arXiv subjects

Huan Tran

Publications and source records attributed to Huan Tran.

At least 19 recordsLinked to original sources

arXiv2026

Accelerated design of proton exchange membranes for green hydrogen production with artificial intelligence

Water electrolysis is an eco-friendly method for hydrogen production that has reached significant levels of technological maturity. Among commercialized water-electrolysis technologies, proton-exchange membrane electrolyzers offer high current density, fast dynamic response, and compact system design, among other advantages. On the other hand, managing their high capital cost and the ``forever-chemistry'' nature of Nafion, a perfluorinated proton-exchange membrane widely used in such devices, remains a major challenge. Searches for fluorine-free replacements for Nafion, pursued largely through physical experimentation, have been active for decades with limited success. In this work, we develop and demonstrate an AI-based strategy for designing proton-exchange membranes for electrolyzers. Two key components of this strategy are an implementation of the virtual forward-synthesis approach and a set of machine-learning predictive models for essential application-inspired membrane properties; the former generates a vast space of millions of synthesizable polymers, which are then evaluated and screened by the latter. The strategy is validated against experimental data for known membranes and then applied to design over 1700 synthesizable candidates. This article concludes with a forward-looking vision in which the strategy could be elevated into an interactive and iterative scheme that is based on large language models to facilitate materials design in multiple ways.

cond-mat.soft↗

arXiv2025

AI-Driven Design of poly(ethylene terephthalate)-replacement copolymers

Poly(ethylene terephthalate) (PET), a widely used thermoplastic in packaging, textiles, and engineering applications, is valued for its strength, clarity, and chemical resistance. Increasing environmental impact concerns and regulatory pressures drive the search for alternatives with comparable or superior performance. We present an AI-driven polymer design pipeline employing virtual forward synthesis (VFS) to generate PET-replacement copolymers. Inspired by the esterification route of PET synthesis, we systematically combined a down-selected set of Toxic Substances Control Act (TSCA)-listed monomers to create 12,100 PET-like polymers. Machine learning models predicted glass transition temperature (Tg), band gap, and tendency to crystallize, for all designs. Multi-objective screening identified 1,108 candidates predicted to match or exceed PET in $T_{\rm g}$ and band gap, including the ``rediscovery'' of other known commercial PET-alternate polymers (e.g., PETG, Tritan, Ecozen) that provide retrospective validation of our design pipeline, demonstrating a capability to rapidly design experimentally feasible polymers at a scale. Furthermore, selected, entirely new (previously unknown) candidates designed here have been synthesized and characterized, providing a definitive validation of the design framework.

cond-mat.soft↗

arXiv2025

Superconductor discovery in the emerging paradigm of Materials Informatics

The last two decades have witnessed a tremendous number of computational predictions of hydride-based (phonon-mediated) superconductors, mostly at extremely high pressures, i.e., hundreds of GPa. These discoveries were heavily driven by Migdal-\'{E}liashberg theory (and its first-principles computational implementations) for electron-phonon interactions, the key concept of phonon-mediated superconductivity. Dozens of predictions were experimentally synthesized and characterized, triggering not only enormous excitement in the community but also some debates. In this Article, we review the computational-driven discoveries and the recent developments in the field from various essential aspects, including the theoretical, computational, and, specifically, artificial intelligence (AI)/machine learning (ML) based approaches emerging within the paradigm of materials informatics. While challenges and critical gaps can be found in all of these approaches, AI/ML efforts specifically remain in its infant stage for good reasons. However, opportunities exist when these approaches can be further developed and integrated in concerted efforts, in which AI/ML approaches could play more important roles.

cond-mat.supr-con↗

arXiv2024

Polymer Composites Informatics for Flammability, Thermal, Mechanical and Electrical Property Predictions

Polymer composite performance depends significantly on the polymer matrix, additives, processing conditions, and measurement setups. Traditional physics-based optimization methods for these parameters can be slow, labor-intensive, and costly, as they require physical manufacturing and testing. Here, we introduce a first step in extending Polymer Informatics, an AI-based approach proven effective for neat polymer design, into the realm of polymer composites. We curate a comprehensive database of commercially available polymer composites, develop a scheme for machine-readable data representation, and train machine-learning models for 15 flame-resistant, mechanical, thermal, and electrical properties, validating them on entirely unseen data. Future advancements are planned to drive the AI-assisted design of functional and sustainable polymer composites.

cond-mat.soft↗

arXiv2024

Gas permeability, diffusivity, and solubility in polymers: Simulation-experiment data fusion and multi-task machine learning

Machine learning (ML) models for predicting gas permeability through polymers have traditionally relied on experimental data. While these models exhibit robustness within familiar chemical domains, reliability wanes when applied to new spaces. To address this challenge, we present a multi-tiered multi-task learning framework empowered with advanced machine-crafted polymer fingerprinting algorithms and data fusion techniques. This framework combines scarce "high-fidelity" experimental data with abundant diverse "low-fidelity" simulation or synthetic data, resulting in predictive models that display a high level of generalizability across novel chemical spaces. Additionally, this multi-task scheme capitalizes on known physics and interrelated properties, such as gas diffusivity and solubility, both of which are closely tied to permeability. By amalgamating high-throughput generated simulation data with available experimental data for gas permeability, diffusivity, and solubility for various gases, we construct multi-task deep learning models. These models can simultaneously predict all three properties for all gases under consideration. With markedly enhanced predictive accuracy, particularly compared to traditional models reliant solely on experimental data for a singular property. This strategy underscores the potential of coupling high-throughput classical simulations with data fusion methodologies to yield state-of-the-art property predictors, especially when experimental data for targeted properties is scarce.

cond-mat.mtrl-sci↗

arXiv2023

PolyGET: Accelerating Polymer Simulations by Accurate and Generalizable Forcefield with Equivariant Transformer

Polymer simulation with both accuracy and efficiency is a challenging task. Machine learning (ML) forcefields have been developed to achieve both the accuracy of ab initio methods and the efficiency of empirical force fields. However, existing ML force fields are usually limited to single-molecule settings, and their simulations are not robust enough. In this paper, we present PolyGET, a new framework for Polymer Forcefields with Generalizable Equivariant Transformers. PolyGET is designed to capture complex quantum interactions between atoms and generalize across various polymer families, using a deep learning model called Equivariant Transformers. We propose a new training paradigm that focuses exclusively on optimizing forces, which is different from existing methods that jointly optimize forces and energy. This simple force-centric objective function avoids competing objectives between energy and forces, thereby allowing for learning a unified forcefield ML model over different polymer families. We evaluated PolyGET on a large-scale dataset of 24 distinct polymer types and demonstrated state-of-the-art performance in force accuracy and robust MD simulations. Furthermore, PolyGET can simulate large polymers with high fidelity to the reference ab initio DFT method while being able to generalize to unseen polymers.

cs.LG↗

arXiv2023

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

Recent works have shown the promise of learning pre-trained models for 3D molecular representation. However, existing pre-training models focus predominantly on equilibrium data and largely overlook off-equilibrium conformations. It is challenging to extend these methods to off-equilibrium data because their training objective relies on assumptions of conformations being the local energy minima. We address this gap by proposing a force-centric pretraining model for 3D molecular conformations covering both equilibrium and off-equilibrium data. For off-equilibrium data, our model learns directly from their atomic forces. For equilibrium data, we introduce zero-force regularization and forced-based denoising techniques to approximate near-equilibrium forces. We obtain a unified pre-trained model for 3D molecular representation with over 15 million diverse conformations. Experiments show that, with our pre-training objective, we increase forces accuracy by around 3 times compared to the un-pre-trained Equivariant Transformer model. By incorporating regularizations on equilibrium data, we solved the problem of unstable MD simulations in vanilla Equivariant Transformers, achieving state-of-the-art simulation performance with 2.45 times faster inference time than NequIP. As a powerful molecular encoder, our pre-trained model achieves on-par performance with state-of-the-art property prediction tasks.

physics.chem-ph↗

arXiv2023

Machine-learning approach for discovery of conventional superconductors

First-principles computations are the driving force behind numerous discoveries of hydride-based superconductors, mostly at high pressures, during the last decade. Machine-learning (ML) approaches can further accelerate the future discoveries if their reliability can be improved. The main challenge of current ML approaches, typically aiming at predicting the critical temperature $T_{\rm c}$ of a solid from its chemical composition and target pressure, is that the correlations to be learned are deeply hidden, indirect, and uncertain. In this work, we showed that predicting superconductivity at any pressure from the atomic structure is sustainable and reliable. For a demonstration, we curated a diverse dataset of 584 atomic structures for which $λ$ and $ω_{\log}$, two parameters of the electron-phonon interactions, were computed. We then trained some ML models to predict $λ$ and $ω_{\log}$, from which $T_{\rm c}$ can be computed in a post-processing manner. The models were validated and used to identify two possible superconductors whose $T_{\rm c}\simeq 10-15$K at zero pressure. Interestingly, these materials have been synthesized and studied in some other contexts. In summary, the proposed ML approach enables a pathway to directly transfer what can be learned from the high-pressure atomic-level details that correlate with high-$T_{\rm c}$ superconductivity to zero pressure. Going forward, this strategy will be improved to better contribute to the discoveries of new superconductors.

cond-mat.supr-con↗

arXiv2022

Informatics-Driven Selection of Polymers for Fuel-Cell Applications

Modern fuel cell technologies use Nafion as the material of choice for the proton exchange membrane (PEM) and as the binding material (ionomer), used to assemble the catalyst layers of the anode and cathode. These applications demand high proton conductivity as well as other requirements. For example, PEM is expected to block electrons, oxygen, and hydrogen from penetrating and diffusing while the anode/cathode ionomer should allow hydrogen/oxygen to move easily, so that they can reach the catalyst nanoparticles. Given some of the well-known limits of Nafion, such as low glass-transition temperature, the community is in the midst of an active search for Nafion replacements. In this work, we present an informatics-based scheme to search large polymer chemical spaces, which includes establishing a list of properties needed for the targeted applications, developing predictive machine-learning models for these properties, defining a search space, and using the developed models to screen the search space. Using the scheme, we have identified 60 new polymer candidates for PEM, anode ionomer, and cathode ionomer that we hope will be advanced to the next step, i.e., validating the designs through synthesis and testing. The proposed informatics scheme is generic, and can be used to select polymers for multiple applications in the future.

physics.app-ph↗

arXiv2022

Adaptive Exploration and Optimization of Materials Crystal Structures

A central problem of materials science is to determine whether a hypothetical material is stable without being synthesized, which is mathematically equivalent to a global optimization problem on a highly non-linear and multi-modal potential energy surface (PES). This optimization problem poses multiple outstanding challenges, including the exceedingly high dimensionality of the PES and that PES must be constructed from a reliable, sophisticated, parameters-free, and thus, very expensive computational method, for which density functional theory (DFT) is an example. DFT is a quantum mechanics based method that can predict, among other things, the total potential energy of a given configuration of atoms. DFT, while accurate, is computationally expensive. In this work, we propose a novel expansion-exploration-exploitation framework to find the global minimum of the PES. Starting from a few atomic configurations, this ``known'' space is expanded to construct a big candidate set. The expansion begins in a non-adaptive manner, where new configurations are added without considering their potential energy. A novel feature of this step is that it tends to generate a space-filling design without the knowledge of the boundaries of the domain space. If needed, the non-adaptive expansion of the space of configurations is followed by adaptive expansion, where ``promising regions'' of the domain space (those with low energy configurations) are further expanded. Once a candidate set of configurations is obtained, it is simultaneously explored and exploited using Bayesian optimization to find the global minimum. The methodology is demonstrated using a problem of finding the most stable crystal structure of Aluminum.

stat.AP↗

arXiv2020

Polymer Informatics with Multi-Task Learning

Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict the properties of new polymers are becoming commonplace. Nevertheless, these models do not utilize the full breadth of the knowledge available in datasets, which are oftentimes sparse; inherent correlations between different property datasets are disregarded. Here, we demonstrate the potency of multi-task learning approaches that exploit such inherent correlations effectively, particularly when some property dataset sizes are small. Data pertaining to 36 different properties of over $13, 000$ polymers (corresponding to over $23,000$ data points) are coalesced and supplied to deep-learning multi-task architectures. Compared to conventional single-task learning models (that are trained on individual property datasets independently), the multi-task approach is accurate, efficient, scalable, and amenable to transfer learning as more data on the same or different properties become available. Moreover, these models are interpretable. Chemical rules, that explain how certain features control trends in specific property values, emerge from the present work, paving the way for the rational design of application specific polymers meeting desired property or performance objectives.

cond-mat.mtrl-sci↗

arXiv2019

Machine Learning Models for the Lattice Thermal Conductivity Prediction of Inorganic Materials

The lattice thermal conductivity ($κ_{\rm L} $) is a critical property of thermoelectrics, thermal barrier coating materials and semiconductors. While accurate empirical measurements of $κ_{\rm L} $ are extremely challenging, it is usually approximated through computational approaches, such as semi-empirical models, Green-Kubo formalism coupled with molecular dynamics simulations, and first-principles based methods. However, these theoretical methods are not only limited in terms of their accuracy, but sometimes become computationally intractable owing to their cost. Thus, in this work, we build a machine learning (ML)-based model to accurately and instantly predict $κ_{\rm L}$ of inorganic materials, using a benchmark data set of experimentally measured $κ_{\rm L} $ of about 100 inorganic solids. We use advanced and universal feature engineering techniques along with the Gaussian process regression algorithm, and compare the performance of our ML model with past theoretical works. The trained ML model is not only helpful for rational design and screening of novel materials, but we also identify key features governing the thermal transport behavior in non-metals.

cond-mat.mtrl-sci↗

arXiv2011

Valence Bond Entanglement and Fluctuations in Random Singlet Phases

The ground state of the uniform antiferromagnetic spin-1/2 Heisenberg chain can be viewed as a strongly fluctuating liquid of valence bonds, while in disordered chains these bonds lock into random singlet states on long length scales. We show that this phenomenon can be studied numerically, even in the case of weak disorder, by calculating the mean value of the number of valence bonds leaving a block of $L$ contiguous spins (the valence-bond entanglement entropy) as well as the fluctuations in this number. These fluctuations show a clear crossover from a small $L$ regime, in which they behave similar to those of the uniform model, to a large $L$ regime in which they saturate in a way consistent with the formation of a random singlet state on long length scales. A scaling analysis of these fluctuations is used to study the dependence on disorder strength of the length scale characterizing the crossover between these two regimes. Results are obtained for a class of models which include, in addition to the spin-1/2 Heisenberg chain, the uniform and disordered critical 1D transverse-field Ising model and chains of interacting non-Abelian anyons.

cond-mat.dis-nn↗

arXiv2010

Monte Carlo Simulations of Interacting Anyon Chains

A generalized version of the valence-bond Monte Carlo method is used to study ground state properties of the 1+1 dimensional quantum $Q$-state Potts models. For appropriate values of $Q$ these models can be used to describe interacting chains of non-Abelian anyons --- quasiparticle excitations of certain exotic fractional quantum Hall states.

cond-mat.dis-nn↗

arXiv2010

EBEX: A balloon-borne CMB polarization experiment

EBEX is a NASA-funded balloon-borne experiment designed to measure the polarization of the cosmic microwave background (CMB). Observations will be made using 1432 transition edge sensor (TES) bolometric detectors read out with frequency multiplexed SQuIDs. EBEX will observe in three frequency bands centered at 150, 250, and 410 GHz, with 768, 384, and 280 detectors in each band, respectively. This broad frequency coverage is designed to provide valuable information about polarized foreground signals from dust. The polarized sky signals will be modulated with an achromatic half wave plate (AHWP) rotating on a superconducting magnetic bearing (SMB) and analyzed with a fixed wire grid polarizer. EBEX will observe a patch covering ~1% of the sky with 8' resolution, allowing for observation of the angular power spectrum from \ell = 20 to 1000. This will allow EBEX to search for both the primordial B-mode signal predicted by inflation and the anticipated lensing B-mode signal. Calculations to predict EBEX constraints on r using expected noise levels show that, for a likelihood centered around zero and with negligible foregrounds, 99% of the area falls below r = 0.035. This value increases by a factor of 1.6 after a process of foreground subtraction. This estimate does not include systematic uncertainties. An engineering flight was launched in June, 2009, from Ft. Sumner, NM, and the long duration science flight in Antarctica is planned for 2011. These proceedings describe the EBEX instrument and the North American engineering flight.

astro-ph.CO↗

arXiv2010

Software systems for operation, control, and monitoring of the EBEX instrument

We present the hardware and software systems implementing autonomous operation, distributed real-time monitoring, and control for the EBEX instrument. EBEX is a NASA-funded balloon-borne microwave polarimeter designed for a 14 day Antarctic flight that circumnavigates the pole. To meet its science goals the EBEX instrument autonomously executes several tasks in parallel: it collects attitude data and maintains pointing control in order to adhere to an observing schedule; tunes and operates up to 1920 TES bolometers and 120 SQUID amplifiers controlled by as many as 30 embedded computers; coordinates and dispatches jobs across an onboard computer network to manage this detector readout system; logs over 3~GiB/hour of science and housekeeping data to an onboard disk storage array; responds to a variety of commands and exogenous events; and downlinks multiple heterogeneous data streams representing a selected subset of the total logged data. Most of the systems implementing these functions have been tested during a recent engineering flight of the payload, and have proven to meet the target requirements. The EBEX ground segment couples uplink and downlink hardware to a client-server software stack, enabling real-time monitoring and command responsibility to be distributed across the public internet or other standard computer networks. Using the emerging dirfile standard as a uniform intermediate data format, a variety of front end programs provide access to different components and views of the downlinked data products. This distributed architecture was demonstrated operating across multiple widely dispersed sites prior to and during the EBEX engineering flight.

astro-ph.IM↗

arXiv2010

The EBEX Cryostat and Supporting Electronics

We describe the cryostat and supporting electronics for the EBEX experiment. EBEX is a balloon-borne polarimeter designed to measure the B-mode polarization of the cosmic microwave background radiation. The instrument includes a 1.5 meter Gregorian-type telescope and 1432 bolometric transition edge sensor detectors operating at 0.3 K. Electronics for monitoring temperatures and controlling cryostat refrigerators is read out over CANbus. A timing system ensures the data from all subsystems is accurately synchronized. EBEX completed an engineering test flight in June 2009 during which the cryogenics and supporting electronics performed according to predictions. The temperatures of the cryostat were stable, and an analysis of a subset of the data finds no scan synchronous signal in the cryostat temperatures. Preparations are underway for an Antarctic flight.

astro-ph.IM↗

arXiv2009

Study of the Experimental Probe of Inflationary Cosmology (EPIC)-Intemediate Mission for NASA's Einstein Inflation Probe

Measurements of Cosmic Microwave Background (CMB) anisotropy have served as the best experimental probe of the early universe to date. The inflationary paradigm, inspired in part by the extreme isotropy of the CMB, is now a cornerstone in modern cosmology. Inflation has passed a series of rigorous experimental tests, but we still do not understand the physical mechanism or energy scale behind inflation. A general prediction of inflation and one that can provide certain insights into inflationary physics is a background of primordial gravitational waves. These perturbations leave a distinct signature in the CMB B-modes of polarization. The EPIC (Experimental Probe of Inflationary Cosmology) study team has investigated several CMB polarization mission concepts to carry out a definitive measurement of the inflationary B-mode polarization spectrum. In this report we study a mission with an aperture intermediate between the two missions discussed in our previous report. EPIC-IM's increased aperture allows access to a broader science case than the small EPIC-Low Cost mission. In addition to the search for inflationary gravitational waves, the increase aperture allows us to mine the scale polarization and lensing shear polarization signals down to cosmological limits, so that we extract virtually all the cosmological information available from the CMB. In addition, a modest number of channels operating at higher frequencies allows for an all-sky measurement of polarized Galactic dust, which will provide a rich dataset for Galactic science related to magnetic fields. Using a combination of a large sensitivity focal plane with a new optical design, and an efficient 4K mechanical cooler, EPIC-IM realizes higher sensitivity than EPIC-Comprehensive Science mission.

astro-ph.CO↗