Neural networks for predicting the output of wind flow simulations over complex topographies
| dc.contributor.author | Mayo, Michael | en_NZ |
| dc.contributor.author | Wakes, Sarah | en_NZ |
| dc.contributor.author | Anderson, Chris | en_NZ |
| dc.contributor.editor | Wu, X. | en_NZ |
| dc.contributor.editor | Soon, O.Y. | en_NZ |
| dc.contributor.editor | Aggarwal, C. | en_NZ |
| dc.contributor.editor | Chen, H. | en_NZ |
| dc.coverage.spatial | Singapore | en_NZ |
| dc.date.accessioned | 2019-02-11T01:16:55Z | |
| dc.date.available | 2018 | en_NZ |
| dc.date.available | 2019-02-11T01:16:55Z | |
| dc.date.issued | 2018 | en_NZ |
| dc.description.abstract | We use deep learning techniques to model computational fluid dynamics (CFD) simulations of wind flow over a complex topography. Our motivation is to "speed up" the optimisation of CFD-based simulations (such as the 3D wind farm layout optimisation problem) by developing surrogate models capable of predicting the output of a simulation at any given point in 3D space, given output from a set of training simulations that have already been run. Our promising results using TensorFlow show that deep neural networks can be learned to model CFD outputs with an error of as low as 2.5 meters per second. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | Mayo, M., Wakes, S., & Anderson, C. (2018). Neural networks for predicting the output of wind flow simulations over complex topographies. In X. Wu, O. Y. Soon, C. Aggarwal, & H. Chen (Eds.), Proceedings of 2018 IEEE International Conference on Big Knowledge (ICBK) (pp. 184–191). Washington, DC, USA: IEEE. https://doi.org/10.1109/ICBK.2018.00032 | en |
| dc.identifier.doi | 10.1109/ICBK.2018.00032 | en_NZ |
| dc.identifier.isbn | 978-1-5386-9125-0 | en_NZ |
| dc.identifier.uri | https://hdl.handle.net/10289/12319 | |
| dc.language.iso | en | |
| dc.publisher | IEEE | en_NZ |
| dc.relation.isPartOf | Proceedings of 2018 IEEE International Conference on Big Knowledge (ICBK) | en_NZ |
| dc.rights | This is an author’s accepted version of an article published in the Proceedings of 2018 IEEE International Conference on Big Knowledge (ICBK). © 2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. | |
| dc.source | ICBK 2018 | en_NZ |
| dc.subject | computer science | en_NZ |
| dc.subject | wind farm layout optimisation | en_NZ |
| dc.subject | deep learning | en_NZ |
| dc.subject | computational fluid dynamics | en_NZ |
| dc.subject | wind flow modelling | en_NZ |
| dc.subject | complex topography | en_NZ |
| dc.subject | Machine learning | |
| dc.title | Neural networks for predicting the output of wind flow simulations over complex topographies | en_NZ |
| dc.type | Conference Contribution | |
| dspace.entity.type | Publication | |
| pubs.begin-page | 184 | |
| pubs.end-page | 191 | |
| pubs.finish-date | 2018-11-18 | en_NZ |
| pubs.place-of-publication | Washington, DC, USA | |
| pubs.start-date | 2018-11-17 | en_NZ |