Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 1 de 1
Filtrar
Más filtros

Bases de datos
Tipo de estudio
Tipo del documento
Asunto de la revista
País de afiliación
Intervalo de año de publicación
1.
Nat Commun ; 13(1): 5145, 2022 09 01.
Artículo en Inglés | MEDLINE | ID: mdl-36050311

RESUMEN

Existing weather forecasting models are based on physics and use supercomputers to evolve the atmosphere into the future. Better physics-based forecasts require improved atmospheric models, which can be difficult to discover and develop, or increasing the resolution underlying the simulation, which can be computationally prohibitive. An emerging class of weather models based on neural networks overcome these limitations by learning the required transformations from data instead of relying on hand-coded physics and by running efficiently in parallel. Here we present a neural network capable of predicting precipitation at a high resolution up to 12 h ahead. The model predicts raw precipitation targets and outperforms for up to 12 h of lead time state-of-the-art physics-based models currently operating in the Continental United States. The results represent a substantial step towards validating the new class of neural weather models.


Asunto(s)
Aprendizaje Profundo , Simulación por Computador , Predicción , Redes Neurales de la Computación , Tiempo (Meteorología)
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA