https://www.mdu.se/

mdu.sePublications
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
Trust, but Verify-Post-Hoc Analysis of Industrial Machine Learning via Interpretability Metric Embedding and Surrogate Mapping
Kanthal AB, SE-73427 Hallstahammar, Sweden.
Mälardalen University, Faculty of Engineering and Health Sciences, Department of Engineering Sciences.ORCID iD: 0009-0004-4717-2528
Kanthal AB, SE-73427 Hallstahammar, Sweden.
Mälardalen University, Faculty of Engineering and Health Sciences, Department of Engineering Sciences.ORCID iD: 0000-0002-8466-356X
2026 (English)In: Sensors, E-ISSN 1424-8220, Vol. 26, no 10, article id 3232Article in journal (Refereed) Published
Abstract [en]

In industrial machine learning, predictive performance alone is insufficient to ensure reliable deployment, as model behaviour may vary across different regions of the input space under limited data and evolving process conditions. This work investigates whether such variation can be systematically analysed through post-hoc methods. A model-agnostic framework is proposed in which interpretability metrics, including residuals and feature attributions, are embedded into a low-dimensional space and approximated using a continuous surrogate model. This representation enables the analysis of model behaviour as a structured landscape, rather than as isolated pointwise explanations. The approach is applied to ceramic heating element production, where two distinct regimes are identified. One corresponds to a stable region with consistent and accurate predictions, while the other reflects a transitional regime associated with increased ambiguity and sensitivity to feature interactions. These regimes are shown to align with known process conditions and temporal variation. The results demonstrate that model behaviour can be organised into coherent regions that are not observable through aggregate performance metrics alone. This provides a structured basis for post-hoc analysis, supporting targeted interpretation and further investigation of model reliability in industrial settings.

Place, publisher, year, edition, pages
MDPI AG , 2026. Vol. 26, no 10, article id 3232
Keywords [en]
post-hoc analysis, explainable AI, UMAP, interpretability metrics, industrial machine learning, decision landscape
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-77162DOI: 10.3390/s26103232ISI: 001775516600001PubMedID: 42198039OAI: oai:DiVA.org:mdh-77162DiVA, id: diva2:2065568
Available from: 2026-06-03 Created: 2026-06-03 Last updated: 2026-06-03Bibliographically approved

Open Access in DiVA

fulltext(1196 kB)11 downloads
File information
File name FULLTEXT01.pdfFile size 1196 kBChecksum SHA-512
5c88f2c590873446ade079849b8452f446ace1aa8472693a1461472eee4c0ad15ffe7d357b6e348616a5a3b35c7b819d21f5c230d967d7719e5dac6541b26119
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMed

Authority records

Mählkvist, SimonNetzell, PontusKyprianidis, Konstantinos

Search in DiVA

By author/editor
Mählkvist, SimonNetzell, PontusKyprianidis, Konstantinos
By organisation
Department of Engineering Sciences
In the same journal
Sensors
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
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

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 128 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