Statistical comparison of additive regression tree methods on ecological grassland data

Plant, Emily and King, Rachel ORCID: https://orcid.org/0000-0002-3302-0919 and Kath, Jarrod ORCID: https://orcid.org/0000-0003-2391-1264 (2021) Statistical comparison of additive regression tree methods on ecological grassland data. Ecological Informatics, 61:101198. pp. 1-23. ISSN 1574-9541


Abstract

Additive tree methods are widely used in ecology. To date most ecologists have used boosted regression tree (BRT) methods. However, Bayesian additive regression tree (BART) models may offer advantages to ecologists previously unexamined.

Here we test whether BART has some benefits over the widely used BRT method. To do this we use two grassland data and 13 hydroclimatic and land use predictor variables. The dataset contained data from a period of drought as well as during a recovery phase after the drought. The response variable was the trend in the Enhanced Vegetation Index (EVI), which is an remotely sensed indicator of grassland degradation and recovery.

The settable parameters of both methods (BRT and BART) were varied to compare the performance of each method. BRT and BART models were evaluated using three prediction error statistics; root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2). The best models across the two methods were assessed by inspecting the relative importance of predictor variables and the prediction error statistics.

BRT and BART models exhibited similar variable selection abilities, but the BART method generated models with similar or more favourable prediction error statistics than the BRT method (BART explained an additional 10.17% to 11.92% of the variation than BRT models). Our results indicate that BARTs may be more effective at modelling ecological data than BRTs.

BARTs also had shorter run times, more reasonable defaults in its software implementation, and greater functionality of said software implementation, beyond model building and prediction functions. Ecologists using additive regression approaches may benefit from using BART approaches and we suggest their use alongside more commonly used BRT methods in ecological studies.


Statistics for USQ ePrint 40511
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 -)
Faculty/School / Institute/Centre: Current - Institute for Life Sciences and the Environment - Centre for Applied Climate Sciences (1 Aug 2018 -)
Date Deposited: 12 Jan 2021 00:44
Last Modified: 22 Jun 2021 09:54
Uncontrolled Keywords: Bayesian additive regression tree; Boosted regression tree; Remote sensing; Satellite; Grassland; Pasture
Fields of Research (2008): 01 Mathematical Sciences > 0104 Statistics > 010401 Applied Statistics
07 Agricultural and Veterinary Sciences > 0701 Agriculture, Land and Farm Management > 070104 Agricultural Spatial Analysis and Modelling
07 Agricultural and Veterinary Sciences > 0701 Agriculture, Land and Farm Management > 070101 Agricultural Land Management
Fields of Research (2020): 30 AGRICULTURAL, VETERINARY AND FOOD SCIENCES > 3002 Agriculture, land and farm management > 300206 Agricultural spatial analysis and modelling
49 MATHEMATICAL SCIENCES > 4905 Statistics > 490501 Applied statistics
30 AGRICULTURAL, VETERINARY AND FOOD SCIENCES > 3002 Agriculture, land and farm management > 300202 Agricultural land management
Socio-Economic Objectives (2008): D Environment > 96 Environment > 9605 Ecosystem Assessment and Management > 960510 Ecosystem Assessment and Management of Sparseland, Permanent Grassland and Arid Zone Environments
Socio-Economic Objectives (2020): 10 ANIMAL PRODUCTION AND ANIMAL PRIMARY PRODUCTS > 1005 Pasture, browse and fodder crops > 100503 Native and residual pastures
Identification Number or DOI: https://doi.org/10.1016/j.ecoinf.2020.101198
URI: http://eprints.usq.edu.au/id/eprint/40511

Actions (login required)

View Item Archive Repository Staff Only