Publication Details

Category Text Publication
Reference Category Journals
DOI 10.3389/fenvs.2023.1009191
Licence creative commons licence
Title (Primary) Probabilistic prediction by means of the propagation of response variable uncertainty through a Monte Carlo approach in regression random forest: application to soil moisture regionalization
Author Dega, S.; Dietrich, P. ORCID logo ; Schrön, M.; Paasche, H.
Journal Frontiers in Environmental Science
Year 2023
Department MET
Volume 11
Page From art. 1009191
Language englisch
Topic T5 Future Landscapes
Keywords uncertainty propagation; Probabilistic prediction; Monte Carlo (MC); Quantile Regression Random Forest; soil moisture
Abstract Probabilistic predictions aim at producing a prediction interval with probabilities associated with each possible outcome, instead of a single value for each outcome. In multiple regression problems, this can be achieved by propagating the known uncertainties in data of the response variables through a Monte Carlo approach. This paper provides an analysis of the impact of the training response variable uncertainty on the prediction uncertainties with the help of a comparison with probabilistic prediction obtained with quantile regression random forest. The result is an uncertainty quantification of the impact on the prediction. The approach is illustrated with the example of the probabilistic regionalization of soil moisture derived from Cosmic Ray Neutron Sensing measurements providing a regional-scale soil-moisture map with data uncertainty quantification covering the Selke river catchment, Eastern Germany.
Persistent UFZ Identifier https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=25620
Dega, S., Dietrich, P., Schrön, M., Paasche, H. (2023):
Probabilistic prediction by means of the propagation of response variable uncertainty through a Monte Carlo approach in regression random forest: application to soil moisture regionalization
Front. Environ. Sci. 11 , art. 1009191