Engineering topics

Peng, Cheng (ORCID:0000000292671789)

Publications and source records attributed to Peng, Cheng (ORCID:0000000292671789).

3 records

DOE OSTI2026

An agentic artificially intelligent X-ray scientist

Executing experimental tasks in both normal research laboratories and large-scale scientific facilities often requires extensive human supervision and remains a key challenge on the path to fully autonomous, artificial intelligence (AI)-driven science. Here we demonstrate a large language model-driven agent that autonomously performs X-ray sample alignment on a synchrotron beamline by planning actions, executing instrumental commands, interpreting observations and iterating towards experimental goals. Based on existing large language models with structured tool-use via the model context protocol, our AI X-ray scientist was guided and tested using an in-house-built virtual experimental setup that mirrors a six-circle diffractometer at an operational synchrotron beamline. The agentic workflow developed in the virtual environment was directly deployed on a real beamline, where it correctly identified reference reflections and determined the orientation matrix, an essential first step in any type of single-crystal scattering experiment. Our AI X-ray scientist responded effectively to unexpected experimental conditions, demonstrating adaptive problem-solving and readiness for addressing practical experimental situations. Our study provides a step towards autonomous operation across diverse experimental environments at large-scale scattering facilities.

Chen, Zhantao (ORCID:0000000319543868)↗

DOE OSTI2026

Multi-resolution enhancement for full-spectrum neural representations

Scientific data acquisition continues to outpace storage and analysis capabilities, making voxel-basedrepresentations increasingly intractable. Implicit neural representations (INRs) offer a promising solutionby encoding signals through coordinate-based neural networks, serving as surrogates of data, withcomputational and storage requirements scaling with network complexity rather than data dimensionality.However, smaller INRs struggle to faithfully represent multiscale structures, high-frequency informationand fine textures that constitute a large proportion of scientific measurements. We propose WIEN-INR, atheoretically guided hierarchical INR framework that distributes modelling across resolution scales andenables improved representation capacity through a novel enhancement network to recover subtle details.This multiscale architecture allows smaller networks to retain the full spatial-frequency content of thesignal as well as preserve training efficiency and lower storage cost. Evaluated on distinct raw experimentalmeasurements across scales and complexities, WIEN-INR represents a practical step towards a broaderadoption of neural representations in scientific workflows, delivering compact, robust and high-fidelityrepresentations.

Ni, Yuan [SLAC National Accelerator Laboratory (SL↗

DOE OSTI2024

Kitaev physics in the two-dimensional magnet NiPSe 3

The Kitaev interaction, found in candidate materials such as α − RuCl 3 , occurs through the metal ( M )-ligand ( X )-metal ( M ) paths of the edge-sharing octahedra because the large spin-orbit coupling (SOC) on the metal atoms activates directional spin interactions. Here, we show that even in 3 d transition-metal compounds, where the SOC of the metal atom is negligible, heavy ligands can induce bond-dependent Kitaev interactions. In this work, we take as an example the 3 d transition-metal chalcogenophosphate NiPSe 3 and show that the key is found in the presence of a sizable SOC on the Se p orbital, one which mediates the super-exchange between the nearest-neighbor Ni sites. Our study provides a pathway for engineering enhanced Kitaev interactions through the interplay of SOC strength, lattice distortions, and chemical substitutions. Published by the American Physical Society 2024

36 MATERIALS SCIENCE↗