On data selection for training wind forecasting neural networks

被引：5

作者：

Homsi Goulart, Antonio Jose ^{[1
]}

de Camargo, Ricardo ^{[1
]}

机构：

[1] Univ Sao Paulo, Inst Astron Geophys & Atmospher Sci, Sao Paulo, Brazil

来源：

COMPUTERS & GEOSCIENCES | 2021年 / 155卷

关键词：

Wind forecasting; Convolutional LSTM; Training data selection;

D O I：

10.1016/j.cageo.2021.104825

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this article we investigate the influence of meteorological data selection for the training of a neural network that predicts wind patterns. Different sets of meteorological information, distinct regions of the globe, various sizes for the observed area and different time windows are considered both for training and evaluation of the predicted winds. NCEP reanalysis 2 data was used to feed the neural network, which was based on a spatiotemporal architecture considering convolutions and recurrences. Besides achieving acceptable quality wind speed forecasts, the results for the contrasting cases highlight an integrative methodology for data selection when exploring machine learning in the geosciences.

引用

页数：10

共 50 条

[1] Forecasting of wind speed using feature selection and neural networks
[J]. Senthil Kumar, P. (senbe@rediffmail.com), 2016, International Journal of Renewable Energy Research (06):
[2] Forecasting of Wind Speed Using Feature Selection and Neural Networks
Kumar, Senthil P.
Lopez, Daphne
[J]. INTERNATIONAL JOURNAL OF RENEWABLE ENERGY RESEARCH, 2016, 6 (03): : 833 - 837
[3] Forecasting wind with neural networks
More, A
Deo, MC
[J]. MARINE STRUCTURES, 2003, 16 (01) : 35 - 49
[4] Selection of training data for neural networks by a genetic algorithm
Reeves, CR
Taylor, SJ
[J]. PARALLEL PROBLEM SOLVING FROM NATURE - PPSN V, 1998, 1498 : 633 - 642
[5] A training data selection in on-line training for multilayer neural networks
Hara, K
Nakayama, K
Kharaf, AAM
[J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 2247 - 2252
[6] Wind power forecasting based on meteorological data using neural networks
Sayenko, Yuriy
Pawelek, Ryszard
Liubartsev, Vadym
[J]. PRZEGLAD ELEKTROTECHNICZNY, 2021, 97 (11): : 207 - 210
[7] Training data selection method for generalization by multilayer neural networks
Hara, K
Nakayama, K
[J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1998, E81A (03) : 374 - 381
[8] Shallow Neural Networks to Deep Neural Networks for Probabilistic Wind Forecasting
Arora, Parul
Panigrahi, B. K.
Suganthan, P. N.
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION, AND INTELLIGENT SYSTEMS (ICCCIS), 2021, : 377 - 382
[9] Forecasting wind speed with recurrent neural networks
Cao, Qing
Ewing, Bradley T.
Thompson, Mark A.
[J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2012, 221 (01) : 148 - 154
[10] Wind speed forecasting using neural networks
Blanchard, Tyler
Samanta, Biswanath
[J]. WIND ENGINEERING, 2020, 44 (01) : 33 - 48

← 1 2 3 4 5 →