Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Counterfactual Explanations for Deep Forecasting Models: An Application on Fisheries Catch
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2024 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This thesis explores the application of advanced time series forecasting models, specifically N-BEATSx and N-HiTS, to understand complex dynamics within marine ecosystems in the North Sea. By integrating exogenous variables, such as sea surface temperature (SST), and employing counterfactual explanations, this research addresses the question: ”How and to what extent can counterfactual explanations enhance our understanding of deep learning models for time series forecasting with exogenous variables in marine ecosystems?” The findings reveal that incorporating SST as an exogenous variable alone does not improve the forecasting models’ performance. However, counterfactual explanations generated using ForecastCF-Exog offer valuable insights into how changes in external factors influence fish populations. This framework not only advances the interpretability of deep learning models but also provides actionable insights for sustainable policy-making and ecosystem management. By enhancing our understanding of complex environmental systems through interpretable models, this research contributes a framework that offers novel insights for effective decision-making in natural sciences and other applications.

Place, publisher, year, edition, pages
2024.
Keywords [en]
Time series forecasting, machine learning, deep learning, N- BEATSx, N-HiTS, ForecastCF, counterfactual explanations, marine ecosystems, policy-making
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:su:diva-242669OAI: oai:DiVA.org:su-242669DiVA, id: diva2:1955560
Available from: 2025-04-30 Created: 2025-04-30

Open Access in DiVA

fulltext(1383 kB)11 downloads
File information
File name FULLTEXT01.pdfFile size 1383 kBChecksum SHA-512
f254eb98ae7ec5cf507d8fb5d0b19de3373c8a5302d90496a99c5efffea6f47d9678a5e32d43ed362857f195df3f8976bb229e5a65ba524b0394d994a1596b65
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Mandakovic, Damir
By organisation
Department of Computer and Systems Sciences
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 11 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 18 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf