arXiv subjects

Sergei V Kalinin

Publications and source records attributed to Sergei V Kalinin.

4 recordsLinked to original sources

arXiv2026

PACE-SIMS: Checkpoint-Gated Autonomous SIMS Characterization with AI-Agent Quality Control

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is widely used for local chemical investigations across a broad range of materials and systems. However, its operation is expensive in expert time: a trained researcher must supervise the acquisition continuously, tuning parameters as the experiment proceeds, often across a campaign spanning multiple days. Here, we present PACE-SIMS (Pause-Assess-Correct-Execute for SIMS), an agentic workflow that runs a SIMS study as a human-AI collaboration. In this workflow, the researcher specifies the scientific questions and quality requirements, and an AI agent builds the plan and, after approval, executes it autonomously, pausing at checkpoints to judge each measurement and to correct, retry, or escalate. To validate the approach, we applied it to a study of chemical composition in 18O-enriched WOx films. During this randomized, blind two-polarity study (8.1 hours, 35 measurements), the agent applied three rule-governed corrections and diagnosed an unanticipated source excursion without requiring event-specific control logic to be programmed in advance. The same run returned transferable measurement science, including a composition calibration and the deposition's tracer-delivery mechanism, from less than two hours of researcher attention. The developed agentic architecture is not specific to SIMS and can be applied to other analytical techniques, with the primary target being destructive measurements, for which optimization-based methods are poorly suited.

cond-mat.mtrl-sci↗

arXiv2026

SPEAR: Structure Property Explainability with Attention Regularization

Machine learning is increasingly used to learn structure property relationships from spectroscopic and diffraction data, yet its adoption in materials discovery is often limited by poor interpretability of model predictions. Although attention mechanisms are frequently treated as inherently explainable, unregularized attention can yield unstable, fragmented, or intensity driven attribution patterns that obscure the physical origin of these relationships. Here we introduce SPEAR (Structure Property Explainability with Attention Regularization), a framework that constrains attention distributions during training to improve their stability, selectivity, and physical interpretability. SPEAR augments attention based regression with a learnable temperature that controls attention concentration and a smoothness penalty that enforces coherence across neighboring spectral positions, treating attention as a learnable explanatory object rather than a post hoc visualization. Using synthetic spectral benchmarks with known generative structure, we show that attention regularization produces smooth, contiguous attribution profiles aligned with causal features while preserving predictive accuracy. Applied to experimental X ray diffraction data from a combinatorial rare earth zirconate thin film library, the regularized model selectively emphasizes physically relevant diffraction features and decouples feature importance from raw peak intensity. The reflection it identified prompted a reassessment of our earlier structural analysis, revealing a correlation between the 220 peak position, the tetragonal distortion that accommodates cation size disorder, and the local thermal conductivity. Attention regularization therefore provides a principled training constraint for explainable structure property regression, yielding mechanistically meaningful explanations without sacrificing predictive performance.

cond-mat.mtrl-sci↗

arXiv2026

AI-assisted Human-in-the-Loop Web Platform for Structural Characterization in Hard drive design

Scanning transmission electron microscopy (STEM) has become a cornerstone instrument for semiconductor materials metrology, enabling nanoscale analysis of complex multilayer structures that define device performance. Developing effective metrology workflows for such systems requires balancing automation with flexibility; rigid pipelines are brittle to sample variability, while purely manual approaches are slow and subjective. Here, we present a tunable human-AI-assisted workflow framework that enables modular and adaptive analysis of STEM images for device characterization. As an illustrative example, we demonstrate a workflow for automated layer thickness and interface roughness quantification in multilayer thin films. The system integrates gradient-based peak detection with interactive correction modules, allowing human input at the design stage while maintaining fully automated execution across samples. Implemented as a web-based interface, it processes TEM/EMD files directly, applies noise reduction and interface tracking algorithms, and outputs statistical roughness and thickness metrics with nanometer precision. This architecture exemplifies a general approach toward adaptive, reusable metrology workflows - bridging human insight and machine precision for scalable, standardized analysis in semiconductor manufacturing. The code is made available at https://github.com/utkarshp1161/thickness-mapping-webapp

cond-mat.mtrl-sci↗

arXiv2024

Implementing dynamic high-performance computing supported workflows on Scanning Transmission Electron Microscope

Scanning Transmission Electron Microscopy (STEM) coupled with Electron Energy Loss Spectroscopy (EELS) presents a powerful platform for detailed material characterization via rich imaging and spectroscopic data. Modern electron microscopes can access multiple length scales and sampling rates far beyond human perception and reaction time. Recent advancements in machine learning (ML) offer a promising avenue to enhance these capabilities by integrating ML algorithms into the STEM-EELS framework, fostering an environment of active learning. This work enables the seamless integration of STEM with High-Performance Computing (HPC) systems. We present several implemented workflows that exemplify this integration. These workflows include sophisticated techniques such as object finding and Deep Kernel Learning (DKL). Through these developments, we demonstrate how the fusion of STEM-EELS with ML and HPC enhances the efficiency and scope of material characterization for 70% STEM available globally. The codes are available at GitHub link.

physics.ins-det↗