arXiv subjects

Maxim Ziatdinov

Publications and source records attributed to Maxim Ziatdinov.

At least 19 recordsLinked to original sources

arXiv2026

Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation

We present a multi-agentic workflow for critical materials recovery that deploys a series of AI agents and automated instruments to recover critical materials from produced water and magnet leachates. This approach achieves selective precipitation from real-world feedstocks using simple chemicals, accelerating the development of efficient, adaptable, and scalable separations to a timeline of days, rather than months and years.

cond-mat.mtrl-sci↗

arXiv2025

Automated Materials Discovery Platform Realized: Scanning Probe Microscopy of Combinatorial Libraries

Combinatorial materials libraries provide a powerful platform for mapping how physical properties evolve across binary and ternary cross-sections of multicomponent phase diagrams. While synthesis of such libraries has advanced since the 1960s and been accelerated by laboratory automation, their broader utility depends on rapid, quantitative measurements of composition-dependent structures and functionalities. Scanning probe microscopies (SPM), including piezoresponse force microscopy (PFM), offer unique potential for providing these functionally relevant, spatially resolved readouts. Here, we demonstrate a fully automated SPM framework for exploring ferroelectric properties across combinatorial libraries, focusing on binary Sm-doped BiFeO3 (SmBFO) and ternary Al$_{1-x-y}$Sc$_x$B$_y$N (Al,Sc,B)N systems. In SmBFO, automated exploration identifies the known morphotropic phase boundary with enhanced ferroelectric response and reveals a previously unreported double-peak fine structure. In the (Al,Sc,B)N library, ferroelectric behavior emerges at the phase-stability boundary, correlating with variations in morphology and defect concentration. By integrating automated SPM with wavelength-dispersive spectroscopy (WDS) and photoluminescence mapping, we resolve the composition-morphology-defect-property relationships underlying ferroelectric response and demonstrate a pathway toward a multi-tool, high-throughput characterization platform. Finally, we implement Gaussian-process-based single- and multi-objective Bayesian optimization to enable autonomous exploration, highlighting the Pareto front as a powerful framework for balancing competing physical rewards and accelerating data-driven physics discovery.

cond-mat.mtrl-sci↗

arXiv2025

Comparing Machine Learning and Physics-Based Nanoparticle Geometry Determinations Using Far-Field Spectral Properties

Anisotropic metal nanostructures exhibit polarization-dependent light scattering. This property has been widely exploited to determine geometries of subwavelength structures using far-field microscopy. Here, we explore the use of variational autoencoders (VAEs) to determine the geometries of gold nanorods (NRs) such as in-plane orientation and aspect ratio under linearly polarized dark-field illumination in an optical microscope. We input polarized dark-field scattering spectra and electron microscopy images into a dual-branch multimodal VAE with a single shared latent space trained on paired spectra-image data, using a learnable linear adapter. We achieve prediction of Au NRs using only polarized dark-field scattering spectra input. We determine geometrical parameters of orientational angle and aspect ratio quantitatively via both dual-VAE and physics-based analysis. We show that orientational angle prediction by dual-VAE performs well with only a small (300 particle) training set, yielding a mean absolute error (MAE) of 14.4 and a concordance correlation coefficient (CCC) of 0.95. This performance is only marginally worse than the physics-based cos(2theta) fitting approach between the scattering intensity and the polarizing angle, which achieves MAE of 8.78 and CCC of 0.99. Aspect ratio determination is also similar for the dual-VAE and physics-based fitting comparison (MAE of 0.21 vs. 0.23 and CCC of 0.53 vs. 0.68). By learning a shared latent manifold linking spectra and morphology, the model can generate NR images with accurate orientation and aspect ratio with spectra-only input in the small-data regime (300 particles), suggesting a general recipe for inverse nano-optical problems requiring both structure and orientation information.

physics.optics↗

arXiv2025

Beyond Optimization: Exploring Novelty Discovery in Autonomous Experiments

Autonomous experiments (AEs) are transforming how scientific research is conducted by integrating artificial intelligence with automated experimental platforms. Current AEs primarily focus on the optimization of a predefined target; while accelerating this goal, such an approach limits the discovery of unexpected or unknown physical phenomena. Here, we introduce a novel framework, INS2ANE (Integrated Novelty Score-Strategic Autonomous Non-Smooth Exploration), to enhance the discovery of novel phenomena in autonomous experimentation. Our method integrates two key components: (1) a novelty scoring system that evaluates the uniqueness of experimental results, and (2) a strategic sampling mechanism that promotes exploration of under-sampled regions even if they appear less promising by conventional criteria. We validate this approach on a pre-acquired dataset with a known ground truth comprising of image-spectral pairs. We further implement the process on autonomous scanning probe microscopy experiments. INS2ANE significantly increases the diversity of explored phenomena in comparison to conventional optimization routines, enhancing the likelihood of discovering previously unobserved phenomena. These results demonstrate the potential for AE to enhance the depth of scientific discovery; in combination with the efficiency provided by AEs, this approach promises to accelerate scientific research by simultaneously navigating complex experimental spaces to uncover new phenomena.

cs.LG↗

arXiv2025

Operationalizing Serendipity: Multi-Agent AI Workflows for Enhanced Materials Characterization with Theory-in-the-Loop

The history of science is punctuated by serendipitous discoveries, where unexpected observations, rather than targeted hypotheses, opened new fields of inquiry. While modern autonomous laboratories excel at accelerating hypothesis testing, their optimization for efficiency risks overlooking these crucial, unplanned findings. To address this gap, we introduce SciLink, an open-source, multi-agent artificial intelligence framework designed to operationalize serendipity in materials research by creating a direct, automated link between experimental observation, novelty assessment, and theoretical simulations. The framework employs a hybrid AI strategy where specialized machine learning models perform quantitative analysis of experimental data, while large language models handle higher-level reasoning. These agents autonomously convert raw data from materials characterization techniques into falsifiable scientific claims, which are then quantitatively scored for novelty against the published literature. We demonstrate the framework's versatility across diverse research scenarios, showcasing its application to atomic-resolution and hyperspectral data, its capacity to integrate real-time human expert guidance, and its ability to close the research loop by proposing targeted follow-up experiments. By systematically analyzing all observations and contextualizing them, SciLink provides a practical framework for AI-driven materials research that not only enhances efficiency but also actively cultivates an environment ripe for serendipitous discoveries, thereby bridging the gap between automated experimentation and open-ended scientific exploration.

cs.AI↗

arXiv2025

Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy

Rapidly determining structure-property correlations in materials is an important challenge in better understanding fundamental mechanisms and greatly assists in materials design. In microscopy, imaging data provides a direct measurement of the local structure, while spectroscopic measurements provide relevant functional property information. Deep kernel active learning approaches have been utilized to rapidly map local structure to functional properties in microscopy experiments, but are computationally expensive for multi-dimensional and correlated output spaces. Here, we present an alternative lightweight curiosity algorithm which actively samples regions with unexplored structure-property relations, utilizing a deep-learning based surrogate model for error prediction. We show that the algorithm outperforms random sampling for predicting properties from structures, and provides a convenient tool for efficient mapping of structure-property relationships in materials science.

cond-mat.mtrl-sci↗

arXiv2025

Active Deep Kernel Learning of Molecular Properties: Realizing Dynamic Structural Embeddings

As vast databases of chemical identities become increasingly available, the challenge shifts to how we effectively explore and leverage these resources to study molecular properties. This paper presents an active learning approach for molecular discovery using Deep Kernel Learning (DKL), demonstrated on the QM9 dataset. DKL links structural embeddings directly to properties, creating organized latent spaces that prioritize relevant property information. By iteratively recalculating embedding vectors in alignment with target properties, DKL uncovers concentrated maxima representing key molecular properties and reveals unexplored regions with potential for innovation. This approach underscores DKL's potential in advancing molecular research and discovery.

cs.LG↗

arXiv2025

Active and transfer learning with partially Bayesian neural networks for materials and chemicals

Active learning, an iterative process of selecting the most informative data points for exploration, is crucial for efficient characterization of materials and chemicals property space. Neural networks excel at predicting these properties but lack the uncertainty quantification needed for active learning-driven exploration. Fully Bayesian neural networks, in which weights are treated as probability distributions inferred via advanced Markov Chain Monte Carlo methods, offer robust uncertainty quantification but at high computational cost. Here, we show that partially Bayesian neural networks (PBNNs), where only selected layers have probabilistic weights while others remain deterministic, can achieve accuracy and uncertainty estimates on active learning tasks comparable to fully Bayesian networks at lower computational cost. Furthermore, by initializing prior distributions with weights pre-trained on theoretical calculations, we demonstrate that PBNNs can effectively leverage computational predictions to accelerate active learning of experimental data. We validate these approaches on both molecular property prediction and materials science tasks, establishing PBNNs as a practical tool for active learning with limited, complex datasets.

cond-mat.dis-nn↗

arXiv2025

Building Workflows for Interactive Human in the Loop Automated Experiment (hAE) in STEM-EELS

Exploring the structural, chemical, and physical properties of matter on the nano- and atomic scales has become possible with the recent advances in aberration-corrected electron energy-loss spectroscopy (EELS) in scanning transmission electron microscopy (STEM). However, the current paradigm of STEM-EELS relies on the classical rectangular grid sampling, in which all surface regions are assumed to be of equal a priori interest. This is typically not the case for real-world scenarios, where phenomena of interest are concentrated in a small number of spatial locations. One of foundational problems is the discovery of nanometer- or atomic scale structures having specific signatures in EELS spectra. Here we systematically explore the hyperparameters controlling deep kernel learning (DKL) discovery workflows for STEM-EELS and identify the role of the local structural descriptors and acquisition functions on the experiment progression. In agreement with actual experiment, we observe that for certain parameter combinations the experiment path can be trapped in the local minima. We demonstrate the approaches for monitoring automated experiment in the real and feature space of the system and monitor knowledge acquisition of the DKL model. Based on these, we construct intervention strategies, thus defining human-in the loop automated experiment (hAE). This approach can be further extended to other techniques including 4D STEM and other forms of spectroscopic imaging.

cond-mat.mtrl-sci↗

arXiv2025

Autonomous scanning probe microscopy with hypothesis learning: Exploring the physics of domain switching in ferroelectric materials

We report the development and implementation of a hypothesis learning based automated experiment, in which the microscope operating in the autonomous mode identifies the physical laws behind the material's response. Specifically, we explore the bias induced transformations that underpin the functionality of broad classes of devices and functional materials from batteries and memristors to ferroelectrics and antiferroelectrics. Optimization and design of these materials require probing the mechanisms of these transformations on the nanometer scale as a function of the broad range of control parameters such as applied potential and time, often leading to experimentally intractable scenarios. At the same time, often the behaviors of these systems are understood within potentially competing theoretical models, or hypotheses. Here, we develop a hypothesis list that covers the possible limiting scenarios for the domain growth, including thermodynamic, domain wall pinning, and screening limited. We further develop and experimentally implement the hypothesis driven automated experiment in Piezoresponse Force Microscopy, autonomously identifying the mechanisms of the bias induced domain switching. This approach can be applied for a broad range of physical and chemical experiments with relatively low dimensional control parameter space and for which the possible competing models of the system behavior that ideally cover the full range of physical eventualities are known or can be created. These include other scanning probe microscopy modalities such as force distance curve measurements and nanoindentation, as well as materials synthesis and optimization.

cond-mat.mtrl-sci↗

arXiv2024

Predicting Battery Capacity Fade Using Probabilistic Machine Learning Models With and Without Pre-Trained Priors

Lithium-ion batteries are a key energy storage technology driving revolutions in mobile electronics, electric vehicles and renewable energy storage. Capacity retention is a vital performance measure that is frequently utilized to assess whether these batteries have approached their end-of-life. Machine learning (ML) offers a powerful tool for predicting capacity degradation based on past data, and, potentially, prior physical knowledge, but the degree to which an ML prediction can be trusted is of significant practical importance in situations where consequential decisions must be made based on battery state of health. This study explores the efficacy of fully Bayesian machine learning in forecasting battery health with the quantification of uncertainty in its predictions. Specifically, we implemented three probabilistic ML approaches and evaluated the accuracy of their predictions and uncertainty estimates: a standard Gaussian process (GP), a structured Gaussian process (sGP), and a fully Bayesian neural network (BNN). In typical applications of GP and sGP, their hyperparameters are learned from a single sample while, in contrast, BNNs are typically pre-trained on an existing dataset to learn the weight distributions before being used for inference. This difference in methodology gives the BNN an advantage in learning global trends in a dataset and makes BNNs a good choice when training data is available. However, we show that pre-training can also be leveraged for GP and sGP approaches to learn the prior distributions of the hyperparameters and that in the case of the pre-trained sGP, similar accuracy and improved uncertainty estimation compared to the BNN can be achieved. This approach offers a framework for a broad range of probabilistic machine learning scenarios where past data is available and can be used to learn priors for (hyper)parameters of probabilistic ML models.

cs.LG↗

arXiv2024

Measurements with Noise: Bayesian Optimization for Co-optimizing Noise and Property Discovery in Automated Experiments

We have developed a Bayesian optimization (BO) workflow that integrates intra-step noise optimization into automated experimental cycles. Traditional BO approaches in automated experiments focus on optimizing experimental trajectories but often overlook the impact of measurement noise on data quality and cost. Our proposed framework simultaneously optimizes both the target property and the associated measurement noise by introducing time as an additional input parameter, thereby balancing the signal-to-noise ratio and experimental duration. Two approaches are explored: a reward-driven noise optimization and a double-optimization acquisition function, both enhancing the efficiency of automated workflows by considering noise and cost within the optimization process. We validate our method through simulations and real-world experiments using Piezoresponse Force Microscopy (PFM), demonstrating the successful optimization of measurement duration and property exploration. Our approach offers a scalable solution for optimizing multiple variables in automated experimental workflows, improving data quality, and reducing resource expenditure in materials science and beyond.

cond-mat.mtrl-sci↗

arXiv2024

Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data

Active learning optimizes the exploration of large parameter spaces by strategically selecting which experiments or simulations to conduct, thus reducing resource consumption and potentially accelerating scientific discovery. A key component of this approach is a probabilistic surrogate model, typically a Gaussian Process (GP), which approximates an unknown functional relationship between control parameters and a target property. However, conventional GPs often struggle when applied to systems with discontinuities and non-stationarities, prompting the exploration of alternative models. This limitation becomes particularly relevant in physical science problems, which are often characterized by abrupt transitions between different system states and rapid changes in physical property behavior. Fully Bayesian Neural Networks (FBNNs) serve as a promising substitute, treating all neural network weights probabilistically and leveraging advanced Markov Chain Monte Carlo techniques for direct sampling from the posterior distribution. This approach enables FBNNs to provide reliable predictive distributions, crucial for making informed decisions under uncertainty in the active learning setting. Although traditionally considered too computationally expensive for 'big data' applications, many physical sciences problems involve small amounts of data in relatively low-dimensional parameter spaces. Here, we assess the suitability and performance of FBNNs with the No-U-Turn Sampler for active learning tasks in the 'small data' regime, highlighting their potential to enhance predictive accuracy and reliability on test functions relevant to problems in physical sciences.

cs.LG↗

arXiv2024

Evolution of ferroelectric properties in SmxBi1-xFeO3 via automated Piezoresponse Force Microscopy across combinatorial spread libraries

Combinatorial spread libraries offer a unique approach to explore evolution of materials properties over the broad concentration, temperature, and growth parameter spaces. However, the traditional limitation of this approach is the requirement for the read-out of functional properties across the library. Here we demonstrate the application of automated Piezoresponse Force Microscopy (PFM) for the exploration of the physics in the SmxBi1-xFeO3 system with the ferroelectric-antiferroelectric morphotropic phase boundary. This approach relies on the synergy of the quantitative nature of PFM and the implementation of automated experiments that allows PFM-based gird sampling over macroscopic samples. The concentration dependence of pertinent ferroelectric parameters has been determined and used to develop the mathematical framework based on Ginzburg-Landau theory describing the evolution of these properties across the concentration space. We pose that combination of automated scanning probe microscope and combinatorial spread library approach will emerge as an efficient research paradigm to close the characterization gap in the high-throughput materials discovery. We make the data sets open to the community and hope that will stimulate other efforts to interpret and understand the physics of these systems.

cond-mat.mtrl-sci↗

arXiv2024

Multiscale structure-property discovery via active learning in scanning tunneling microscopy

Atomic arrangements and local sub-structures fundamentally influence emergent material functionalities. The local structures are conventionally probed using spatially resolved studies and the property correlations are usually deciphered by a researcher based on sequential explorations and auxiliary information, thus limiting the throughput efficiency. Here we demonstrate a Bayesian deep learning based framework that automatically correlates material structure with its electronic properties using scanning tunneling microscopy (STM) measurements in real-time. Its predictions are used to autonomously direct exploration toward regions of the sample that optimize a given material property. This autonomous method is deployed on the low-temperature ultra-high vacuum STM to understand the structure-property relationship in a europium-based semimetal, EuZn2As2, one of the promising candidates for studying the magnetism-driven topological properties. The framework employs a sparse sampling approach to efficiently construct the scalar-property space using a minimal number of measurements, about 1 - 10 % of the data required in standard hyperspectral imaging methods. We further demonstrate a target-property-guided active learning of structures within a multiscale framework. This is implemented across length scales in a hierarchical fashion for the autonomous discovery of structural origins for an observed material property. This framework offers the choice to select and derive a suitable scalar property from the spectroscopic data to steer exploration across the sample space. Our findings reveal correlations of the electronic properties unique to surface terminations, local defect density, and point defects.

cond-mat.mtrl-sci↗

arXiv2024

Towards accelerating physical discovery via non-interactive and interactive multi-fidelity Bayesian Optimization: Current challenges and future opportunities

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and often non-differentiable parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, processing spaces, and molecular embedding spaces. Often these systems are expensive or time-consuming to evaluate a single instance, and hence classical approaches based on exhaustive grid or random search are too data intensive. This resulted in strong interest towards active learning methods such as Bayesian optimization (BO) where the adaptive exploration occurs based on human learning (discovery) objective. However, classical BO is based on a predefined optimization target, and policies balancing exploration and exploitation are purely data driven. In practical settings, the domain expert can pose prior knowledge on the system in form of partially known physics laws and often varies exploration policies during the experiment. Here, we explore interactive workflows building on multi-fidelity BO (MFBO), starting with classical (data-driven) MFBO, then structured (physics-driven) sMFBO, and extending it to allow human in the loop interactive iMFBO workflows for adaptive and domain expert aligned exploration. These approaches are demonstrated over highly non-smooth multi-fidelity simulation data generated from an Ising model, considering spin-spin interaction as parameter space, lattice sizes as fidelity spaces, and the objective as maximizing heat capacity. Detailed analysis and comparison show the impact of physics knowledge injection and on-the-fly human decisions for improved exploration, current challenges, and potential opportunities for algorithm development with combining data, physics and real time human decisions.

cs.LG↗

arXiv2023

Autonomous convergence of STM control parameters using Bayesian Optimization

Scanning Tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and its surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip-surface interaction, and thus limits the throughput efficiency. Here we deploy a machine learning (ML) based framework to achieve optimal-atomically resolved imaging conditions in real time. The experimental workflow leverages Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control-parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.

physics.app-ph↗

arXiv2023

Dynamic STEM-EELS for single atom and defect measurement during electron beam transformations

On- and off-axis electron energy loss spectroscopy (EELS) is a powerful method for probing local electronic structure on single atom level. However, many materials undergo electron-beam induced transformation during the scanning transmission electron microscopy (STEM) and spectroscopy, the problem particularly acute for off-axis EELS signals. Here, we propose and operationalize the rapid object detection and action system (RODAS) for dynamic exploration of the structure-property relationships in STEM-EELS. In this approach, the electron beam is used to induce dynamic transformations creating new defect types at sufficiently small rates and avoiding complete material destruction. The deep convolutional neural networks trained via the ensemble learning iterative training (ELIT) approach are used to identify the defects as they form and perform EELS measurements only at specific defect types. Overall, in this case the EEL spectra are collected only at predefined objects of interest, avoiding measurements on the ideal regions or holes. We note that this approach can be extended to identify new defect classes as they appear, allowing for efficient collection of structure-property relationship data via balanced sampling over defect types.

cond-mat.mtrl-sci↗