Mikusinski, G. | bioRxiv Science

bioRxiv2023

Mapping forests with different levels of naturalness using machine learning and landscape data mining

To conserve biodiversity, it is imperative to maintain and restore sufficient amounts of functional habitat networks. Hence, locating remaining forests with natural structures and processes over landscapes and large regions is a key task. We integrated machine learning (Random Forest) and open landscape data to scan all forest landscapes in Sweden with a 1 ha spatial resolution with respect to the relative likelihood of hosting High Conservation Value Forests (HCVF). Using independent spatial stand-and plot-level validation data we confirmed that our predictions (ROC AUC in the range of 0.89 - 0.90) correctly represent forests with different levels of naturalness, from deteriorated to those with high and associated biodiversity conservation values. Given ambitious national and international conservation objectives, and increasingly intensive forestry, our model and the resulting wall-to-wall mapping fills an urgent gap for assessing fulfilment of evidence-based conservation targets, spatial planning, and designing forest landscape restoration.

ecology↗

bioRxiv2020

Species associations and management intensity modulate the habitat niche breadth of forest birds

Species associations can have profound effects on the realized habitat niche of species, indicating that habitat structure alone cannot fully explain observed abundances. To account for this aspect of community organization in niche modelling, we developed multi-species abundance models, incorporating the local effect of potentially associated species, alongside with environmental ones, targeting mainly forest management intensity. We coupled it with a landscape-scale analysis to further examine the role of management intensity in modifying the habitat niche in connection with the landscape context. Using empirical data from the Black Forest in southern Germany, we focused on the forest bird assemblage and in particular on the cavity nester and canopy forager guilds. We included in the analysis species that co-occur and for which evidences suggest association is likely. Our findings show that the local effect of species associations can moderate the effects of management intensity. We also found that species express a larger habitat niche breadth in intensively managed forests, depending on the landscape context. Species associations may facilitate the utilization of a broader range of environmental conditions under intensive forest management, which benefits some species over others. Such network of associations may be a relevant factor in the effectiveness of conservation-oriented forest management.

ecology↗