arXiv subjects

Venkatasubramanian Viswanathan

Publications and source records attributed to Venkatasubramanian Viswanathan.

At least 19 recordsLinked to original sources

arXiv2026

Differentiable Solvation Shell Model for Rational Electrolyte Design

Tailoring Li+ solvation structures has emerged as a promising design principle across multiple Li metal battery (LMB) electrolytes, with localized high concentration electrolytes (LHCE) emerging as a leading candidate. However, rational design of these electrolytes remains limited by a poor quantitative understanding of how molecular properties govern Li+ solvation shell composition. Here we introduce a mean field modeling framework, built on an Ising model, that predicts solvation shell composition from donor number (DN), acceptor number (AN), molar ratio, and molecular size. This framework is end-to-end differentiable, which enables parameterization directly from molecular dynamics (MD) solvation structures via gradient-based optimization. Focusing on LHCE, the model achieves 10.7% RMSE and R2=0.87 for shell composition, 2.3% RMSE on free solvent ratio, and further reproduces solvation trends in real LHCE electrolytes, at a fraction of MD's cost. Our model also shows good generalizability on other electrolyte systems in addition to LHCE. Analysis of its interaction terms shows that DN dominates Li+ solvation energetics, providing a thermodynamic basis for empirical DN-based design rules. We further demonstrate the model's design utility on the LiTFSI/tetraglyme (G4) system absent from training. The model identifies fluorobenzene (FB) as a promising diluent and predicts a salt-concentration window with anion-rich solvation shells and low free solvent, favorable for stable anion-derived SEIs and high oxidative stability, respectively. This prediction is validated by higher-fidelity MD. This work establishes an interpretable differentiable framework for predicting Li+ solvation shell composition, with potential to extend to other electrolyte classes.

physics.chem-ph↗

arXiv2026

DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation

Large language model (LLM) agents can execute long-horizon scientific workflows, but their numerical outputs are difficult to trust: agents lose context, game verification checks, and can produce large volumes of plausible yet invalid results. We introduce the DFT-based Research Engine for Agentic Materials Simulation (DREAMS), a hierarchical multi-agent framework for density functional theory (DFT) built around a multi-tier safety guard. The guard applies deterministic checks wherever explicit criteria exist and scoped LLM judgment elsewhere, evaluating one parameter at a time and tracing every value to its registered source. Verification extends from tool-call time, where fabricated, laundered, or unsourced values are rejected before entering the workflow, to report time, where a judge audits the full provenance graph behind every claim; a shared canvas preserves information integrity across hundreds of steps. DREAMS achieves average errors below 1% on the Sol27LC lattice-constant benchmark, reproduces expert-level adsorption-energy differences on the CO/Pt(111) puzzle, and quantifies functional-driven uncertainty with Bayesian ensemble sampling, confirming the face-centered-cubic (FCC) site preference at the generalized gradient approximation (GGA) level. Compared with its unguarded counterpart, which reached a nearly correct answer while only 81% of its essential steps succeeded, the guarded system verifies every essential step at approximately 13 times the input tokens; verification layers can be disabled individually to balance trustworthiness against cost, and the tuned judge rules transfer across five judge models. DREAMS operates at an enhanced L2 (L2+) automation level and demonstrates capabilities approaching L3 automation, providing a path toward trustworthy, high-throughput autonomous materials simulation.

cs.AI↗

arXiv2026

Foundation Models for Discovery and Exploration in Chemical Space

Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing computational and experimental approaches lack the scalability required to navigate chemical space efficiently. Scientific foundation models trained on large unlabelled datasets offer a path towards navigating chemical space across application domains. Here, we develop MIST, a family of molecular foundation models with up to an order of magnitude more parameters and data than prior works. Trained using a novel tokenizer, Smirk, which comprehensively captures nuclear, electronic, and geometric information, MIST learns a diverse range of molecules. MIST models have been fine-tuned to predict more than 400 structure-property relationships and have been shown to match or exceed state-of-the-art performance across diverse benchmarks, from physiology to electrochemistry. We demonstrate the ability of these models to solve real-world problems across chemical space from multiobjective electrolyte solvent screening to stereochemical reasoning for organometallics and mixture property prediction. The clearest demonstration of a foundation model is its ability to solve problems that were neither explicit targets of training nor central to the intentions of its developers. We identify olfactory perception mapping as such a problem, and show that MIST accurately predicted scent profiles and learned a hierarchical representation of olfactory space consistent with hyperbolic geometry. We formulated hyperparameter aware Bayesian neural scaling laws which eliminate the need for hyperparameter sweeps at every scale, making training large compute-optimal models feasible on a limited compute budget. The methods and findings presented here represent a significant step towards accelerating materials discovery, design, and optimization using foundation models.

physics.chem-ph↗

arXiv2025

Stability and Structure of Binary Metal Hydrides under Pressure, Electrochemical Potential and Combined Pressure-Electrochemistry

Metal hydrides can be tuned to have a diverse range of properties and find applications in hydrogen storage and superconductivity. Finding methods to control the synthesis of hydrides can open up new pathways to unlock novel hydride compounds with desired properties. We introduced the idea of utilizing electrochemistry as an additional tuning knob and in this work, we study the synthesis of binary metal hydrides using high pressure, electrochemistry and combined pressure-electrochemistry. Using density functional theory calculations, we predict the phase diagrams of selected transition metal hydrides under combined pressure and electrochemical conditions and demonstrate that the approach agrees well with experimental observations for most phases. We use the phase diagrams to determine trends in the stability of binary metal hydrides of scandium, yttrium and lanthanum as well as discuss the hydrogen-metal charge transfer at different pressures. Furthermore, we predict a diverse range of vanadium and chromium hydrides that could potentially be synthesized using pressure electrochemistry. These predictions highlight the value of exploring pressure-electrochemistry as a pathway to novel hydride synthesis.

cond-mat.mtrl-sci↗

arXiv2025

Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics

Differentiable physical simulators are proving to be valuable tools for developing data-driven models for computational fluid dynamics (CFD). In particular, these simulators enable end-to-end training of machine learning (ML) models embedded within CFD solvers. This paradigm enables novel algorithms which combine the generalization power and low cost of physics-based simulations with the flexibility and automation of deep learning methods. In this study, we introduce a framework for embedding deep learning models within a finite element solver for incompressible Navier-Stokes equations, specifically applying this approach to learn a subgrid-scale (SGS) closure with a graph neural network (GNN). We first demonstrate the feasibility of the approach on flow over a two-dimensional backward-facing step, using it as a proof of concept to show that solver-consistent training produces stable and physically meaningful closures. Then, we extend this to a turbulent flow over a three-dimensional backward-facing step. In this setting, the GNN-based closure not only attains low prediction errors, but also recovers key turbulence statistics and preserves multiscale turbulent structures. We further demonstrate that the closure can be identified in data-limited learning scenarios as well. Overall, the proposed end-to-end learning paradigm offers a viable pathway toward physically consistent and generalizable data-driven SGS modeling on complex and unstructured domains.

physics.flu-dyn↗

arXiv2025

Differentiable Electrochemistry: A paradigm for uncovering hidden physical phenomena in electrochemical systems

Despite the long history of electrochemistry, there is a lack of quantitative algorithms that rigorously correlate experiment with theory. Electrochemical modeling has had advanced across empirical, analytical, numerical, and data-driven paradigms. Data-driven machine learning and physics based electrochemical modeling, however, have not been explicitly linked. Here we introduce Differentiable Electrochemistry, a mew paradigm in electrochemical modeling that integrates thermodynamics, kinetics and mass transport with differentiable programming enabled by automatic differentiation. By making the entire electrochemical simulation end-to-end differentiable, this framework enables gradient-based optimization for mechanistic discovery from experimental and simulation data, achieving approximately one to two orders of improvement over gradient-free methods. We develop a rich repository of differentiable simulators across diverse mechanisms, and apply Differentiable Electrochemistry to bottleneck problems in kinetic analysis. Specifically, Differentiable Electrochemistry advances beyond Tafel and Nicholson method by removing several limitations including Tafel region selection, and identifies the electron transfer mechanism in Li metal electrodeposition/stripping by parameterizing the full Marcus-Hush-Chidsey formalism. In addition, Differentiable Electrochemistry interprets Operando X-ray measurements in concentrated electrolyte by coupling concentration and velocity theories. This framework resolves ambiguity when multiple electrochemical theories intertwine, and establishes a physics-consistent and data-efficient foundation for predictive electrochemical modeling.

physics.chem-ph↗

arXiv2025

Fundamental Limits of Dissociative Electrochemical Ammonia Synthesis via Electrodeposited Metals

Electrochemical ammonia synthesis via lithium-mediated nitrogen dissociation has demonstrated exceptional Faradaic efficiency at ambient conditions, but its viability is limited by a high energy cost of ~9.12 eV per NH3 via lithium electrodeposition. Here, we establish the thermodynamic limits for dissociative nitrogen reduction using elemental metals by decomposing the process into three steps: metal deposition, nitridation, and protonation. We derive energetic constraints that any viable mediator must satisfy and show that highly reducing metals impose significant energetic penalties. To reduce this cost, we explore solvent tuning and bimetallic alloy strategies that shift deposition potentials without compromising nitridation spontaneity. Our results offer design principles for lowering the energy input of dissociative nitrogen reduction while maintaining its selectivity advantage over associative routes.

physics.chem-ph↗

arXiv2025

Tokenization for Molecular Foundation Models

Text-based foundation models have become an important part of scientific discovery, with molecular foundation models accelerating advancements in material science and molecular design.However, existing models are constrained by closed-vocabulary tokenizers that capture only a fraction of molecular space. In this work, we systematically evaluate 34 tokenizers, including 19 chemistry-specific ones, and reveal significant gaps in their coverage of the SMILES molecular representation. To assess the impact of tokenizer choice, we introduce n-gram language models as a low-cost proxy and validate their effectiveness by pretraining and finetuning 18 RoBERTa-style encoders for molecular property prediction. To overcome the limitations of existing tokenizers, we propose two new tokenizers -- Smirk and Smirk-GPE -- with full coverage of the OpenSMILES specification. The proposed tokenizers systematically integrate nuclear, electronic, and geometric degrees of freedom; facilitating applications in pharmacology, agriculture, biology, and energy storage. Our results highlight the need for open-vocabulary modeling and chemically diverse benchmarks in cheminformatics.

cs.LG↗

arXiv2025

CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning

The prediction of crystal properties is essential for understanding structure-property relationships and accelerating the discovery of functional materials. However, conventional approaches relying on experimental measurements or density functional theory (DFT) calculations are often resource-intensive, limiting their scalability. Machine learning (ML) models offer a promising alternative by learning complex structure-property relationships from data, enabling faster predictions. Yet, existing ML models often rely on labeled data, adopt representations that poorly capture essential structural characteristics, and lack integration with physical principles--factors that limit their generalizability and interpretability. Here, we introduce CLOUD (Crystal Language mOdel for Unified and Differentiable materials modeling), a transformer-based framework trained on a novel Symmetry-Consistent Ordered Parameter Encoding (SCOPE) that encodes crystal symmetry, Wyckoff positions, and composition in a compact, coordinate-free string representation. Pre-trained on over six million crystal structures, CLOUD is fine-tuned on multiple downstream tasks and achieves competitive performance in predicting a wide range of material properties, demonstrating strong scaling performance. Furthermore, as proof of concept of differentiable materials modeling, CLOUD is applied to predict the phonon internal energy and heat capacity, which integrates the Debye model to preserve thermodynamic consistency. The CLOUD-DEBYE framework enforces thermodynamic consistency and enables temperature-dependent property prediction without requiring additional data. These results demonstrate the potential of CLOUD as a scalable and physics-informed foundation model for crystalline materials, unifying symmetry-consistent representations with physically grounded learning for property prediction and materials discovery.

cond-mat.mtrl-sci↗

arXiv2025

Learning second-order TVD flux limiters using differentiable solvers

This paper presents a data-driven framework for learning optimal second-order total variation diminishing (TVD) flux limiters via differentiable simulations. In our fully differentiable finite volume solvers, the limiter functions are replaced by neural networks. By representing the limiter as a pointwise convex linear combination of the Minmod and Superbee limiters, we enforce both second-order accuracy and TVD constraints at all stages of training. Our approach leverages gradient-based optimization through automatic differentiation, allowing a direct backpropagation of errors from numerical solutions to the limiter parameters. We demonstrate the effectiveness of this method on various hyperbolic conservation laws, including the linear advection equation, the Burgers' equation, and the one-dimensional Euler equations. Remarkably, a limiter trained solely on linear advection exhibits strong generalizability, surpassing the accuracy of most classical flux limiters across a range of problems with shocks and discontinuities. The learned flux limiters can be readily integrated into existing computational fluid dynamics codes, and the proposed methodology also offers a flexible pathway to systematically develop and optimize flux limiters for complex flow problems.

physics.flu-dyn↗

arXiv2024

Excess Density as a Descriptor for Electrolyte Solvent Design

Electrolytes mediate interactions between the cathode and anode and determine performance characteristics of batteries. Mixtures of multiple solvents are often used in electrolytes to achieve desired properties, such as viscosity, dielectric constant, boiling point, and melting point. Conventionally, multi-component electrolyte properties are approximated with linear mixing, but in practice, significant deviations are observed. Excess quantities can provide insights into the molecular behavior of the mixture and could form the basis for designing high-performance electrolytes. Here we investigate the excess density of commonly used Li-ion battery solvents such as cyclic carbonates, linear carbonates, ethers, and nitriles with molecular dynamics simulations. We additionally investigate electrolytes consisting of these solvents and a salt. The results smoothly vary with mole percent and are fit to permutation-invariant Redlich-Kister polynomials. Mixtures of similar solvents, such as cyclic-cyclic carbonate mixtures, tend to have excess properties that are lower in magnitude compared to mixtures of dissimilar substances, such as carbonate-nitrile mixtures. We perform experimental testing using our robotic test stand, Clio, to provide validation to the observed simulation trends. We quantify the structure similarity using SOAP fingerprints to create a descriptor for excess density, enabling the design of electrolyte properties. To a first approximation, this will allow us to estimate the deviation of a mixture from ideal behavior based solely upon the structural dissimilarity of the components.

physics.chem-ph↗

arXiv2024

Controlling moving interfaces in solid state batteries

Safe, all-solid-state lithium metal batteries enable high energy density applications, but suffer from instabilities during operation that lead to rough interfaces between the metal and electrolyte and subsequently cause void formation and dendrite growth that degrades performance and safety. Inspired by the morphogenetic control of thin lamina such as tree leaves that robustly grow into flat shapes -- we propose a range of approaches to control lithium metal stripping and plating. To guide discovery of materials that will implement these feedback mechanisms, we develop a reduced order model that captures couplings between mechanics, interface growth, temperature, and electrochemical variables. We find that long-range feedback is required to achieve true interface stability, while approaches based on local feedback always eventually grow into rough interfaces. All together, our study provides the beginning of a practical framework for analyzing and designing stable electrochemical interfaces in terms of the mechanical properties and the physical chemistry that underlie their dynamics.

cond-mat.mtrl-sci↗

arXiv2024

Self-supervised Pretraining for Partial Differential Equations

In this work, we describe a novel approach to building a neural PDE solver leveraging recent advances in transformer based neural network architectures. Our model can provide solutions for different values of PDE parameters without any need for retraining the network. The training is carried out in a self-supervised manner, similar to pretraining approaches applied in language and vision tasks. We hypothesize that the model is in effect learning a family of operators (for multiple parameters) mapping the initial condition to the solution of the PDE at any future time step t. We compare this approach with the Fourier Neural Operator (FNO), and demonstrate that it can generalize over the space of PDE parameters, despite having a higher prediction error for individual parameter values compared to the FNO. We show that performance on a specific parameter can be improved by finetuning the model with very small amounts of data. We also demonstrate that the model scales with data as well as model size.

cs.LG↗

arXiv2024

Vibrational Entropy and Free Energy of Solid Lithium using Covariance of Atomic Displacements Enabled by Machine Learning

Vibrational properties of solids are key to determining stability, response and functionality. However, they are challenging to computationally predict at Ab-Initio accuracy, even for elemental systems. Ab-Initio methods for modeling atomic interactions are limited in the system sizes and simulation times that can be achieved. Due to these limitations, Machine Learning Interatomic Potentials (MLIPs) are gaining popularity and success as a faster, more scalable approach for modeling atomic interactions, potentially at Ab-Initio accuracy. Even with faster potentials, methodologies for predicting entropy, free energy and vibrational properties vary in accuracy, cost and difficulty to implement. Using the Covariance of Atomic Displacements (CAD) to predict entropy, free energy and finite-temperature phonon dispersions is a promising approach but thorough benchmarking has been hampered by the cost of Ab-Initio methods for sampling. In this work, we use a MLIP and the CAD to characterize the convergence of the predicted properties and determine optimal sampling strategies. We focus on solid lithium at zero pressure, showing that the MLIP-CAD approach reproduces experimental entropy, phonon dispersions and the martensitic transition while also comparing to more established methods.

cond-mat.mtrl-sci↗

arXiv2024

Differentiable Turbulence: Closure as a partial differential equation constrained optimization

Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an end-to-end differentiable solver is used in combination with physics-inspired choices of deep learning architectures to learn highly effective and versatile SGS models for two-dimensional turbulent flow. We perform an in-depth analysis of the inductive biases in the chosen architectures, finding that the inclusion of small-scale non-local features is most critical to effective SGS modeling, while large-scale features can improve pointwise accuracy of the \textit{a-posteriori} solution field. The velocity gradient tensor on the LES grid can be mapped directly to the SGS stress via decomposition of the inputs and outputs into isotropic, deviatoric, and anti-symmetric components. We see that the model can generalize to a variety of flow configurations, including higher and lower Reynolds numbers and different forcing conditions. We show that the differentiable physics paradigm is more successful than offline, \textit{a-priori} learning, and that hybrid solver-in-the-loop approaches to deep learning offer an ideal balance between computational efficiency, accuracy, and generalization. Our experiments provide physics-based recommendations for deep-learning based SGS modeling for generalizable closure modeling of turbulence.

physics.flu-dyn↗

arXiv2023

Differentiable Modeling and Optimization of Battery Electrolyte Mixtures Using Geometric Deep Learning

Electrolytes play a critical role in designing next-generation battery systems, by allowing efficient ion transfer, preventing charge transfer, and stabilizing electrode-electrolyte interfaces. In this work, we develop a differentiable geometric deep learning (GDL) model for chemical mixtures, DiffMix, which is applied in guiding robotic experimentation and optimization towards fast-charging battery electrolytes. In particular, we extend mixture thermodynamic and transport laws by creating GDL-learnable physical coefficients. We evaluate our model with mixture thermodynamics and ion transport properties, where we show improved prediction accuracy and model robustness of DiffMix than its purely data-driven variants. Furthermore, with a robotic experimentation setup, Clio, we improve ionic conductivity of electrolytes by over 18.8% within 10 experimental steps, via differentiable optimization built on DiffMix gradients. By combining GDL, mixture physics laws, and robotic experimentation, DiffMix expands the predictive modeling methods for chemical mixtures and enables efficient optimization in large chemical spaces.

physics.chem-ph↗

arXiv2023

Statistical methods for resolving poor uncertainty quantification in machine learning interatomic potentials

Machine learning interatomic potentials (MLIPs) are promising surrogates for quantum mechanics evaluations in ab-initio molecular dynamics simulations due to their ability to reproduce the energy and force landscape within chemical accuracy at four orders of magnitude less cost. While developing uncertainty quantification (UQ) tools for MLIPs is critical to build production MLIP datasets using active learning, only limited progress has been made and the most robust method, ensembling, still shows low correlation between high error and high uncertainty predictions. Here we develop a rigorous method rooted in statistics for determining an error cutoff that distinguishes regions of high and low UQ performance. The statistical cutoff illuminates that a main cause of the poor UQ performance is due to the machine learning model already describing the entire dataset and not having any datapoints with error greater than the statistical error distribution. Second, we extend the statistical analysis to create an interpretable connection between the error and uncertainty distributions to predict an uncertainty cutoff separating high and low errors. We showcase the statistical cutoff in active learning benchmarks on two datasets of varying chemical complexity for three common UQ methods: ensembling, sparse Gaussian processes, and latent distance metrics and compare them to the true error and random sampling, showing that the statistical cutoff is generalizable to a variety of different UQ methods and protocols and performs similarly to using the true error. Importantly, we conclude that utilizing this uncertainty cutoff enables using significantly lower cost uncertainty quantification tools such as sparse gaussian processes and latent distances compared to ensembling approaches for generating MLIP datasets at a fraction of the cost.

cond-mat.mtrl-sci↗

arXiv2023

Twisto-electrochemical activity volcanoes in Trilayer Graphene

In this work, we develop a twist-dependent electrochemical activity map, combining a tight-binding electronic structure model with modified Marcus-Hush-Chidsey kinetics in trilayer graphene. We identify a counterintuitive rate enhancement region spanning the magic angle curve and incommensurate twists of the system geometry. We find a broad activity peak with a ruthenium hexamine redox couple in regions corresponding to both magic angles and incommensurate angles, a result qualitatively distinct from the twisted bilayer case. Flat bands and incommensurability offer new avenues for reaction rate enhancements in electrochemical transformations.

cond-mat.mes-hall↗