气候变化领域集成服务门户(CCPortal): Use of advanced modelling methods to estimate radiata pine productivity indices

CCPortal

DOI	10.1016/j.foreco.2020.118557
	Use of advanced modelling methods to estimate radiata pine productivity indices
	Watt M.S.; Palmer D.J.; Leonardo E.M.C.; Bombrun M.
发表日期	2021
ISSN	0378-1127
卷号	479
英文摘要	Site productivity indices have been widely used to describe age normalised height and volume for a range of forest species. In this study we used a wide range of modelling methods to predict Site Index and 300 Index for Pinus radiata D. Don. Site Index normalises height to a standardised age, while the 300 Index normalises volume measurements to a standardised age, stand density and set of silvicultural conditions. These two indices were derived from a national database of 3,676 plots with predictors extracted from geospatial surfaces describing key landform, topographic, climatic, edaphic and species-specific features (e.g. disease severity). Using these data, our objectives were to (i) compare the accuracy of geospatial, parametric and non-parametric models in predicting Site Index and 300 Index, (ii) determine whether regression kriging could be used to improve the accuracy of these predictions, (iii) identify the most influential predictors of these two indices and (iv) produce maps of both indices across New Zealand. All predictions were made on a test dataset (n = 1,104) that was not used for model fitting. The two non-parametric models eXtreme Gradient Boosting (XGBoost) and random forest provided the most precise predictions of Site Index and 300 Index and markedly outperformed both parametric and geospatial models (ordinary kriging, inverse distance weighting). Random forest provided the most precise predictions of Site Index (R2 = 0.811, RMSE = 2.027 m, RMSE% = 6.73%) while XGBoost most precisely predicted 300 Index (R2 = 0.676, RMSE = 3.462 m3 ha−1 yr−1, RMSE% = 12.63%). The use of regression kriging improved the fit of all but one model through accounting for spatial co-variance in the model error. Gains in precision were most marked for the parametric models, and in particular the regression model. After kriging, the three most precise models for both indices were random forest, followed by XGBoost and the regression model. An ensemble model derived from the mean predictions of these three models provided the most precise predictions, among all tested models, for both Site Index (R2 = 0.818, RMSE = 1.991 m, RMSE% = 6.61%) and 300 Index (R2 = 0.691, RMSE = 3.384 m3 ha−1 yr−1, RMSE% = 12.35%). Fitting a range of models to productivity indices was found to be a useful approach as this allows creation of an ensemble model and provides greater insight into the key determinants of productivity. © 2020 Elsevier B.V.
英文关键词	Elastic net; Inverse distance weighting, multivariate adaptive regression splines; Ordinary kriging; Partial least squares; Random forests
语种	英语
scopus关键词	Decision trees; Forecasting; Interpolation; Productivity; Random forests; Regression analysis; Statistical tests; Ensemble modeling; Inverse distance weighting; National database; Non-parametric model; Parametric models; Productivity index; Regression-kriging; Species specifics; Forestry; accuracy assessment; data set; database; error analysis; kriging; numerical model; pine; prediction; regression analysis; silviculture; Forecasts; Forestry; Models; Productivity; Regression Analysis; Site Index; Statistical Analysis; New Zealand; Pinus radiata; Radiata
来源期刊	Forest Ecology and Management
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/154891
作者单位	Scion, 10 Kyle St, Christchurch, 8011, New Zealand; Scion, PO Box 3020, Rotorua, New Zealand
推荐引用方式 GB/T 7714	Watt M.S.,Palmer D.J.,Leonardo E.M.C.,et al. Use of advanced modelling methods to estimate radiata pine productivity indices[J],2021,479.
APA	Watt M.S.,Palmer D.J.,Leonardo E.M.C.,&Bombrun M..(2021).Use of advanced modelling methods to estimate radiata pine productivity indices.Forest Ecology and Management,479.
MLA	Watt M.S.,et al."Use of advanced modelling methods to estimate radiata pine productivity indices".Forest Ecology and Management 479(2021).