Next Article in Journal
Life Cycle Assessment of Classic and Innovative Batteries for Solar Home Systems in Europe
Next Article in Special Issue
Improving Thermochemical Energy Storage Dynamics Forecast with Physics-Inspired Neural Network Architecture
Previous Article in Journal
Efficient Production of Clean Power and Hydrogen Through Synergistic Integration of Chemical Looping Combustion and Reforming
Open AccessArticle

Localized Convolutional Neural Networks for Geospatial Wind Forecasting

Faculty of Informatics, Kaunas University of Technology, LT-51368 Kaunas, Lithuania
*
Authors to whom correspondence should be addressed.
Energies 2020, 13(13), 3440; https://doi.org/10.3390/en13133440
Received: 19 May 2020 / Revised: 19 June 2020 / Accepted: 24 June 2020 / Published: 3 July 2020
(This article belongs to the Special Issue Machine Learning and Deep Learning for Energy Systems)
Convolutional Neural Networks (CNN) possess many positive qualities when it comes to spatial raster data. Translation invariance enables CNNs to detect features regardless of their position in the scene. However, in some domains, like geospatial, not all locations are exactly equal. In this work, we propose localized convolutional neural networks that enable convolutional architectures to learn local features in addition to the global ones. We investigate their instantiations in the form of learnable inputs, local weights, and a more general form. They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed. In this work we address spatio-temporal prediction: test the effectiveness of our methods on a synthetic benchmark dataset and tackle three real-world wind prediction datasets. For one of them, we propose a method to spatially order the unordered data. We compare the recent state-of-the-art spatio-temporal prediction models on the same data. Models that use convolutional layers can be and are extended with our localizations. In all these cases our extensions improve the results, and thus often the state-of-the-art. We share all the code at a public repository. View Full-Text
Keywords: convolutional neural networks; recurrent neural networks; deep learning; machine learning; spatial-temporal wind forecasting convolutional neural networks; recurrent neural networks; deep learning; machine learning; spatial-temporal wind forecasting
Show Figures

Figure 1

MDPI and ACS Style

Uselis, A.; Lukoševičius, M.; Stasytis, L. Localized Convolutional Neural Networks for Geospatial Wind Forecasting. Energies 2020, 13, 3440. https://doi.org/10.3390/en13133440

AMA Style

Uselis A, Lukoševičius M, Stasytis L. Localized Convolutional Neural Networks for Geospatial Wind Forecasting. Energies. 2020; 13(13):3440. https://doi.org/10.3390/en13133440

Chicago/Turabian Style

Uselis, Arnas; Lukoševičius, Mantas; Stasytis, Lukas. 2020. "Localized Convolutional Neural Networks for Geospatial Wind Forecasting" Energies 13, no. 13: 3440. https://doi.org/10.3390/en13133440

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop