Deep coastal sea elements forecasting using UNet-based models

被引：12

作者：

Fernández J.G. ^{[2
]}

Abdellaoui I.A. ^{[2
]}

Mehrkanoon S. ^{[1
,2
]}

机构：

[1] Information and Computing Sciences, Utrecht University, Utrecht

[2] Department of Data Science and Knowledge Engineering, Maastricht University

来源：

Knowledge-Based Systems | 2022年 / 252卷

关键词：

Coastal sea elements; Convolutional neural networks; Deep learning; Time-series satellite data; UNet;

D O I：

10.1016/j.knosys.2022.109445

中图分类号：

学科分类号：

摘要：

Due to the recent development of deep learning techniques applied to satellite imagery, weather forecasting that uses remote sensing data has also been the subject of major progress. The present paper investigates multiple hours ahead coastal sea elements forecasting in the Netherlands using UNet based architectures. The hourly satellite image data from the Copernicus observation program spanned over a period of two years has been used to train the models and make the forecasting, including seasonal forecasting. Here, we propose 3D dimension Reducer UNet (3DDR-UNet), a variation of the UNet architecture, and further extend this novel model using residual connections, parallel convolutions and asymmetric convolutions which result in introducing three additional architectures, i.e. Res-3DDR-UNet, InceptionRes-3DDR-UNet and AsymmInceptionRes-3DDR-UNet respectively. In particular, we show that the architecture equipped with parallel and asymmetric convolutions as well as skip connections outperforms the other three discussed models. © 2022 The Author(s)

引用

共 56 条

[1]

Katz R.W., Murphy A.H., Economic Value of Weather and Climate Forecasts, (2005)

[2]

da Silva R.G., Ribeiro M.H.D.M., Moreno S.R., Mariani V.C., dos Santos Coelho L., A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting, Energy, 216, (2021)

[3]

Moreno S.R., Mariani V.C., dos Santos Coelho L., Hybrid multi-stage decomposition with parametric model applied to wind speed forecasting in Brazilian Northeast, Renew. Energy, 164, pp. 1508-1526, (2021)

[4]

Liu Z., Hara R., Kita H., Hybrid forecasting system based on data area division and deep learning neural network for short-term wind speed forecasting, Energy Convers. Manage., 238, (2021)

[5]

Moreno S.R., da Silva R.G., Mariani V.C., dos Santos Coelho L., Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network, Energy Convers. Manage., 213, (2020)

[6]

Lorenc A.C., Analysis methods for numerical weather prediction, Q. J. R. Meteorol. Soc., 112, 474, pp. 1177-1194, (1986)

[7]

Bauer P., Thorpe A., Brunet G., The quiet revolution of numerical weather prediction, Nature, 525, 7567, pp. 47-55, (2015)

[8]

Glahn H.R., Statistical weather forecasting, Probability, Statistics, and Decision Making in the Atmospheric Sciences, pp. 289-335, (1985)

[9]

Holtslag A., De Bruijn E., Pan H., A high resolution air mass transformation model for short-range weather forecasting, Mon. Weather Rev., 118, 8, pp. 1561-1575, (1990)

[10]

Saito K., Seko H., Kuroda T., Fujita T., Kawabata T., Aonashi K., Tsuyuki T., Next generation supercomputer project toward cloud resolving NWP, CAS/JSC WGNE Res. Act. Atmos. Ocea. Model, 41, pp. 5-19, (2011)

← 1 2 3 4 5 6 →