Rule-based vs parametric approaches for developing climate-sensitive site index models: a case study for Scots pine stands in northwestern Spain

Abstract

Key message Parametric indirect models derived from stem analysis of dominant trees were more robust than rulebased machine learning techniques for predicting Site Index of Scots pine stands as a function of climate. • ContextThe uncertainties derived from climate change make it necessary to develop new methods for representing the relationships between site conditions and forest growth.• Aims To compare parametric vs nonparametric approaches for modeling site index (SI) of Scots pine stands using bioclimatic variables.• Methods We used Random Forest, Boosted Trees, and Cubist techniques for directly predicting the SI of 41 research plots of Scots pine stands, and six parametric models for indirectly predicting SI using stem analysis data. As predictors, we used raster maps of 19 bioclimatic variables. • ResultsThe fitted models explained up to ∼80% of the SI variability, using from five to nine bioclimatic predictors. Though the apparent performance of the parametric models was lower than the rule-based, their bootstrap validation statistics were noticeably higher.• Conclusion Parametric indirect models seemed to be the most robust modeling alternative.

Forecasting Variations in Profitability and Silviculture under Climate Change of Radiata Pine Plantations through Differentiable Optimization

“…This reduction was caused by a drop in average productivity over climate scenarios which is mainly driven by an increase of temperatures and continentality. The sharpest increase among these climatic drivers was the mean temperature of the coldest month, whose negative impact on site index has already been noticed in previous studies in this region for radiata pine [12] and Scots pine [45]. The main hypothesis for explaining this negative effect is the stress on carbon balance due to high respiration rates during winter, which has also been observed for other pine species [46,47].…”

Early Prediction of Regional Red Needle Cast Outbreaks Using Climatic Data Trends and Satellite-Derived Observations

“…Ideally, predictions outside of the Gisborne region should be based on a model that is built from the weather of the new region. Although model predictions in random forests can be made outside of the fitted data range, these empirical predictions are likely to be more robust when the fitted data range covers the range and combination of input variables used for predictions [51][52][53].…”