arXiv subjects

Zekun Ren

Publications and source records attributed to Zekun Ren.

14 recordsLinked to original sources

arXiv2026

PUDA: An AI-Native Hardware Harness for Self-Driving Laboratories

Physical Unified Device Architecture (PUDA) is an AI-native hardware harness for self-driving laboratories (SDLs). Rather than building a human-centered graphical user interface (GUI) orchestration layer, PUDA creates a command-line runtime environment that lets agents observe, orient, decide, and act over experiments while hardware execution remains deterministic, atomic, and auditable. Headless by design, devices appear through discoverable command-line interfaces, JSON protocols are routed through a distributed messaging system, and command responses, data products, and reports are preserved as structured records. PUDA organizes protocols, runs, samples, measurements, and command logs into an AI-native data structure linked by run identifiers and timestamps, preserving provenance from submitted protocol through hardware response to resulting data products. PUDA separates scientific orchestration from physical operation and data telemetry: agents choose experiments, while PUDA executes validated commands and captures provenance-linked state, responses, and data. The contribution is not another optimizer, orchestrator, or recipe language. It is a practical execution and data environment for agentic SDLs; the broader physical AI implication is that PUDA provides an AI-native hardware harness for AI systems to interact with physical tools.

cond-mat.mtrl-sci↗

arXiv2026

Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates

The appearance of generative models has opened vast chemical spaces in the design of functional materials. Although machine learning interatomic potentials (MLIPs) have substantially accelerated phonon calculations, high-fidelity prediction of lattice thermal conductivity \k{appa}lat still requires accurate treatment of anharmonic interactions, which remains a key challenge for existing potentials across novel chemical spaces. To address this challenge, we present a comprehensive benchmark of 15 surrogate models for predicting \k{appa}lat using the Phonix database, which contains 6,966 entries with anharmonic phonon properties derived from first-principles calculations. Firstly, We categorize these surrogate models into three distinct groups: Physical-informed feature descriptors combined with ML models, end-to-end deep neural networks, and pre-trained MLIP-embeddings combined with ML models. By evaluating model performance across random, space-group disjoint (testing generalization to unseen crystal symmetries), and Out-Of-Distribution splits (OOD dataset that testing extrapolation to property regimes beyond the training range) based on \k{appa}lat, we probe both interpolation and exploration capabilities. Our results reveal that MLIP-embedded models excel in interpolation within well-sampled regions, deep neural network models especially ALiEGNN demonstrate superior robustness in OOD regimes critical for discovering novel low-\k{appa}lat. Additionally, we find a systematic degradation in performance when the structural representation is reduced. Although surrogate models exhibit lower accuracy than direct simulations using first-principles calculation, they reduce computational costs by orders of magnitude, enabling efficient high-throughput screening of thermoelectric materials with minimal loss in generative design workflows.

cond-mat.mtrl-sci↗

arXiv2025

Energy Underprediction from Symmetry in Machine-Learning Interatomic Potentials

Machine learning interatomic potentials (MLIAPs) have emerged as powerful tools for accelerating materials simulations with near-density functional theory (DFT) accuracy. However, despite significant advances, we identify a critical yet overlooked issue undermining their reliability: a systematic energy underprediction. This problem becomes starkly evident in large-scale thermodynamic stability assessments. By performing over 12 million calculations using nine MLIAPs for over 150,000 inorganic crystals in the Materials Project, we demonstrate that most frontier models consistently underpredict energy above hull (Ehull), a key metric for thermodynamic stability, total energy, and formation energy, despite the fact that over 90\% of test structures (DFT-relaxed) are in the training data. The mean absolute errors (MAE) for Ehull exceed ~30 meV/atom even by the best model, directly challenging claims of achieving ``DFT accuracy'' for property predictions central to materials discovery, especially related to (meta-)stability. Crucially, we trace this underprediction to insufficient handling of symmetry degrees of freedom (DOF), constituting both lattice symmetry and Wyckoff site symmetries for the space group. MLIAPs exhibit pronounced errors (MAE for Ehull $>$ ~40 meV/atom) in structures with high symmetry DOF, where subtle atomic displacements significantly impact energy landscapes. Further analysis also indicates that the MLIAPs show severe energy underprediction for a large proportion of near-hull materials. We argue for improvements on symmetry-aware models such as explicit DOF encoding or symmetry-regularized loss functions, and more robust MLIAPs for predicting crystal properties where the preservation and breaking of symmetry are pivotal.

cond-mat.mtrl-sci↗

arXiv2023

Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)

Needle-in-a-Haystack problems exist across a wide range of applications including rare disease prediction, ecological resource management, fraud detection, and material property optimization. A Needle-in-a-Haystack problem arises when there is an extreme imbalance of optimum conditions relative to the size of the dataset. For example, only $0.82\%$ out of $146$k total materials in the open-access Materials Project database have a negative Poisson's ratio. However, current state-of-the-art optimization algorithms are not designed with the capabilities to find solutions to these challenging multidimensional Needle-in-a-Haystack problems, resulting in slow convergence to a global optimum or pigeonholing into a local minimum. In this paper, we present a Zooming Memory-Based Initialization algorithm, entitled ZoMBI. ZoMBI actively extracts knowledge from the previously best-performing evaluated experiments to iteratively zoom in the sampling search bounds towards the global optimum "needle" and then prunes the memory of low-performing historical experiments to accelerate compute times by reducing the algorithm time complexity from $O(n^3)$ to $O(ϕ^3)$ for $ϕ$ forward experiments per activation, which trends to a constant $O(1)$ over several activations. Additionally, ZoMBI implements two custom adaptive acquisition functions to further guide the sampling of new experiments toward the global optimum. We validate the algorithm's optimization performance on three real-world datasets exhibiting Needle-in-a-Haystack and further stress-test the algorithm's performance on an additional 174 analytical datasets. The ZoMBI algorithm demonstrates compute time speed-ups of 400x compared to traditional Bayesian optimization as well as efficiently discovering optima in under 100 experiments that are up to 3x more highly optimized than those discovered by similar methods MiP-EGO, TuRBO, and HEBO.

cs.LG↗

arXiv2022

Tackling Data Scarcity with Transfer Learning: A Case Study of Thickness Characterization from Optical Spectra of Perovskite Thin Films

Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning. In the application of high-throughput thickness as a downstream process of the high-throughput optimization of optoelectronic thin films with autonomous workflows, data scarcity occurs especially for new materials. To achieve high-throughput thickness characterization, we propose a machine learning model called thicknessML that predicts thickness from UV-Vis spectrophotometry input and an overarching transfer learning workflow. We demonstrate the transfer learning workflow from generic source domain of generic band-gapped materials to specific target domain of perovskite materials, where the target domain data only come from limited number (18) of refractive indices from literature. The target domain can be easily extended to other material classes with a few literature data. Defining thickness prediction accuracy to be within-10% deviation, thicknessML achieves 92.2% (with a deviation of 3.6%) accuracy with transfer learning compared to 81.8% (with a deviation of 3.6%) 11.7% without (lower mean and larger standard deviation). Experimental validation on six deposited perovskite films also corroborates the efficacy of the proposed workflow by yielding a 10.5% mean absolute percentage error (MAPE).

cs.LG↗

arXiv2022

What Information is Necessary and Sufficient to Predict Materials Properties using Machine Learning?

Conventional wisdom of materials modelling stipulates that both chemical composition and crystal structure are integral in the prediction of physical properties. However, recent developments challenge this by reporting accurate property-prediction machine learning (ML) frameworks using composition alone without knowledge of the local atomic environments or long-range order. To probe this behavior, we conduct a systematic comparison of supervised ML models built on composition only vs. composition plus structure features. Similar performance for property prediction is found using both models for compounds close to the thermodynamic convex hull. We hypothesize that composition embeds structural information of ground-state structures in support of composition-centric models for property prediction and inverse design of stable compounds.

cond-mat.mtrl-sci↗

arXiv2022

Machine Learning with Knowledge Constraints for Process Optimization of Open-Air Perovskite Solar Cell Manufacturing

Perovskite photovoltaics (PV) have achieved rapid development in the past decade in terms of power conversion efficiency of small-area lab-scale devices; however, successful commercialization still requires further development of low-cost, scalable, and high-throughput manufacturing techniques. One of the critical challenges of developing a new fabrication technique is the high-dimensional parameter space for optimization, but machine learning (ML) can readily be used to accelerate perovskite PV scaling. Herein, we present an ML-guided framework of sequential learning for manufacturing process optimization. We apply our methodology to the Rapid Spray Plasma Processing (RSPP) technique for perovskite thin films in ambient conditions. With a limited experimental budget of screening 100 process conditions, we demonstrated an efficiency improvement to 18.5% as the best-in-our-lab device fabricated by RSPP, and we also experimentally found 10 unique process conditions to produce the top-performing devices of more than 17% efficiency, which is 5 times higher rate of success than the control experiments with pseudo-random Latin hypercube sampling. Our model is enabled by three innovations: (a) flexible knowledge transfer between experimental processes by incorporating data from prior experimental data as a probabilistic constraint; (b) incorporation of both subjective human observations and ML insights when selecting next experiments; (c) adaptive strategy of locating the region of interest using Bayesian optimization first, and then conducting local exploration for high-efficiency devices. Furthermore, in virtual benchmarking, our framework achieves faster improvements with limited experimental budgets than traditional design-of-experiments methods (e.g., one-variable-at-a-time sampling).

cs.LG↗

arXiv2021

An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties

Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis.

physics.comp-ph↗

arXiv2021

Predicting antimicrobial activity of conjugated oligoelectrolyte molecules via machine learning

New antibiotics are needed to battle growing antibiotic resistance, but the development process from hit, to lead, and ultimately to a useful drug, takes decades. Although progress in molecular property prediction using machine-learning methods has opened up new pathways for aiding the antibiotics development process, many existing solutions rely on large datasets and finding structural similarities to existing antibiotics. Challenges remain in modelling of unconventional antibiotics classes that are drawing increasing research attention. In response, we developed an antimicrobial activity prediction model for conjugated oligoelectrolyte molecules, a new class of antibiotics that lacks extensive prior structure-activity relationship studies. Our approach enables us to predict minimum inhibitory concentration for E. coli K12, with 21 molecular descriptors selected by recursive elimination from a set of 5,305 descriptors. This predictive model achieves an R2 of 0.65 with no prior knowledge of the underlying mechanism. We find the molecular representation optimum for the domain is the key to good predictions of antimicrobial activity. In the case of conjugated oligoelectrolytes, a representation reflecting the 3-dimensional shape of the molecules is most critical. Although it is demonstrated with a specific example of conjugated oligoelectrolytes, our proposed approach for creating the predictive model can be readily adapted to other novel antibiotic candidate domains.

physics.app-ph↗

arXiv2021

Accelerated automated screening of viscous graphene suspensions with various surfactants for optimal electrical conductivity

Functional composite thin films have a wide variety of applications in flexible and/or electronic devices, telecommunications and multifunctional emerging coatings. Rapid screening of their properties is a challenging task, especially with multiple components defining the targeted properties. In this work we present a manifold for accelerated automated screening of viscous graphene suspensions for optimal electrical conductivity. Using Opentrons OT2 robotic auto-pipettor, we tested 3 most industrially significant surfactants - PVP, SDS and T80 - by fabricating 288 samples of graphene suspensions in aqueous hydroxypropylmethylcellulose. Enabled by our custom motorized 4-point probe measurement setup and computer vision algorithms, we then measured electrical conductivity of every sample using custom and identified that the highest performance is achieved for PVP-based samples, peaking at 10.4 mS/cm. The automation of the experimental procedure allowed us to perform majority of the experiments using robots, while involvement of human researcher was kept to minimum. Overall the experiment was completed in less than 18 hours, only 3 of which involved humans.

physics.app-ph↗

arXiv2021

Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains

In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems. However, very few studies have evaluated the efficiency of BO as a general optimization algorithm across a broad range of experimental materials science domains. In this work, we evaluate the performance of BO algorithms with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems, namely carbon nanotube polymer blends, silver nanoparticles, lead-halide perovskites, as well as additively manufactured polymer structures and shapes. By defining acceleration and enhancement metrics for general materials optimization objectives, we find that for surrogate model selection, Gaussian Process (GP) with anisotropic kernels (automatic relevance detection, ARD) and Random Forests (RF) have comparable performance and both outperform the commonly used GP without ARD. We discuss the implicit distributional assumptions of RF and GP, and the benefits of using GP with anisotropic kernels in detail. We provide practical insights for experimentalists on surrogate model selection of BO during materials optimization campaigns.

cond-mat.mtrl-sci↗

arXiv2020

Bridging the gap between photovoltaics R&D and manufacturing with data-driven optimization

Novel photovoltaics, such as perovskites and perovskite-inspired materials, have shown great promise due to high efficiency and potentially low manufacturing cost. So far, solar cell R&D has mostly focused on achieving record efficiencies, a process that often results in small batches, large variance, and limited understanding of the physical causes of underperformance. This approach is intensive in time and resources, and ignores many relevant factors for industrial production, particularly the need for high reproducibility and high manufacturing yield, and the accompanying need of physical insights. The record-efficiency paradigm is effective in early-stage R&D, but becomes unsuitable for industrial translation, requiring a repetition of the optimization procedure in the industrial setting. This mismatch between optimization objectives, combined with the complexity of physical root-cause analysis, contributes to decade-long timelines to transfer new technologies into the market. Based on recent machine learning and technoeconomic advances, our perspective articulates a data-driven optimization framework to bridge R&D and manufacturing optimization approaches. We extend the maximum-efficiency optimization paradigm by considering two additional dimensions: a technoeconomic figure of merit and scalable physical inference. Our framework naturally aligns different stages of technology development with shared optimization objectives, and accelerates the optimization process by providing physical insights.

physics.app-ph↗

arXiv2019

Embedding Physics Domain Knowledge into a Bayesian Network Enables Layer-by-Layer Process Innovation for Photovoltaics

Process optimization of photovoltaic devices is a time-intensive, trial and error endeavor, without full transparency of the underlying physics, and with user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach that identifies the root cause(s) of underperformance with layer by-layer resolution and reveals alternative optimal process windows beyond global black-box optimization. Our Bayesian-network approach links process conditions to materials descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency), using a Bayesian inference framework with an autoencoder-based surrogate device-physics model that is 100x faster than numerical solvers. With the trained surrogate model, our approach is robust and reduces significantly the time consuming experimentalist intervention, even with small numbers of fabricated samples. To demonstrate our method, we perform layer-by-layer optimization of GaAs solar cells. In a single cycle of learning, we find an improved growth temperature for the GaAs solar cells without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above baseline and traditional black-box optimization methods.

physics.app-ph↗

arXiv2019

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16°, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.

physics.data-an↗