Evaluation of six methods for correcting bias in estimates from ensemble tree machine learning regression model

Environmental Modeling and Software
By:  and 

Links

Abstract

Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias. Method performance was evaluated using four case studies of groundwater quality: the units of the dependent variable were pH in two and log-concentration in the others. When performance metrics (bias and RMSE for both points and the CDF) were computed using the same units as those in the ML model, empirical distribution matching (EDM) provided the best results. When the metrics were computed using retransformed concentration, EDM and a method incorporating Duan's smearing estimate were both effective. A method based on the Z-score transform approximates EDM if the correlation coefficient between rank-ordered ML estimates and rank-ordered observations approaches one.

Publication type Article
Publication Subtype Journal Article
Title Evaluation of six methods for correcting bias in estimates from ensemble tree machine learning regression model
Series title Environmental Modeling and Software
DOI 10.1016/j.envsoft.2021.105006
Volume 139
Year Published 2021
Language English
Publisher Elsevier
Contributing office(s) WMA - Earth System Processes Division
Description 105006, 12 p.
Google Analytics Metrics Metrics page
Additional publication details