Modeling an Agricultural Process Coordination Problem to Enhance Efficiency and Resilience with Methods of Artificial Intelligence
| dc.contributor.author | Hubl, Marvin | |
| dc.contributor.editor | Michael, Judith | |
| dc.contributor.editor | Pfeiffer | |
| dc.contributor.editor | Jérôme | |
| dc.contributor.editor | Wortmann, Andreas | |
| dc.date.accessioned | 2022-06-30T13:01:05Z | |
| dc.date.available | 2022-06-30T13:01:05Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Modeling of relations in a domain is a fundamental basis for solving domain problems. However, even well-formulated mathematical models do not always allow for satisfactory solutions. Here, methods from Artificial Intelligence bring value for solutions based on the formal models, e.\,g. by meta-heuristics. Furthermore, variables in a mathematical model may require manifestations although exact values are not known or measured. Machine-learning-based methods can enhance the appropriateness for the variable manifestation. We study upon these issues at the example of a process coordination problem in agricultural crop production. We analyze how methods of Artificial Intelligence can enhance processual efficiency and resilience. Therefore, two domain objectives are formalized: (i) maximization of machine utilization; (ii) maximization of aggregated area output. We identify and discuss the contribution of Artificial Intelligence for solving the mathematically formalized problem appropriately. | en |
| dc.identifier.doi | 10.18420/modellierung2022ws-003 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/38793 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | Modellierung 2022 Satellite Events | |
| dc.subject | Mathematical Modeling | |
| dc.subject | Optimization Problem | |
| dc.subject | Process Coordination | |
| dc.subject | Resource Allocation | |
| dc.subject | Agricultural Engineering | |
| dc.title | Modeling an Agricultural Process Coordination Problem to Enhance Efficiency and Resilience with Methods of Artificial Intelligence | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 17 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 6 | |
| gi.conference.date | 27.6. - 1.7.2022 | |
| gi.conference.location | Hamburg | |
| gi.conference.sessiontitle | MoKI - Modelle und KI |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- paper1.pdf
- Größe:
- 262.87 KB
- Format:
- Adobe Portable Document Format