PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI)
Version 1
: Received: 25 April 2024 / Approved: 26 April 2024 / Online: 26 April 2024 (09:32:45 CEST)
How to cite:
Bröde, P.; Fiala, D.; Kampmann, B. Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI). Preprints2024, 2024041732. https://doi.org/10.20944/preprints202404.1732.v1
Bröde, P.; Fiala, D.; Kampmann, B. Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI). Preprints 2024, 2024041732. https://doi.org/10.20944/preprints202404.1732.v1
Bröde, P.; Fiala, D.; Kampmann, B. Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI). Preprints2024, 2024041732. https://doi.org/10.20944/preprints202404.1732.v1
APA Style
Bröde, P., Fiala, D., & Kampmann, B. (2024). Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI). Preprints. https://doi.org/10.20944/preprints202404.1732.v1
Chicago/Turabian Style
Bröde, P., Dusan Fiala and Bernhard Kampmann. 2024 "Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI)" Preprints. https://doi.org/10.20944/preprints202404.1732.v1
Abstract
The objective of this paper was to verify the applicability of statistical learning (SL) compared to human reasoning with respect to the Universal Thermal Climate Index (UTCI), a complex tool for the assessment of outdoor thermal stress. UTCI is an equivalent temperature index based on the 48-dimensional output of an advanced model of human thermoregulation formed by 12 variables at four consecutive 30-minute intervals, which were calculated for 105642 thermal conditions from extreme cold to extreme heat. Comparing the performance of SL algorithms to the results accomplished by an international endeavor involving more than 40 experts from 23 countries, we found that random forests and k-nearest neighbors closely predicted UTCI values, but that clustering applied after dimension reduction algorithms (principal component analysis and t-distributed stochastic neighbor embedding) were inadequate for risk assessment in relation to the UTCI stress categories. This indicates a potential supportive role for SL, as it will not (yet) fully replace the bio-meteorological expert knowledge.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
