Results 211 to 220 of about 118,488 (274)

Predicting Drop‐Weight Impact Sensitivity From Molecular Graphs Using Physics‐Informed Artificial Intelligence

Propellants, Explosives, Pyrotechnics, EarlyView.
This work presents an approach for predicting the drop‐weight impact sensitivity of pure molecular explosives directly from 2D molecular graphs using physics‐informed artificial intelligence (AI) models. A dataset comprising experimentally measured sensitivities for 625 unique high‐explosive molecules is augmented with physics‐informed synthetic ...
Grant Hutchings, Jack V. Davis, Virginia W. Manner, Marc J. Cawkwell, Frank W. Marrs   +4 more
wiley   +1 more source

Hybrid deep learning model for air quality prediction and its impact on healthcare. [PDF]

Sci Rep
Madan T, Sagar S, Singh Y, Jain A, Krejcar O, Frischer R, Namazi H, Panwar A.   +7 more
europepmc   +1 more source

Reduced‐Order Modeling of Energetic Materials Using Physics‐Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)

Propellants, Explosives, Pyrotechnics, EarlyView.
Physics‐Aware Recurrent Convolutional Neural Networks (PARC) can reliably learn the thermomechanics of energetic materials as a function of morphology. This work introduces LatentPARC, which accelerates PARC by modeling the dynamics in a low‐dimensional latent space.
Zoë J. Gray, Joseph B. Choi, Youngsoo Choi, H. Keo Springer, H. S. Udaykumar, Stephen S. Baek   +5 more
wiley   +1 more source

Genetic risk predictions using deep learning models with summary data. [PDF]

Front Bioinform
Wang A, Xiao E, Cheng J, Shen X.
europepmc   +1 more source

Massive Sampling Strategy for Antibody–Antigen Targets in CAPRI Round 55 With MassiveFold

Proteins: Structure, Function, and Bioinformatics, EarlyView.
ABSTRACT Massive sampling with AlphaFold2 improves protein–protein complex predictions. This has been shown during the last CASP15‐CAPRI blind prediction round by the AFsample tool. However, more difficult targets including antibody–antigen binding remain challenging. CAPRI Round 55 consisted of three antibody–antigen targets and one heterotrimer.
Nessim Raouraoua, Marc F. Lensink, Guillaume Brysbaert   +2 more
wiley   +1 more source

Enhancing age and gender verification in OTT accounts using deep learning techniques. [PDF]

Front Artif Intell
Sanjay M, Manoj P, Graceline Jasmine S, Sriganth R, Febin Daya JL, Russel B.   +5 more
europepmc   +1 more source

Fendioxypyracil, a new and systemic PPO‐inhibiting herbicide for X‐spectrum weed control

Pest Management Science, EarlyView.
This graphical abstract presents the discovery and synthesis of PPO herbicide structures with a central pyridine core, showing molecular conformations, dose–response inhibition curves for PPO1 and PPO2, and comparative weed and grass control efficacy of fendioxypyracil versus other herbicides in greenhouse and field trials.
Tobias Seiser, Aimone Porri, Philipp Johnen, Silke Zeyer, Judith Wahrheit, Michael Betz, Breght Vandenberghe, Scott Asher, Liliana Parra Rapado   +8 more
wiley   +1 more source

Windows of opportunity in subseasonal weather regime forecasting: A statistical–dynamical approach

Quarterly Journal of the Royal Meteorological Society, EarlyView.
This study explores how the atmospheric state at initialisation creates windows of opportunity for improving week 3 forecasts of weather regime activity. Greenland blocking activity increases following Madden–Julian Oscillation phases 7, 8, and 1 and weak stratospheric polar vortex states, revealing patterns exploitable by statistical models.
Fabian Mockert, Christian M. Grams, Sebastian Lerch, Julian Quinting   +3 more
wiley   +1 more source

Activity constraints and the emergence of non-scale-free networks: Evidence from hip-hop and academia. [PDF]

PLoS One
Lee J, Li Y.
europepmc   +1 more source

A composite‐loss graph neural network for the multivariate post‐processing of ensemble weather forecasts

Quarterly Journal of the Royal Meteorological Society, EarlyView.
The dual graph neural network (dualGNN), trained with a composite loss combining the energy score (ES) and variogram score (VS), consistently outperformed models optimized solely for ES or the continuous ranked probability score in the multivariate setting, as well as empirical copula approaches.
Mária Lakatos
wiley   +1 more source