Results 141 to 150 of about 171,073 (263)

Integration of Liquid Handling Robotics, Turbidimetry, and Machine Learning Toward Inverse Design of Lower Critical Solution Temperature Polymer Formulations

open access: yesAdvanced Intelligent Systems, EarlyView.
An integrated OT‐2/plate reader platform automates LCST cloud point measurement of NIPAM‐co‐DMAEMA copolymers across high‐dimensional formulation spaces. Machine learning trained on the resulting high‐throughput datasets achieves R2 up to 0.96 and enables inverse design of polymer formulations to target transition temperatures with <1% error.
Lachlan Alexander   +2 more
wiley   +1 more source

Graph Neural Network‐Based Reinforcement Learning for Decentralized Multi‐Robot Manipulation

open access: yesAdvanced Intelligent Systems, EarlyView.
Robot arms lifting a large object face a trade‐off: centralized controllers explode in parameters, while decentralized ones cannot coordinate. A GNN resolves this—each arm runs its own network but acts on the full team state, achieving centralized‐level coordination with decentralized execution. Trained across team sizes, a single policy scales to four‐
Tong Chen   +3 more
wiley   +1 more source

Physics‐Informed Machine Learning for Predicting Phases and Density of Al2O3–TiB2 Composites Synthesized via Laser Ignition From the Al–TiO2–B2O3–H3BO3 Reactive System

open access: yesAdvanced Intelligent Systems, EarlyView.
This interactive physics‐informed machine learning model predicts the composition and density of advanced ceramic materials produced by self‐propagating high‐temperature synthesis. The model requires user input processing parameters and demonstrates high accuracy.
Evangelos Daskalakis   +4 more
wiley   +1 more source

ZEBRA‐Prop: A Zero‐Shot Embedding‐Based Rapid and Accessible Regression Model for Materials Properties

open access: yesAdvanced Intelligent Systems, EarlyView.
ZEBRA‐Prop makes language‐model‐based property prediction practical without specialized computing expertise or high‐performance computing systems. The framework predicts materials properties directly from natural‐language descriptions of crystal structures, integrating multiple descriptions through learnable weights while the language model stays ...
Ryoma Yamamoto   +4 more
wiley   +1 more source

Mirror versus Inversion Symmetry Breaking in Mesogenic Dimers: NTB versus NF Phase

open access: yesAngewandte Chemie, EarlyView.
Two non‐conventional nematic phases, twist‐bend NTB and ferroelectric NF, are observed within the same homologous series of dimers built of two strongly dipolar mesogenic units linked by a flexible spacer. The type of the phase formed depends on the molecular geometry, defined by parity of internal linkage.
Małgorzata Bakiera   +6 more
wiley   +2 more sources

Fourier and microlocal methods for quantum Rabi systems. [PDF]

open access: yesAnn Univ Ferrara Sez 7 Sci Mat
Malagutti M, Parmeggiani A.
europepmc   +1 more source

AI Dependence as a Longitudinal Governance Problem

open access: yesAI &Innovation, EarlyView.
ABSTRACT Artificial intelligence governance typically focuses on whether people rely on AI appropriately during individual decisions. This Perspective addresses a different question: whether repeated AI use changes the capabilities and alternatives available to users and organisations over time.
Yiran Du
wiley   +1 more source

PRISM, a Bidirectional NMR Foundation Model: From Peak List to Structure and Back

open access: yesAngewandte Chemie, EarlyView.
Structure elucidation from NMR can consume an expert for hours or even days. PRISM addresses this with a bidirectional transformer trained on 1.19 M real experimental spectra: it translates 1H and 13C peak lists into structures with 60.1% stereo‐aware top‐1 accuracy (72.5% stereo‐unaware), and, working in reverse, predicts spectra back from structures,
Ajnabiul Hoque, Frank Glorius
wiley   +2 more sources

Linking community structure and climate vulnerability in desert plant assemblages of southern California

open access: yesAmerican Journal of Botany, EarlyView.
Abstract Premise Desert plant assemblages in southern California provide an opportunity to link patterns of community structure with climate‐driven vulnerability in a rapidly changing environment. California sustains an exceptionally diverse flora of approximately 4300 plant species, with 31% identified as endemic.
Hector Zumbado‐Ulate   +4 more
wiley   +1 more source

Home - About - Disclaimer - Privacy