arXiv subjects

N. M. Anoop Krishnan

Publications and source records attributed to N. M. Anoop Krishnan.

At least 37 records · Page 2Linked to original sources

arXiv2025

Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials

Universal Machine Learning Interactomic Potentials (MLIPs) enable accelerated simulations for materials discovery. However, current research efforts fail to impactfully utilize MLIPs due to: 1. Overreliance on Density Functional Theory (DFT) for MLIP training data creation; 2. MLIPs' inability to reliably and accurately perform large-scale molecular dynamics (MD) simulations for diverse materials; 3. Limited understanding of MLIPs' underlying capabilities. To address these shortcomings, we aargue that MLIP research efforts should prioritize: 1. Employing more accurate simulation methods for large-scale MLIP training data creation (e.g. Coupled Cluster Theory) that cover a wide range of materials design spaces; 2. Creating MLIP metrology tools that leverage large-scale benchmarking, visualization, and interpretability analyses to provide a deeper understanding of MLIPs' inner workings; 3. Developing computationally efficient MLIPs to execute MD simulations that accurately model a broad set of materials properties. Together, these interdisciplinary research directions can help further the real-world application of MLIPs to accurately model complex materials at device scale.

cond-mat.mtrl-sci↗

arXiv2025

Foundational Large Language Models for Materials Research

Materials discovery and development are critical for addressing global challenges. Yet, the exponential growth in materials science literature comprising vast amounts of textual data has created significant bottlenecks in knowledge extraction, synthesis, and scientific reasoning. Large Language Models (LLMs) offer unprecedented opportunities to accelerate materials research through automated analysis and prediction. Still, their effective deployment requires domain-specific adaptation for understanding and solving domain-relevant tasks. Here, we present LLaMat, a family of foundational models for materials science developed through continued pretraining of LLaMA models on an extensive corpus of materials literature and crystallographic data. Through systematic evaluation, we demonstrate that LLaMat excels in materials-specific NLP and structured information extraction while maintaining general linguistic capabilities. The specialized LLaMat-CIF variant demonstrates unprecedented capabilities in crystal structure generation, predicting stable crystals with high coverage across the periodic table. Intriguingly, despite LLaMA-3's superior performance in comparison to LLaMA-2, we observe that LLaMat-2 demonstrates unexpectedly enhanced domain-specific performance across diverse materials science tasks, including structured information extraction from text and tables, more particularly in crystal structure generation, a potential adaptation rigidity in overtrained LLMs. Altogether, the present work demonstrates the effectiveness of domain adaptation towards developing practically deployable LLM copilots for materials research. Beyond materials science, our findings reveal important considerations for domain adaptation of LLMs, such as model selection, training methodology, and domain-specific performance, which may influence the development of specialized scientific AI systems.

cond-mat.mtrl-sci↗

arXiv2025

CoNOAir: A Neural Operator for Forecasting Carbon Monoxide Evolution in Cities

Carbon Monoxide (CO) is a dominant pollutant in urban areas due to the energy generation from fossil fuels for industry, automobile, and domestic requirements. Forecasting the evolution of CO in real-time can enable the deployment of effective early warning systems and intervention strategies. However, the computational cost associated with the physics and chemistry-based simulation makes it prohibitive to implement such a model at the city and country scale. To address this challenge, here, we present a machine learning model based on neural operator, namely, Complex Neural Operator for Air Quality (CoNOAir), that can effectively forecast CO concentrations. We demonstrate this by developing a country-level model for short-term (hourly) and long-term (72-hour) forecasts of CO concentrations. Our model outperforms state-of-the-art models such as Fourier neural operators (FNO) and provides reliable predictions for both short and long-term forecasts. We further analyse the capability of the model to capture extreme events and generate forecasts in urban cities in India. Interestingly, we observe that the model predicts the next hour CO concentrations with R2 values greater than 0.95 for all the cities considered. The deployment of such a model can greatly assist the governing bodies to provide early warning, plan intervention strategies, and develop effective strategies by considering several what-if scenarios. Altogether, the present approach could provide a fillip to real-time predictions of CO pollution in urban cities.

cs.LG↗

arXiv2024

Industrial-scale Prediction of Cement Clinker Phases using Machine Learning

Cement production, exceeding 4.1 billion tonnes and contributing 2.4 tonnes of CO2 annually, faces critical challenges in quality control and process optimization. While traditional process models for cement manufacturing are confined to steady-state conditions with limited predictive capability for mineralogical phases, modern plants operate under dynamic conditions that demand real-time quality assessment. Here, exploiting a comprehensive two-year operational dataset from an industrial cement plant, we present a machine learning framework that accurately predicts clinker mineralogy from process data. Our model achieves unprecedented prediction accuracy for major clinker phases while requiring minimal input parameters, demonstrating robust performance under varying operating conditions. Through post-hoc explainable algorithms, we interpret the hierarchical relationships between clinker oxides and phase formation, providing insights into the functioning of an otherwise black-box model. This digital twin framework can potentially enable real-time optimization of cement production, thereby providing a route toward reducing material waste and ensuring quality while reducing the associated emissions under real plant conditions. Our approach represents a significant advancement in industrial process control, offering a scalable solution for sustainable cement manufacturing.

cs.LG↗

arXiv2024

Force field optimization by end-to-end differentiable atomistic simulation

The accuracy of atomistic simulations depends on the precision of force fields. Traditional numerical methods often struggle to optimize the empirical force field parameters for reproducing target properties. Recent approaches rely on training these force fields based on forces and energies from first-principle simulations. However, it is unclear whether these approaches will enable capturing complex material responses such as vibrational, or elastic properties. To this extent, we introduce a framework, employing inner loop simulations and outer loop optimization, that exploits automatic differentiation for both property prediction and force-field optimization by computing gradients of the simulation analytically. We demonstrate the approach by optimizing classical Stillinger-Weber and EDIP potentials for silicon systems to reproduce the elastic constants, vibrational density of states, and phonon dispersion. We also demonstrate how a machine-learned potential can be fine-tuned using automatic differentiation to reproduce any target property such as radial distribution functions. Interestingly, the resulting force field exhibits improved accuracy and generalizability to unseen temperatures than those fine-tuned on energies and forces. Finally, we demonstrate the extension of the approach to optimize the force fields towards multiple target properties. Altogether, differentiable simulations, through the analytical computation of their gradients, offer a powerful tool for both theoretical exploration and practical applications toward understanding physical systems and materials.

cond-mat.mtrl-sci↗

arXiv2024

Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems

Neural networks with physics based inductive biases such as Lagrangian neural networks (LNN), and Hamiltonian neural networks (HNN) learn the dynamics of physical systems by encoding strong inductive biases. Alternatively, Neural ODEs with appropriate inductive biases have also been shown to give similar performances. However, these models, when applied to particle based systems, are transductive in nature and hence, do not generalize to large system sizes. In this paper, we present a graph based neural ODE, GNODE, to learn the time evolution of dynamical systems. Further, we carefully analyse the role of different inductive biases on the performance of GNODE. We show that, similar to LNN and HNN, encoding the constraints explicitly can significantly improve the training efficiency and performance of GNODE significantly. Our experiments also assess the value of additional inductive biases, such as Newtons third law, on the final performance of the model. We demonstrate that inducing these biases can enhance the performance of model by orders of magnitude in terms of both energy violation and rollout error. Interestingly, we observe that the GNODE trained with the most effective inductive biases, namely MCGNODE, outperforms the graph versions of LNN and HNN, namely, Lagrangian graph networks (LGN) and Hamiltonian graph networks (HGN) in terms of energy violation error by approx 4 orders of magnitude for a pendulum system, and approx 2 orders of magnitude for spring systems. These results suggest that competitive performances with energy conserving neural networks can be obtained for NODE based systems by inducing appropriate inductive biases.

cs.LG↗

arXiv2024

TAGMol: Target-Aware Gradient-guided Molecule Generation

3D generative models have shown significant promise in structure-based drug design (SBDD), particularly in discovering ligands tailored to specific target binding sites. Existing algorithms often focus primarily on ligand-target binding, characterized by binding affinity. Moreover, models trained solely on target-ligand distribution may fall short in addressing the broader objectives of drug discovery, such as the development of novel ligands with desired properties like drug-likeness, and synthesizability, underscoring the multifaceted nature of the drug design process. To overcome these challenges, we decouple the problem into molecular generation and property prediction. The latter synergistically guides the diffusion sampling process, facilitating guided diffusion and resulting in the creation of meaningful molecules with the desired properties. We call this guided molecular generation process as TAGMol. Through experiments on benchmark datasets, TAGMol demonstrates superior performance compared to state-of-the-art baselines, achieving a 22% improvement in average Vina Score and yielding favorable outcomes in essential auxiliary properties. This establishes TAGMol as a comprehensive framework for drug generation.

q-bio.BM↗

arXiv2024

DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles

A crucial component in the curation of KB for a scientific domain (e.g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's published research articles. To facilitate research in this direction, we define a novel NLP task of extracting compositions of materials (e.g., glasses) from tables in materials science papers. The task involves solving several challenges in concert, such as tables that mention compositions have highly varying structures; text in captions and full paper needs to be incorporated along with data in tables; and regular languages for numbers, chemical compounds and composition expressions must be integrated into the model. We release a training dataset comprising 4,408 distantly supervised tables, along with 1,475 manually annotated dev and test tables. We also present a strong baseline DISCOMAT, that combines multiple graph neural networks with several task-specific regular expressions, features, and constraints. We show that DISCOMAT outperforms recent table processing architectures by significant margins.

cs.CL↗

arXiv2024

Disorder-induced enhancement of lithium-ion transport in solid-state electrolytes

Enhancing the ion conduction in solid electrolytes is critically important for the development of high-performance all-solid-state lithium-ion batteries (LIBs). Lithium thiophosphates are among the most promising solid electrolytes, as they exhibit superionic conductivity at room temperature. However, the lack of comprehensive understanding regarding their ion conduction mechanism, especially the effect of structural disorder on ionic conductivity, is a long-standing problem that limits further innovations of all-solid-state LIBs. Here, we address this challenge by establishing and employing a deep learning potential to simulate Li3PS4 electrolyte systems with varying levels of disorder. The results show that disorder-driven diffusion dynamics significantly enhances the room-temperature conductivity. We further establish bridges between dynamical characteristics, local structural features, and atomic rearrangements by applying a machine learning-based structure fingerprint termed "softness". This metric allows the classification of the disorder-induced "soft" hopping lithium ions. Our findings offer insights into ion conduction mechanisms in complex disordered structures, thereby contributing to the development of superior solid-state electrolytes for LIBs.

cond-mat.mtrl-sci↗

arXiv2023

MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models

Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Language models have demonstrated their capability to answer domain-specific questions and retrieve information from knowledge bases. However, there are no benchmark datasets in the materials domain that can evaluate the understanding of the key concepts by these language models. In this work, we curate a dataset of 650 challenging questions from the materials domain that require the knowledge and skills of a materials student who has cleared their undergraduate degree. We classify these questions based on their structure and the materials science domain-based subcategories. Further, we evaluate the performance of GPT-3.5 and GPT-4 models on solving these questions via zero-shot and chain of thought prompting. It is observed that GPT-4 gives the best performance (~62% accuracy) as compared to GPT-3.5. Interestingly, in contrast to the general observation, no significant improvement in accuracy is observed with the chain of thought prompting. To evaluate the limitations, we performed an error analysis, which revealed conceptual errors (~64%) as the major contributor compared to computational errors (~36%) towards the reduced performance of LLMs. We hope that the dataset and analysis performed in this work will promote further research in developing better materials science domain-specific LLMs and strategies for information extraction.

cs.CL↗

arXiv2023

Revealing the Predictive Power of Neural Operators for Strain Evolution in Digital Composites

The demand for high-performance materials, along with advanced synthesis technologies such as additive manufacturing and 3D printing, has spurred the development of hierarchical composites with superior properties. However, computational modelling of such composites using physics-based solvers, while enabling the discovery of optimal microstructures, have prohibitively high computational cost hindering their practical application. To this extent, we show that Neural Operators (NOs) can be used to learn and predict the strain evolution in 2D digital composites. Specifically, we consider three architectures, namely, Fourier NO (FNO), Wavelet NO (WNO), and Multi-wavelet NO (MWT). We demonstrate that by providing a few initial strain frames as input, NOs can accurately predict multiple future time steps in an extremely data-efficient fashion, especially WNO. Further, once trained, NOs forecast the strain trajectories for completely unseen boundary conditions. Among NOs, only FNO offers super-resolution capabilities for estimating strains at multiple length scales, which can provide higher material and pixel-wise resolution. We also show that NOs can generalize to arbitrary geometries with finer domain resolution without the need for additional training. Based on all the results presented, we note that the FNO exhibits the best performance among the NOs, while also giving minimum inference time that is almost three orders magnitude lower than the conventional finite element solutions. Thus, FNOs can be used as a surrogate for accelerated simulation of the strain evolution in complex microstructures toward designing the next composite materials.

cond-mat.mtrl-sci↗

arXiv2023

Graph Neural Stochastic Differential Equations for Learning Brownian Dynamics

Neural networks (NNs) that exploit strong inductive biases based on physical laws and symmetries have shown remarkable success in learning the dynamics of physical systems directly from their trajectory. However, these works focus only on the systems that follow deterministic dynamics, for instance, Newtonian or Hamiltonian dynamics. Here, we propose a framework, namely Brownian graph neural networks (BROGNET), combining stochastic differential equations (SDEs) and GNNs to learn Brownian dynamics directly from the trajectory. We theoretically show that BROGNET conserves the linear momentum of the system, which in turn, provides superior performance on learning dynamics as revealed empirically. We demonstrate this approach on several systems, namely, linear spring, linear spring with binary particle types, and non-linear spring systems, all following Brownian dynamics at finite temperatures. We show that BROGNET significantly outperforms proposed baselines across all the benchmarked Brownian systems. In addition, we demonstrate zero-shot generalizability of BROGNET to simulate unseen system sizes that are two orders of magnitude larger and to different temperatures than those used during training. Altogether, our study contributes to advancing the understanding of the intricate dynamics of Brownian motion and demonstrates the effectiveness of graph neural networks in modeling such complex systems.

cs.LG↗

arXiv2023

StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes

Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, we present a graph reinforcement learning approach, StriderNET, that learns a policy to displace the atoms towards low energy configurations. We evaluate the performance of StriderNET on three complex atomic systems, namely, binary Lennard-Jones particles, calcium silicate hydrates gel, and disordered silicon. We show that StriderNET outperforms all classical optimization algorithms and enables the discovery of a lower energy minimum. In addition, StriderNET exhibits a higher rate of reaching minima with energies, as confirmed by the average over multiple realizations. Finally, we show that StriderNET exhibits inductivity to unseen system sizes that are an order of magnitude different from the training system.

cs.LG↗

arXiv2023

Glass Hardness: Predicting Composition and Load Effects via Symbolic Reasoning-Informed Machine Learning

Glass hardness varies in a non-linear fashion with the chemical composition and applied load, a phenomenon known as the indentation size effect (ISE), which is challenging to predict quantitatively. Here, using a curated dataset of over approx. 3000 inorganic glasses from the literature comprising the composition, indentation load, and hardness, we develop machine learning (ML) models to predict the composition and load dependence of Vickers hardness. Interestingly, when tested on new glass compositions unseen during the training, the standard data-driven ML model failed to capture the ISE. To address this gap, we combined an empirical expression (Bernhardt law) to describe the ISE with ML to develop a framework that incorporates the symbolic law representing the domain reasoning in ML, namely Symbolic Reasoning-Informed ML Procedure (SRIMP). We show that the resulting SRIMP outperforms the data-driven ML model in predicting the ISE. Finally, we interpret the SRIMP model to understand the contribution of the glass network formers and modifiers toward composition and load-dependent (ISE) and load-independent hardness. The deconvolution of the hardness into load-dependent and load-independent terms paves the way toward a holistic understanding of composition and ISE in glasses, enabling the accelerated discovery of new glass compositions with targeted hardness.

cond-mat.mtrl-sci↗

arXiv2022

Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network

Lagrangian and Hamiltonian neural networks (LNNs and HNNs, respectively) encode strong inductive biases that allow them to outperform other models of physical systems significantly. However, these models have, thus far, mostly been limited to simple systems such as pendulums and springs or a single rigid body such as a gyroscope or a rigid rotor. Here, we present a Lagrangian graph neural network (LGNN) that can learn the dynamics of articulated rigid bodies by exploiting their topology. We demonstrate the performance of LGNN by learning the dynamics of ropes, chains, and trusses with the bars modeled as rigid bodies. LGNN also exhibits generalizability -- LGNN trained on chains with a few segments exhibits generalizability to simulate a chain with large number of links and arbitrary link length. We also show that the LGNN can simulate unseen hybrid systems including bars and chains, on which they have not been trained on. Specifically, we show that the LGNN can be used to model the dynamics of complex real-world structures such as the stability of tensegrity structures. Finally, we discuss the non-diagonal nature of the mass matrix and its ability to generalize in complex systems.

cs.LG↗

arXiv2022

Cementron: Machine Learning the Constituent Phases in Cement Clinker from Optical Images

Cement is the most used construction material. The performance of cement hydrate depends on the constituent phases, viz. alite, belite, aluminate, and ferrites present in the cement clinker, both qualitatively and quantitatively. Traditionally, clinker phases are analyzed from optical images relying on a domain expert and simple image processing techniques. However, the non-uniformity of the images, variations in the geometry and size of the phases, and variabilities in the experimental approaches and imaging methods make it challenging to obtain the phases. Here, we present a machine learning (ML) approach to detect clinker microstructure phases automatically. To this extent, we create the first annotated dataset of cement clinker by segmenting alite and belite particles. Further, we use supervised ML methods to train models for identifying alite and belite regions. Specifically, we finetune the image detection and segmentation model Detectron-2 on the cement microstructure to develop a model for detecting the cement phases, namely, Cementron. We demonstrate that Cementron, trained only on literature data, works remarkably well on new images obtained from our experiments, demonstrating its generalizability. We make Cementron available for public use.

cs.CV↗

arXiv2022

Accelerated Design of Chalcogenide Glasses through Interpretable Machine Learning for Composition Property Relationships

Chalcogenide glasses possess several outstanding properties that enable several ground breaking applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite the ubiquitous usage of these glasses, the composition property relationships in these materials remain poorly understood. Here, we use a large experimental dataset comprising approx 24000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Youngs modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models, by far, are the largest for chalcogenide glasses. Further, we use SHAP, a game theory based algorithm, to interpret the output of machine learning algorithms by analyzing the contributions of each element towards the models prediction of a property. This provides a powerful tool for experimentalists to interpret the models prediction and hence design new glass compositions with targeted properties. Finally, using the models, we develop several glass selection charts that can potentially aid in the rational design of novel chalcogenide glasses for various applications.

cond-mat.mtrl-sci↗

arXiv2022

Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors

Due to their disordered structure, glasses present a unique challenge in predicting the composition-property relationships. Recently, several attempts have been made to predict the glass properties using machine learning techniques. However, these techniques have the limitations, namely, (i) predictions are limited to the components that are present in the original dataset, and (ii) predictions towards the extreme values of the properties, important regions for new materials discovery, are not very reliable due to the sparse datapoints in this region. To address these challenges, here we present a low complexity neural network (LCNN) that provides improved performance in predicting the properties of oxide glasses. In addition, we combine the LCNN with physical and chemical descriptors that allow the development of universal models that can provide predictions for components beyond the training set. By training on a large dataset (~50000) of glass components, we show the LCNN outperforms state-of-the-art algorithms such as XGBoost. In addition, we interpret the LCNN models using Shapely additive explanations to gain insights into the role played by the descriptors in governing the property. Finally, we demonstrate the universality of the LCNN models by predicting the properties for glasses with new components that were not present in the original training set. Altogether, the present approach provides a promising direction towards accelerated discovery of novel glass compositions.

cond-mat.mtrl-sci↗