Publication type: | Conference paper |
Type of review: | Peer review (publication) |
Title: | A hybrid deep learning approach for forecasting air temperature |
Authors: | Gygax, Gregory Schüle, Martin |
et. al: | No |
DOI: | 10.1007/978-3-030-58309-5_19 |
Proceedings: | Artificial Neural Networks in Pattern Recognition |
Editors of the parent work: | Schilling, Frank-Peter Stadelmann, Thilo |
Page(s): | 235 |
Pages to: | 246 |
Conference details: | 9th IAPR TC 3 Workshop on Artificial Neural Networks for Pattern Recognition (ANNPR'20), Winterthur, Switzerland, 2-4 September 2020 |
Issue Date: | 2-Sep-2020 |
Series: | Lecture Notes in Computer Science |
Series volume: | 12294 |
Publisher / Ed. Institution: | Springer |
Publisher / Ed. Institution: | Cham |
ISBN: | 978-3-030-58308-8 978-3-030-58309-5 |
Language: | English |
Subjects: | Machine learning; Deep learning; Weather prediction |
Subject (DDC): | 006: Special computer methods 551: Geology and hydrology |
Abstract: | Forecasting the weather is a great scientific challenge. Physics-based, numerical weather prediction (NWP) models have been developed for decades by large research teams and the accuracy of forecasts has been steadily increased. Yet, recently, more and more data-driven machine learning approaches to weather forecasting are being developed. In this contribution we aim to develop an approach that combines the advantages of both methodologies, that is, we develop a deep learning model to predict air temperature that is trained both on NWP models and local weather data. We evaluate the approach for 249 weather station sites in Switzerland and find that the model outperfoms the NWP models on short time-scales and in some geographically distinct regions of Switzerland. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/20891 |
Fulltext version: | Published version |
License (according to publishing contract): | Licence according to publishing contract |
Departement: | Life Sciences and Facility Management |
Organisational Unit: | Institute of Computational Life Sciences (ICLS) |
Published as part of the ZHAW project: | An integrated modelling and learning framework for real-time online decision assistance in Swiss agriculture |
Appears in collections: | Publikationen Life Sciences und Facility Management |
Files in This Item:
There are no files associated with this item.
Show full item record
Gygax, G., & Schüle, M. (2020). A hybrid deep learning approach for forecasting air temperature [Conference paper]. In F.-P. Schilling & T. Stadelmann (Eds.), Artificial Neural Networks in Pattern Recognition (pp. 235–246). Springer. https://doi.org/10.1007/978-3-030-58309-5_19
Gygax, G. and Schüle, M. (2020) ‘A hybrid deep learning approach for forecasting air temperature’, in F.-P. Schilling and T. Stadelmann (eds) Artificial Neural Networks in Pattern Recognition. Cham: Springer, pp. 235–246. Available at: https://doi.org/10.1007/978-3-030-58309-5_19.
G. Gygax and M. Schüle, “A hybrid deep learning approach for forecasting air temperature,” in Artificial Neural Networks in Pattern Recognition, Sep. 2020, pp. 235–246. doi: 10.1007/978-3-030-58309-5_19.
GYGAX, Gregory und Martin SCHÜLE, 2020. A hybrid deep learning approach for forecasting air temperature. In: Frank-Peter SCHILLING und Thilo STADELMANN (Hrsg.), Artificial Neural Networks in Pattern Recognition. Conference paper. Cham: Springer. 2 September 2020. S. 235–246. ISBN 978-3-030-58308-8
Gygax, Gregory, and Martin Schüle. 2020. “A Hybrid Deep Learning Approach for Forecasting Air Temperature.” Conference paper. In Artificial Neural Networks in Pattern Recognition, edited by Frank-Peter Schilling and Thilo Stadelmann, 235–46. Cham: Springer. https://doi.org/10.1007/978-3-030-58309-5_19.
Gygax, Gregory, and Martin Schüle. “A Hybrid Deep Learning Approach for Forecasting Air Temperature.” Artificial Neural Networks in Pattern Recognition, edited by Frank-Peter Schilling and Thilo Stadelmann, Springer, 2020, pp. 235–46, https://doi.org/10.1007/978-3-030-58309-5_19.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.