, our approach leverages predictions several steps ahead in time at increasing compression rates for next-timestep refinements. By actively adjusting the temporal downsampling ratios, our design enables the model to capture dynamics across multiple granularities and enforce long-range temporal coherence. Experiments on turbulent fluid dynamics show that our method achieves high short-term accuracy and produces long-term stable forecasts, significantly outperforming autoregressive baselines while adding minimal computational overhead.

cs.LG↗

arXiv2024

Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges

There is growing interest in discovering interpretable, closed-form equations for subgrid-scale (SGS) closures/parameterizations of complex processes in Earth systems. Here, we apply a common equation-discovery technique with expansive libraries to learn closures from filtered direct numerical simulations of 2D turbulence and Rayleigh-Bénard convection (RBC). Across common filters (e.g., Gaussian, box), we robustly discover closures of the same form for momentum and heat fluxes. These closures depend on nonlinear combinations of gradients of filtered variables, with constants that are independent of the fluid/flow properties and only depend on filter type/size. We show that these closures are the nonlinear gradient model (NGM), which is derivable analytically using Taylor-series. Indeed, we suggest that with common (physics-free) equation-discovery algorithms, for many common systems/physics, discovered closures are consistent with the leading term of the Taylor-series (except when cutoff filters are used). Like previous studies, we find that large-eddy simulations with NGM closures are unstable, despite significant similarities between the true and NGM-predicted fluxes (correlations $> 0.95$). We identify two shortcomings as reasons for these instabilities: in 2D, NGM produces zero kinetic energy transfer between resolved and subgrid scales, lacking both diffusion and backscattering. In RBC, potential energy backscattering is poorly predicted. Moreover, we show that SGS fluxes diagnosed from data, presumed the ''truth'' for discovery, depend on filtering procedures and are not unique. Accordingly, to learn accurate, stable closures in future work, we propose several ideas around using physics-informed libraries, loss functions, and metrics. These findings are relevant to closure modeling of any multi-scale system.

physics.flu-dyn↗

arXiv2021

Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax

Computer vision has shown promising results in medical image processing. Pneumothorax is a deadly condition and if not diagnosed and treated at time then it causes death. It can be diagnosed with chest X-ray images. We need an expert and experienced radiologist to predict whether a person is suffering from pneumothorax or not by looking at the chest X-ray images. Everyone does not have access to such a facility. Moreover, in some cases, we need quick diagnoses. So we propose an image segmentation model to predict and give the output a mask that will assist the doctor in taking this crucial decision. Deep Learning has proved their worth in many areas and outperformed man state-of-the-art models. We want to use the power of these deep learning model to solve this problem. We have used U-net [13] architecture with ResNet [17] as a backbone and achieved promising results. U-net [13] performs very well in medical image processing and semantic segmentation. Our problem falls in the semantic segmentation category.

cs.CV↗

arXiv2019

Spline-based Interface Modeling and Optimization (SIMO) for Surface Tension and Contact Angle Measurements

Surface tension and contact angle measurements are fundamental characterization techniques relevant to thermal and fluidic applications. Drop shape analysis techniques for the measurement of interfacial tension are powerful, versatile and flexible. Here we develop a Spline-based Interface Modeling and Optimization (SIMO) tool for estimating the surface tension and the contact angle from the profiles of sessile and pendant drops of various sizes. The employed strategy models the profile using a vector parametrized cubic spline which is then evolved to the eventual equilibrium shape using a novel thermodynamic free-energy minimization-based iterative algorithm. We perform experiments to show that in comparison, the typical fitting-based techniques are very sensitive to errors due to image acquisition, digitization and edge detection, and do not predict the correct surface tension and the contact angle values. We mimic these errors in theoretical drop profiles by applying the Gaussian noise and the smoothing filters. We then demonstrate that our optimization algorithm can even drive such inaccurate digitized profiles to the minimum energy equilibrium shape for the precise estimation of the surface tension and the contact angle values. We compare our scheme with software tools available in public domain to characterize the accuracy and the precision of SIMO.

physics.flu-dyn↗