arXiv subjects

Rama Vasudevan

Publications and source records attributed to Rama Vasudevan.

At least 19 recordsLinked to original sources

arXiv2026

AEcroscopyWave: Towards Self-Driving Characterization Platforms for Agentic AI

The characterization of electronic materials has traditionally been stratified into two distinct regimens: industry-scale automated systems to inspect materials for defects and ensure quality (such as in the semiconductor industry), and highly customized, operator-driven systems requiring human experts. The former offers high throughput but limited flexibility, whereas the latter is heavily bandwidth-limited but provides research-grade discovery capabilities. Recent advances in "self-driving" characterization tools offer the potential to bridge the two stratified regimes, by the creation of application program interfaces (APIs) that can control hardware, and the integration of AI methods to incorporate autonomy into the process. Here, we discuss our latest developments in AEcroscopyWave, a custom-built characterization platform for the agentic-AI era, that provides unified control of scanning probe microscopes with programmable peripheral instrumentation, highlighting the design choices that are necessary for maximizing the capability of the system and the ease of use for both human and AI agents. The benefits of making heterogeneous scientific instruments accessible, composable and usable by agents is demonstrated by test cases.

cond-mat.mtrl-sci↗

arXiv2026

Accelerating Structure-Property Relationship Discovery with Multimodal Machine Learning and Self-Driving Microscopy

Microscopy combined with local spectroscopy is widely used to correlate nanoscale structure with functional properties in materials, but conventional measurements rely heavily on human-selected sampling locations and predefined targets, limiting dataset diversity and the potential for discovery. Here, we present a framework that integrates autonomous microscopy with a dual-novelty deep kernel learning (DN-DKL) for adaptive data acquisition and a dual variational autoencoder (VAE) for representation learning. DN-DKL actively guides the microscopy toward structurally and spectroscopically novel regions, enabling efficient collection of large spectral datasets. Dual-VAE embeds local structure and spectroscopic responses into a shared latent manifold that serves as a structure-property relationship map. We applied this framework for the investigation of halide perovskite films using conductive atomic force microscopy. The results reveal distinct hysteresis behaviors that are linked to specific nanoscale structural motifs, including grain boundary junction points that show hysteresis under different bias conditions and asymmetric grain boundaries that suppress charge transport. This framework establishes a general strategy that leverages the complementary strengths of self-driving microscopy, machine learning, and human expertise to accelerate scientific discovery in functional materials.

cond-mat.mtrl-sci↗

arXiv2026

Quality-Controlled Active Learning via Gaussian Processes for Robust Structure-Property Learning in Autonomous Microscopy

Autonomous experimental systems are increasingly used in materials research to accelerate scientific discovery, but their performance is often limited by low-quality, noisy data. This issue is especially problematic in data-intensive structure-property learning tasks such as Image-to-Spectrum (Im2Spec) and Spectrum-to-Image (Spec2Im) translations, where standard active learning strategies can mistakenly prioritize poor-quality measurements. We introduce a gated active learning framework that combines curiosity-driven sampling with a physics-informed quality control filter based on the Simple Harmonic Oscillator model fits, allowing the system to automatically exclude low-fidelity data during acquisition. Evaluations on a pre-acquired dataset of band-excitation piezoresponse spectroscopy (BEPS) data from PbTiO3 thin films with spatially localized noise show that the proposed method outperforms random sampling, standard active learning, and multitask learning strategies. The gated approach enhances both Im2Spec and Spec2Im by handling noise during training and acquisition, leading to more reliable forward and inverse predictions. In contrast, standard active learners often misinterpret noise as uncertainty and end up acquiring bad samples that hurt performance. Given its promising applicability, we further deployed the framework in real-time experiments on BiFeO3 thin films, demonstrating its effectiveness in real autonomous microscopy experiments. Overall, this work supports a shift toward hybrid autonomy in self-driving labs, where physics-informed quality assessment and active decision-making work hand-in-hand for more reliable discovery.

cs.LG↗

arXiv2026

Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale

Self-driving laboratories or autonomous experimentation are emerging as transformative platforms for accelerating scientific discovery. Bayesian optimization (BO) is among the most widely used machine learning frameworks for these purposes, but these BO-based frameworks rely on predefined scalar descriptors to guide experimentation. In many situations, the determination of an appropriate scalar descriptor can be challenging, and may fail to capture subtle yet scientifically important phenomena apparent to experts with interdisciplinary insight. To overcome this limitation, here we develop deep-kernel pairwise learning (DKPL), an approach for autonomous microscopy experiments which incorporates human expertise and interdisciplinary scientific knowledge into an active learning loop. Instead of relying on explicit scalar objectives, DKPL enables experts to directly evaluate which experimental output is more promising using interdisciplinary knowledge. DKPL then learns a latent utility function from these expert judgements to guide subsequent autonomous microscopy experiments. We demonstrate DKPL's performance in learning physically meaningful nanoscale structures while effectively prioritizing high-information measurement regions using an experimental model dataset with known ground truth. We further apply DKPL to analyze the character of ferroelectric domain walls, where we find DKPL capable of distinguishing between high and low characteristic domain-wall angles in bismuth ferrite, and able to discover both head-to-head and tail-to-tail domain-wall character in erbium manganite. This development establishes an approach to integrate expert knowledge into autonomous microscopy experiments and demonstrates a pathway toward expert-guided self-driving laboratories capable of addressing scientific problems beyond the limits of scalar-metrics-driven learning.

cs.LG↗

arXiv2025

Thermal and Size Effects in Ferroelastic Domains by Machine Learning

Ferroelastic domain walls (DWs) underpin key functionalities in complex oxides. In free-standing ferroic thin films, where elastic interactions are highly thickness dependent, understanding DW behaviour across length scales and external stimuli is crucial. A thickness-dependent monopolar-to-dipolar crossover in elastic DW behaviour has been reported; however, how temperature influences this regime remains unexplored. Here, LaAlO3 thin films spanning the dipolar ($<200$ nm) and crossover (200-300 nm) regimes are investigated using in situ heating scanning transmission electron microscopy (STEM) and a machine-learning-driven image analysis approach. By tracking DW curvature and density from above $T_C$ (approximately $550,^\circ$C) to room temperature (RT), a distinct interplay between temperature and thickness is identified. In the dipolar regime, DWs are mobile and curved near $T_C$ and gradually freeze upon cooling, consistent with the well-known temperature freezing regime. In contrast, within the crossover regime, DWs are nearly static, with minimal reconfiguration through cooling and curvature an order of magnitude lower at RT. These results map the evolution of DWs across the thermally driven super-elastic to freezing regimes, revealing how thickness and temperature govern DW morphology and dynamics, and providing insight relevant for domain engineering in free-standing oxide thin films.

cond-mat.mtrl-sci↗

arXiv2025

Auto-3DPFM: Automating Polarization-Vector Mapping at the Nanoscale

The functional properties of ferroelectric materials are strongly influenced by ferroelectric polarization orientation; as such, access to consistent and precise characterization of polarization vectors is of substantial importance to ferroelectrics research. Here, we develop a fully automated three-dimensional piezoresponse force microscopy (Auto-3DPFM) technique automating all essential steps in interferometric PFM for 3D polarization vector characterization, including laser alignment, tip calibration and approach, image acquisition, polarization vector reconstruction, and visualization. The automation reduces the experimental burden of ferroelectric polarization vector characterization, while the back-and-forth calibration ensures consistency and reproducibility of 3D polarization reconstruction. An algorithmic workflow is also developed to identify domain walls and calculate their characteristic angles via a spatial vector-angle-difference method, presenting one unique capability enabled by Auto-3DPFM that is not accessible with traditional PFM techniques. Beyond representing a significant step forward in 3D polarization mapping, Auto-3DPFM promises to accelerate discovery via high-throughput and autonomous characterization in ferroelectric materials research. When integrated with machine learning and adaptive sampling strategies in self-driving labs, Auto-3DPFM will serve as a valuable tool for advancing ferroelectric physics and microelectronics development.

cond-mat.mtrl-sci↗

arXiv2025

Automated Construction of Artificial Lattice Structures with Designer Electronic States

Manipulating matter with a scanning tunneling microscope (STM) enables creation of atomically defined artificial structures that host designer quantum states. However, the time-consuming nature of the manipulation process, coupled with the sensitivity of the STM tip, constrains the exploration of diverse configurations and limits the size of designed features. In this study, we present a reinforcement learning (RL)-based framework for creating artificial structures by spatially manipulating carbon monoxide (CO) molecules on a copper substrate using the STM tip. The automated workflow combines molecule detection and manipulation, employing deep learning-based object detection to locate CO molecules and linear assignment algorithms to allocate these molecules to designated target sites. We initially perform molecule maneuvering based on randomized parameter sampling for sample bias, tunneling current setpoint and manipulation speed. This dataset is then structured into an action trajectory used to train an RL agent. The model is subsequently deployed on the STM for real-time fine-tuning of manipulation parameters during structure construction. Our approach incorporates path planning protocols coupled with active drift compensation to enable atomically precise fabrication of structures with significantly reduced human input while realizing larger-scale artificial lattices with desired electronic properties. Using our approach, we demonstrate the automated construction of an extended artificial graphene lattice and confirm the existence of characteristic Dirac point in its electronic structure. Further challenges to RL-based structural assembly scalability are discussed.

cond-mat.mtrl-sci↗

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

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

Autonomous Fabrication of Tailored Defect Structures in 2D Materials using Machine Learning-enabled Scanning Transmission Electron Microscopy

Materials with tailored quantum properties can be engineered from atomic scale assembly techniques, but existing methods often lack the agility and accuracy to precisely and intelligently control the manufacturing process. Here we demonstrate a fully autonomous approach for fabricating atomic-level defects using electron beams in scanning transmission electron microscopy (STEM) that combines advanced machine learning and automated beam control. As a proof of concept, we achieved controlled fabrication of MoS-nanowire (MoS-NW) edge structures by iterative and targeted exposure of $MoS_2$ monolayer to a focused electron beam to selectively eject sulfur atoms, utilizing high-angle annular dark-field (HAADF) imaging for feedback-controlled monitoring structural evolution of defects. A machine learning framework combining a random forest model and convolutional neural networks (CNN) was developed to decode the HAADF image and accurately identify atomic positions and species. This atomic-level information was then integrated into an autonomous decision-making platform, which applied predefined fabrication strategies to instruct beam control about atomic sites to be ejected. The selected sites were subsequently exposed to localized electron beam using an FPGA-controlled scan routine with precise control over beam positioning and duration. While the MoS-NW edge structures produced exhibit promising mechanical and electronic properties, the proposed autonomous fabrication framework is material-agnostic and can be extended to other 2D materials for the creation of diverse defect structures and heterostructures beyond $MoS_2$.

cond-mat.mtrl-sci↗

arXiv2025

Mic-hackathon 2024: Hackathon on Machine Learning for Electron and Scanning Probe Microscopy

Microscopy is a primary source of information on materials structure and functionality at nanometer and atomic scales. The data generated is often well-structured, enriched with metadata and sample histories, though not always consistent in detail or format. The adoption of Data Management Plans (DMPs) by major funding agencies promotes preservation and access. However, deriving insights remains difficult due to the lack of standardized code ecosystems, benchmarks, and integration strategies. As a result, data usage is inefficient and analysis time is extensive. In addition to post-acquisition analysis, new APIs from major microscope manufacturers enable real-time, ML-based analytics for automated decision-making and ML-agent-controlled microscope operation. Yet, a gap remains between the ML and microscopy communities, limiting the impact of these methods on physics, materials discovery, and optimization. Hackathons help bridge this divide by fostering collaboration between ML researchers and microscopy experts. They encourage the development of novel solutions that apply ML to microscopy, while preparing a future workforce for instrumentation, materials science, and applied ML. This hackathon produced benchmark datasets and digital twins of microscopes to support community growth and standardized workflows. All related code is available at GitHub: https://github.com/KalininGroup/Mic-hackathon-2024-codes-publication/tree/1.0.0.1

cond-mat.mtrl-sci↗

arXiv2025

Ferroelastic Domain Induced Electronic Modulation in Halide Perovskites

Lead halide perovskites have emerged as promising materials for optoelectronic applications due to their exceptional properties. In the all-inorganic CsPbBr3 perovskites, ferroelastic domains formed during phase transitions enhance bulk transport and emissive efficiency. However, the microscopic mechanisms governing carrier dynamics remain poorly understood. In this study, we employ cathodoluminescence (CL) and micro-Raman spectroscopy to image and investigate the electronic properties of the ferroelastic domain walls in CsPbBr3 single crystals. CL measurements reveal a reduced emissive yield and a slight redshift in emission at the domain walls. Further, micro-Raman studies provide spatially resolved mapping of vibrational modes, exhibiting second-order phonon modes localized at the domain boundaries. Our findings suggest that electron-phonon coupling at twin domain walls plays a critical role in facilitating efficient charge separation, thereby improving the optoelectronic performance of the CsPbBr3 perovskites.

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

Non-perturbative cathodoluminescence microscopy of beam-sensitive materials

Cathodoluminescence microscopy is now a well-established and powerful tool for probing the photonic properties of nanoscale materials, but in many cases, nanophotonic materials are easily damaged by the electron-beam doses necessary to achieve reasonable cathodoluminescence signal-to-noise ratios. Two-dimensional materials have proven particularly susceptible to beam-induced modifications, yielding both obstacles to high spatial-resolution measurement and opportunities for beam-induced patterning of quantum photonic systems. Here pan-sharpening techniques are applied to cathodoluminescence microscopy in order to address these challenges and experimentally demonstrate the promise of pan-sharpening for minimally-perturbative high-spatial-resolution spectrum imaging of beam-sensitive materials.

physics.optics↗

arXiv2024

SANE: Strategic Autonomous Non-Smooth Exploration for Multiple Optima Discovery in Multi-modal and Non-differentiable Black-box Functions

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and multimodal parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, material structure image spaces, and molecular embedding spaces. Often these systems are black-box and time-consuming to evaluate, which resulted in strong interest towards active learning methods such as Bayesian optimization (BO). However, these systems are often noisy which make the black box function severely multi-modal and non-differentiable, where a vanilla BO can get overly focused near a single or faux optimum, deviating from the broader goal of scientific discovery. To address these limitations, here we developed Strategic Autonomous Non-Smooth Exploration (SANE) to facilitate an intelligent Bayesian optimized navigation with a proposed cost-driven probabilistic acquisition function to find multiple global and local optimal regions, avoiding the tendency to becoming trapped in a single optimum. To distinguish between a true and false optimal region due to noisy experimental measurements, a human (domain) knowledge driven dynamic surrogate gate is integrated with SANE. We implemented the gate-SANE into a pre-acquired Piezoresponse spectroscopy data of a ferroelectric combinatorial library with high noise levels in specific regions, and a piezoresponse force microscopy (PFM) hyperspectral data. SANE demonstrated better performance than classical BO to facilitate the exploration of multiple optimal regions and thereby prioritized learning with higher coverage of scientific values in autonomous experiments. Our work showcases the potential application of this method to real-world experiment, where such combined strategic and human intervening approaches can be critical to unlocking new discoveries in autonomous research.

cs.LG↗

arXiv2024

Large Bandgap Observed on the Surfaces of EuZn2As2 Single Crystals

EuM2As2 (M = Zn, Cd, In, Sn etc.) is an excellent material system for studying topological properties, which can be easily tuned by magnetism involved. Theoretical calculations predict gapped and flat bands in EuZn2As2 but gapless structure in EuCd2As2. In this work, low-temperature (77 K) cleaved EuZn2As2 crystals are studied using scanning tunneling microscopy/spectroscopy (STM/S) and density functional theory (DFT) calculations. Defects-induced local density of states (LDOS) modification with a triangular shape helps identify the surface terminations: Eu versus AsZn surface. While large bandgaps (~1.5 eV at 77 K) are observed on both pristine surfaces, the bandgap width is found to be very sensitive to local heterogeneity, such as defects and step edges, with the tendency of reduction. Combining experimental data with DFT simulations, we conclude that the modified bandgap in the heterogeneous area arises from Zn vacancies and/or substitution by As atoms. Our investigation offers important information for reevaluating the electron topology of the EuM2As2 family.

cond-mat.mtrl-sci↗

arXiv2024

Scientific Exploration with Expert Knowledge (SEEK) in Autonomous Scanning Probe Microscopy with Active Learning

Microscopy techniques have played vital roles in materials science, biology, and nanotechnology, offering high-resolution imaging and detailed insights into properties at nanoscale and atomic level. The automation of microscopy experiments, in combination with machine learning approaches, is a transformative advancement, offering increased efficiency, reproducibility, and the capability to perform complex experiments. Our previous work on autonomous experimentation with scanning probe microscopy (SPM) demonstrated an active learning framework using deep kernel learning (DKL) for structure-property relationship discovery. This approach has demonstrated broad applications in various microscopy techniques. Here, to address limitations of workflows based on DKL, we developed methods to incorporate prior knowledge and human interest into DKL-based workflows and implemented these workflows in SPM. By integrating expected rewards from structure libraries or spectroscopic features, we enhanced the exploration efficiency of autonomous microscopy, demonstrating more efficient and targeted exploration in autonomous microscopy. We demonstrated the application of these methods in SPM, but we suggest that these methods can be seamlessly applied to other microscopy and imaging techniques. Furthermore, the concept can be adapted for general Bayesian optimization in material discovery across a broad range of autonomous experimental fields.

cond-mat.mtrl-sci↗

arXiv2024

Active oversight and quality control in standard Bayesian optimization for autonomous experiments

The fusion of experimental automation and machine learning has catalyzed a new era in materials research, prominently featuring Gaussian Process Bayesian Optimization (GPBO) driven autonomous experiments navigating complex experimental conditions for accelerated scientific discovery. In traditional GPBO-driven experiments, a predefined scalarizer function is often required to preprocess the experimental data, transforming non-scalar raw data into scalar descriptors for GP training. However, such predefined scalarizer functions have limitations, which likely fail to accommodate the diversity and complexity of real-world experimental data, potentially skewing experimental outcomes. Thus, oversight and quality control are necessitated over the process to avoid GPBO from being misled by low quality scalarizers. To address the limitation, we introduce a Dual-GP approach that enhances traditional GPBO by adding a secondary surrogate model to dynamically constrain the experimental space based on real-time assessments of the raw experimental data. This Dual-GP approach enhances the optimization efficiency of traditional GPBO by isolating more promising space for BO sampling and more valuable experimental data for primary GP training. We also incorporate a flexible, human-in-the-loop intervention method in the Dual-GP workflow to adjust for unanticipated results. We demonstrate the effectiveness of the Dual-GP model with synthetic model data and implement this approach in autonomous pulsed laser deposition experimental data. This Dual-GP approach has broad applicability in diverse GPBO-driven experimental settings, providing a more adaptable and precise framework for refining autonomous experimentation for more efficient optimization.

cond-mat.mtrl-sci↗