Automated Classification of Trees outside Forest for Supporting Operational Management in Rural Landscapes

Abstract

Trees have important and diverse roles that make them essential outside of the forest. The use of remote sensing can substantially support traditional field inventories to evaluate and characterize this resource. Existing studies have already realized the automated detection of trees outside the forest (TOF) and classified the subsequently mapped TOF into three geometrical classes: single objects, linear objects, and ample objects. This study goes further by presenting a fully automated classification method that can support the operational management of TOF as it separates TOF into seven classes matching the definitions used in field inventories: Isolated tree, Aligned trees, Agglomerated trees, Hedge, Grove, Shrub, and Other. Using publicly available software tools, an orthophoto, and a LIDAR canopy height model (CHM), a TOF map was produced and a two-step method was developed for the classification of TOF: (1) the geometrical classification of each TOF polygon; and (2) the spatial neighboring analysis of elements and their classification into seven classes. The overall classification accuracy was 78%. Our results highlight that an automated TOF classification is possible with classes matching the definitions used in field inventories. This suggests that remote sensing has a huge potential to support the operational management of TOF as well as other research areas regarding TOF.

Trees on Farms to Improve Livelihoods and the Environment

“…TOF are increasingly being included in national forest and landscape inventory systems (Schnell et al 2015b; see Schnell 2015a for the contribution of TOF to national tree biomass and carbon stocks on three continents). The use of high-resolution satellite imagery and remote sensing, coupled with automated post-processing techniques, has improved the ability to map TOF at a large scale (Bolyn et al 2019;Yadav 2019;Kattenborn et al 2021). For example, a recently published study in Nature (Brandt et al 2020) mapped all trees (>3 m 2 crown size) in an area in Africa covering 1.3 million km² using machine learning applied to high-resolution (<1 m) satellite imagery.…”

“…The abundance of TonF and the important roles that they play in rural livelihoods and environmental management are increasingly being recognized (Yadav 2019;Schnell et al 2015a;Thapa et al 2021;Thomas et al 2021;Bolyn et al 2019). However, TonF are still largely absent from global initiatives (such as REDD+, FAO/FRA, UN conventions on biological diversity and on water) and in national agendas.…”

The Role of Trees Outside Forests in the Cultural Landscape of the Colline del Prosecco UNESCO Site

“…The use of historical maps or of cadasters, instead, can be problematic due to compatibility. Different TOF-focused studies used different images (aerophotos, orthophotos, satellite images, LIDAR) and different methodologies, from photointerpretation to automatic classifications [21,22,26,[32][33][34][35], but all of them agree regarding the necessity of including TOF in official forest statistics and inventories.…”

Investigating the potential for detecting Oak Decline using Unmanned Aerial Vehicle (UAV) Remote Sensing

“…The use of remote sensing for forest species classification has been applied to both natural and managed forests. It has been used to map and monitor the distribution and diversity of forest species at various scales, from individual trees (Chen et al, 2021;Lee et al, 2016;Plesoianu et al, 2020;Shi et al, 2018Shi et al, , 2021Zhang, 2016), to stands (Grabska et al, 2019;Wan et al, 2021) and entire forests (Bolyn et al, 2022;Welle et al, 2022). The demands regarding the spatial resolution of the species distribution map vary with the final application.…”