Forest Research Institute

About: Forest Research Institute is a facility organization based out in Dehra Dūn, India. It is known for research contribution in the topics: Population & Forest management. The organization has 5320 authors who have published 7625 publications receiving 185876 citations.

SDMtune: An R package to tune and evaluate species distribution models

Abstract: Balancing model complexity is a key challenge of modern computational ecology, particularly so since the spread of machine learning algorithms. Species distribution models are often implemented using a wide variety of machine learning algorithms that can be fine-tuned to achieve the best model prediction while avoiding overfitting. We have released SDMtune, a new R package that aims to facilitate training, tuning, and evaluation of species distribution models in a unified framework. The main innovations of this package are its functions to perform data-driven variable selection, and a novel genetic algorithm to tune model hyperparameters. Real-time and interactive charts are displayed during the execution of several functions to help users understand the effect of removing a variable or varying model hyperparameters on model performance. SDMtune supports three different metrics to evaluate model performance: the area under the receiver operating characteristic curve, the true skill statistic, and Akaike's information criterion corrected for small sample sizes. It implements four statistical methods: artificial neural networks, boosted regression trees, maximum entropy modeling, and random forest. Moreover, it includes functions to display the outputs and create a final report. SDMtune therefore represents a new, unified and user-friendly framework for the still-growing field of species distribution modeling.

Is salvage logging effectively dampening bark beetle outbreaks and preserving forest carbon stocks

Abstract: Salvage logging is one of most frequently applied management responses to forest disturbances world‐wide. As forest disturbances are increasing, so too is the application of salvage logging, yet its effects on ecosystems remains incompletely understood. In the Norway spruce (Picea abies (L.) Karst.) forests of Europe, salvaging of windfelled trees is inter alia applied to reduce the risk of bark beetle outbreaks (mainly Ips typographus L.). By preventing further disturbances, salvage logging can conserve live tree carbon (C) in forest landscapes. At the same time salvage logging reduces C stocks in detrital pools via the extraction of disturbed trees, its net effect thus remains unclear. We used the forest landscape model iLand to explore the effect of a wide range of salvaging intensities on (a) subsequent bark beetle outbreaks, and (b) landscape‐scale forest C stocks in a Norway spruce‐dominated production forest in Slovakia under past and future climatic conditions. Climate change resulted in a two‐ to three‐fold increase in bark beetle disturbances throughout the 21st century in our simulations. We found that removing >95% of disturbed trees can effectively buffer the effect of increasing disturbances, dampening bark beetle infestations and increasing live tree C. Total ecosystem C followed a U‐shaped pattern over salvaging intensity, with highest values in no salvage and 100% salvage scenarios. However, realistic rates of salvaging (<95% of disturbed trees detected and removed) had no significant effect on bark beetle dynamics and live tree C, and reduced the total ecosystem C stored in the landscape. Furthermore, the effect of reduced bark beetle disturbance under intensive salvaging was partly offset by increased wind disturbance. Synthesis and applications. Clearing disturbed areas to prevent future disturbances from bark beetles and conserve live tree carbon should only be applied where very high salvaging rates are feasible (i.e. small and concentrated disturbances). Considering that changing disturbance regimes make high‐intensity salvaging increasingly challenging, alternative disturbance management approaches need to be developed.