Building machine‐readable vocabularies for materials science is slow, expert‐driven work. This study benchmarks 13 large language models on two of its first steps: finding candidate terms in engineering articles and deciding where they belong in a class hierarchy.
Thomas Bjarsch +3 more
wiley +1 more source
A knowledge-driven unified framework for plant disease classification and severity grading via domain adaptation. [PDF]
Yuan Z +8 more
europepmc +1 more source
A Lightweight Procedural Layer for Hybrid Experimental–Computational Workflows in Materials Science
We unveil a prototype hybrid‐workflow framework that fuses automatedcomputation with hands‐on experiments. Built atop pyiron, a lightweight, parameterized layer translates procedure descriptions into executable manual steps, syncing instrument settings, human interventions, and data capture in real‐time today.
Steffen Brinckmann +8 more
wiley +1 more source
Enhanced RNA-Seq Expression Profiling and Functional Enrichment in Non-model Organisms Using Custom Annotations. [PDF]
Eden M IST, Vetrivel U.
europepmc +1 more source
Do not let thermal drift and instrument artifacts deceive high‐temperature nanoindentation results. We compare classical Oliver–Pharr and automatic image recognition analyses across steels and a Ni alloy to quantify these effects. Accounting for artifacts reveals systematic softening with temperature, while Cr and Ni additions boost resistance ...
Velislava Yonkova +2 more
wiley +1 more source
Combination of Chromatographic and Machine Learning-Driven Virtual Fractionation Identifies Aryl Hydrocarbon Receptor Agonists in Sediments. [PDF]
Wang H +5 more
europepmc +1 more source
Optimization of the Production of Rubber Compounds Using Mathematical Models
Rubber compounds were mixed in a batch internal mixer, and symbolic regression was used to derive mathematical models linking recipe and process parameters to ram path, torque, and mixing quality (incorporation, dispersion, distribution). Subsequent optimization with evolutionary algorithms identified operating conditions that reduce specific energy ...
Anke Bardehle +7 more
wiley +1 more source
Using a modular massively parallel reporter assay to discover context-dependent regulatory activity in type 2 diabetes-linked noncoding regions. [PDF]
Tovar A +6 more
europepmc +1 more source
Low‐voltage FIB‐SEM tomography combined with a image preprocessing pipeline improves phase contrast and enables reliable machine‐learning segmentation of conductive networks in lithium‐ion battery electrodes. Structural descriptors are extracted from segmented images, done semimanually and automated, and compared.
Lisa Beran +6 more
wiley +1 more source
PlasticAnalytics: A Deep Learning-Powered Spectral Library and Analytical Suite. [PDF]
Levermore DJM, Kelly PFJ, Wright DSL.
europepmc +1 more source

