Results 191 to 200 of about 66,291 (256)

A Machine Learning Approach to Predict Functional Performance From Measurable Protein Structural Characteristics: A Screening Tool for Protein Ingredient Quality

Proteins: Structure, Function, and Bioinformatics, EarlyView.
ABSTRACT The food industry is witnessing the emergence of specialized protein‐based functional ingredients for the use as gelling, thickening, and/or emulsifying agents in various food applications. Different sources of protein including species and cultivars, as well as variable processing conditions affect the protein's structural characteristics ...
Ronit Mandal, Sara Malvar, Ranveer Chandra, Baraem P. Ismail   +3 more
wiley   +1 more source

Exploring neural manifolds across a wide range of intrinsic dimensions. [PDF]

PLoS Comput Biol
Fadanni J, Pacelli R, Zucchetta A, Rotondo P, Allegra M.   +4 more
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

Assimilation of machine‐learning‐predicted nitrate to improve the quality of phytoplankton forecasting in the shelf‐sea environment

Quarterly Journal of the Royal Meteorological Society, EarlyView.
This article demonstrates that assimilating machine‐learning‐derived surface nitrate can improve five‐day phytoplankton forecast substantially within the Met Office operational system for the Northwest European Shelf. We explain the reasons behind this improvement and propose that an online system where machine learning and data assimilation are cycled
Deep S. Banerjee, Jozef Skákala, David Ford   +2 more
wiley   +1 more source

Bivariate postprocessing of wind vectors

Quarterly Journal of the Royal Meteorological Society, EarlyView.
We introduce three novel bivariate postprocessing approaches and analyze their performance for joint postprocessing of bivariate wind‐vector components in Germany. Bivariate vine‐copula‐based models, a bivariate gradient‐boosted version of ensemble model output statistics (EMOS), and a bivariate distributional regression network (DRN) are compared with
Ferdinand Buchner, David Jobst, Annette Möller, Claudia Czado   +3 more
wiley   +1 more source

Inferring effective networks of spiking neurons using a continuous-time estimator of transfer entropy. [PDF]

PLoS Comput Biol
Shorten DP, Priesemann V, Wibral M, Lizier JT.   +3 more
europepmc   +1 more source

Hybrid physics–data‐driven modeling for sea ice thermodynamics and transfer learning

Quarterly Journal of the Royal Meteorological Society, EarlyView.
Icepack–NN, a machine‐learning‐based hybrid version of the sea‐ice column model Icepack, is developed to correct state‐dependent forecast errors arising from misspecified snow thermodynamics, using neural networks applied online within the physical model.
G. De Cillis, A. Carrassi, J. Brajard, L. Bertino, M. Broccoli, D. Iovino, T.S. Finn, M. Bocquet   +7 more
wiley   +1 more source

Multi-family wavelet-based feature engineering method for short-term time series forecasting. [PDF]

Sci Rep
Yemets K, Izonin I, Mitoulis SA.
europepmc   +1 more source

Deep Learning Decoding of Steady-State Visual Evoked Potential (SSVEP) for Real-Time Mobile Brain-Computer Interfaces: A Narrative Review from Laboratory Settings to Lightweight Engineering Applications. [PDF]

Brain Sci
Zhang H, Tao C.
europepmc   +1 more source