| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Wanders, Niko | |
| dc.contributor.author | Ven, Jordy van de | |
| dc.date.accessioned | 2022-04-07T00:00:37Z | |
| dc.date.available | 2022-04-07T00:00:37Z | |
| dc.date.issued | 2022 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/41461 | |
| dc.description.abstract | Hydrological droughts can have severe impacts on water levels in a river and consequentially also on shipping. Traditionally research on the impact of hydrological drought is done by means of numerical modeling. In this study a machine learning approach was used, to investigate the viability of data driven approaches in drought estimations. It was found that random forest machine learning is a promising tool that can be used to study the impact of hydrological drought. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | A random forest machine learning program developed to estimate the impact of hydrological drought on the shipping industry in the Netherlands. | |
| dc.title | Using Random Forest Machine learning to estimate the impact of hydrological drought on
the shipping industry | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | Drought;Machine learning:random forest;shipping | |
| dc.subject.courseuu | Earth Surface and Water | |
| dc.thesis.id | 3233 | |
