Logo des Repositoriums
 

Explainable AI in grassland monitoring: Enhancing model performance and domain adaptability

Kurzanzeige
dc.contributor.authorShanghua Liu, Anna Hedström
dc.date.accessioned2024-04-08T11:56:33Z
dc.date.available2024-04-08T11:56:33Z
dc.date.issued2024
dc.description.abstractGrasslands are known for their high biodiversity and ability to provide multiple ecosystem services. Challenges in automating the identification of indicator plants are key obstacles to large-scale grassland monitoring. These challenges stem from the scarcity of extensive datasets, the distributional shifts between generic and grassland-specific datasets, and the inherent opacity of deep learning models. This paper delves into the latter two challenges, with a specific focus on transfer learning and eXplainable Artificial Intelligence (XAI) approaches to grassland monitoring, highlighting the novelty of XAI in this domain. We analyze various transfer learning methods to bridge the distributional gaps between generic and grassland-specific datasets. Additionally, we showcase how explainable AI techniques can unveil the model's domain adaptation capabilities, employing quantitative assessments to evaluate the model's proficiency in accurately centering relevant input features around the object of interest. This research contributes valuable insights for enhancing model performance through transfer learning and measuring domain adaptability with explainable AI, showing significant promise for broader applications within the agricultural community.en
dc.identifier.doi10.18420/giljt2024_54
dc.identifier.isbn978-3-88579-738-8
dc.identifier.issn2944-7682
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43866
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartof44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft
dc.relation.ispartofseriesLecture Notes in Informatics(LNI) - Proceedings, Volume P - 344
dc.subjectXAI
dc.subjectdeep learning
dc.subjectindicator detection
dc.subjectdomain adaptation
dc.subjectgrassland monitoring
dc.titleExplainable AI in grassland monitoring: Enhancing model performance and domain adaptabilityen
dc.typeText/Conference Paper
gi.citation.endPage154
gi.citation.publisherPlaceBonn
gi.citation.startPage143
gi.conference.date27.-28. Februar 2024
gi.conference.locationStuttgart
gi.conference.reviewfull

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
GIL_2024_Liu_143-154.pdf
Größe:
842.92 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P344 - 44. GIL-Jahrestagung 2024 - Fokus: Biodiversität fördern durch digitale Landwirtschaft