Downloads provided by UsageCounts
handle: 10902/17865
RESUMEN: Muchos de los modelos utilizados tradicionalmente como la regresión lineal no son capaces de encontrar las relaciones no lineales establecidas entre las variables predictoras utilizadas en los problemas de predicción meteorológica. Además, añadimos elementos como la dependencia temporal o la incertidumbre que lleva intrínseca la meteorología. En los últimos años los modelos de redes neuronales han resurgido y están demostrando sus capacidades en multitud de campos y la meteorología no podía ser excluida. Gracias a sus arquitecturas tan versátiles y altamente no lineales se convierten en una herramienta útil capaz de realizar predicciones con gran exactitud. Arquitecturas modernas como las redes LSTM nos permiten introducir dependencias temporales y abordar con éxito problemas de predicción de series temporales.
ABSTRACT: Many of traditional used models as linear regression are not able to find the non-linear relationships established among the predictive variables used in weather forecasting. In addition, elements such as temporal dependence or uncertainty, which is intrinsic to meteorology, are added to this problem. In recent years, neural network models have resurfaced and are showing their capabilities in many fields, meteorology could not be excluded. Thanks to its versatile and highly non-linear architectures, they become a useful tool capable of making predictions with great accuracy. Modern architectures like LSTM networks allow us to introduce temporary dependencies and deal successfully time series prediction problems.
Máster en Ciencia de Datos
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
| views | 99 | |
| downloads | 181 |

Views provided by UsageCounts
Downloads provided by UsageCounts