Towards crop yield prediction using Automated Machine Learning
| dc.contributor.author | Heil, Jonathan | |
| dc.contributor.author | Valencia, Juan Manuel | |
| dc.contributor.author | Stein, Anthony | |
| dc.contributor.editor | Hoffmann, Christa | |
| dc.contributor.editor | Stein, Anthony | |
| dc.contributor.editor | Ruckelshausen, Arno | |
| dc.contributor.editor | Müller, Henning | |
| dc.contributor.editor | Steckel, Thilo | |
| dc.contributor.editor | Floto, Helga | |
| dc.date.accessioned | 2023-02-21T15:14:20Z | |
| dc.date.available | 2023-02-21T15:14:20Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Recently, several Machine Learning models for crop yield prediction have been introduced in literature. The models differ in the underlying methodological approaches and show variations in the temporal and spatial resolution of the databases. For the creation of the models, a deep understanding of Machine Learning is required. Therefore, Automated Machine Learning, which aims to automate the creation process of Machine Learning models, offers a promising solution as an easy entry point in Machine Learning for crop yield prediction to non-professionals. Based on publicly available data for weather, phenological and yield observations, in this work, we created a dataset for winter wheat and winter barley on Germany’s regional districts level. Furthermore, an initial evaluation of four state of the art Automated Machine Learning frameworks and three baseline models has been conducted. The results showed almost always significantly better performance of models created by Automated Machine Learning. | en |
| dc.identifier.isbn | 978-3-88579-724-1 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/40300 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | 43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-330 | |
| dc.subject | crop yield prediction | |
| dc.subject | Automated Machine Learning | |
| dc.subject | open source data | |
| dc.subject | winter wheat | |
| dc.subject | winter barley | |
| dc.title | Towards crop yield prediction using Automated Machine Learning | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 100 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 89 | |
| gi.conference.date | 13.-14. Februar 2023 | |
| gi.conference.location | Osnabrück |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- GIL_2023_Heil_89-100.pdf
- Größe:
- 466.04 KB
- Format:
- Adobe Portable Document Format