Towards a point cloud understanding framework for forest scene semantic segmentation across forest types and sensor platforms

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: 318, P. 114591 - 114591

Published: Jan. 15, 2025

Language: Английский

---

TomoSense: A unique 3D dataset over temperate forest combining multi-frequency mono- and bi-static tomographic SAR with terrestrial, UAV and airborne lidar, and in-situ forest census

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 290, P. 113532 - 113532

Published: March 22, 2023

Language: Английский

---

Modelling above ground biomass for a mixed-tree urban arboretum forest based on a LiDAR-derived canopy height model and field-sampled data

GEOMATICA, Journal Year: 2025, Volume and Issue: unknown, P. 100047 - 100047

Published: Jan. 1, 2025

Language: Английский

---

Advances in Laser Scanning to Assess Carbon in Forests: From Ground-Based to Space-Based Sensors

Current Forestry Reports, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 22, 2025

Language: Английский

---

Data and knowledge needs for improving science and policy for peatlands in Canada in a changing world: insights from Global Peatlands Initiative Workshop, June 2023

FACETS, Journal Year: 2025, Volume and Issue: 10, P. 1 - 19

Published: Jan. 1, 2025

Knowledge and data on the current function, future threats, benefits of peatlands in Canada are required to support evidence-based decision-making ensure they continue provide critical ecosystem services. This is particularly relevant for Canada, given large expanse relatively intact peatland area. There a need, not only standardize protocols, but also prioritize types information knowledge that can best meet conservation management goals. was challenge posed participants Global Peatlands Initiative workshop June 2023 Quebec City, Quebec, Canada. Participants were composed researchers using primarily Western science approaches use carbon accounting, policy or sustainable land use, reclamation/restoration, conservation, wildlife, water resources applications. For seven categories (hydrometeorological environmental sensing; peat coring depth; greenhouse gas monitoring; biodiversity; vegetation, woody debris, litter; Traditional Knowledge; quality), three priority measurements identified recommendations their collection discussed. The key from (1) create standardized, yet flexible protocols; (2) coordinate field where possible; (3) weave more into understanding peatlands; (4) an atlas existing information; (5) scope opportunities network “super sites”.

Language: Английский

---

OpenForest: a data catalog for machine learning in forest monitoring

Environmental Data Science, Journal Year: 2025, Volume and Issue: 4

Published: Jan. 1, 2025

Abstract Forests play a crucial role in the Earth’s system processes and provide suite of social economic ecosystem services, but are significantly impacted by human activities, leading to pronounced disruption equilibrium within ecosystems. Advancing forest monitoring worldwide offers advantages mitigating impacts enhancing our comprehension composition, alongside effects climate change. While statistical modeling has traditionally found applications biology, recent strides machine learning computer vision have reached important milestones using remote sensing data, such as tree species identification, crown segmentation, biomass assessments. For this, significance open-access data remains essential data-driven algorithms methodologies. Here, we comprehensive extensive overview 86 datasets across spatial scales, encompassing inventories, ground-based, aerial-based, satellite-based recordings, country or world maps. These grouped OpenForest, dynamic catalog open contributions that strives reference all available datasets. Moreover, context these datasets, aim inspire research applied biology establishing connections between contemporary topics, perspectives, challenges inherent both domains. We hope encourage collaborations among scientists, fostering sharing exploration diverse through application methods for large-scale monitoring. OpenForest is at following url: https://github.com/RolnickLab/OpenForest .

Language: Английский

---

Selecting allometric equations to estimate forest biomass from plot- rather than individual-level predictive performance

Biogeosciences, Journal Year: 2025, Volume and Issue: 22(5), P. 1413 - 1426

Published: March 13, 2025

Abstract. In the context of global change, it is essential to quantify and monitor carbon stored in forests. Allometric equations are mathematical models that predict biomass a tree from dendrometrical characteristics easier measure, such as diameter, height, or wood density. Various model forms have been proposed for allometric equations. Moreover, choice has critical influence on estimate forest. So far, selection performed based tree-level predictive performance models. However, used plots rather than individual trees. The distribution trees sampled establishing often differs forest structure. at plot level, residual errors different can cancel off. Therefore, we expect plot-level differ its performance. Using dataset giving observed 844 central Africa null size forest, simulated between 0.1 50 ha area. Then, using Monte Carlo approach, calculated mean sum squared (MSS) differences predicted biomass. We showed MSS could be well approximated by three-term formula, where first term corresponded bias, second one error, third uncertainty coefficients. For small (≤ ha), was dominated error term. Model then consistent with large plots, this vanished. case chains combined general equation local some predictors provide good trade-off bias recommend select formula developed provides an easy way assess effect balance respective contributions

Language: Английский

---

Evaluating the Research Status of the Remote Sensing-Mediated Monitoring of Forest Biomass: A Bibliometric Analysis of WOS

Forests, Journal Year: 2024, Volume and Issue: 15(3), P. 524 - 524

Published: March 12, 2024

Forests serve as the largest carbon reservoir in terrestrial ecosystems, playing a crucial role mitigating global warming and achieving goal of “carbon neutrality”. Forest biomass is intrinsically related to sinks sources forest thus, accurate monitoring great significance ensuring ecological security maintaining balance. Significantly, remote sensing not only able estimate at large spatial scale but does so quickly, accurately, without loss. Moreover, it can obtain areas inaccessible human beings, which have become main data source for estimation present. For this reason, study analyzes current research status, hotspots, future trends field based on 1678 results from 1985 2023 obtained Web Science Core Collection database. The showed that following: (1) number publications an exponential upward trend 2023, with average annual growth rate 2.64%. top ten journals contributed 53.76% total 52.89% citations field. (2) In particular, Remote Sensing Environment has maintained leading position extended period, boasting highest impact factor. Additionally, author Saatchi S. stands out articles. (3) Keyword clustering analysis revealed topics be categorized into optical sensing, LiDAR SAR stock. explosion keywords last six years indicates increasing researchers are focusing carbon, airborne data, mapping, constructing optimal models.

Language: Английский

---

Individual-Tree Segmentation from UAV–LiDAR Data Using a Region-Growing Segmentation and Supervoxel-Weighted Fuzzy Clustering Approach

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(4), P. 608 - 608

Published: Feb. 6, 2024

Accurate individual-tree segmentation is essential for precision forestry. In previous studies, the canopy height model-based method was convenient to process, but its performance limited owing loss of 3D information, and point-based methods usually had high computational costs. Although some hybrid have been proposed solve above problems, most are used detect subdominant trees in one coarse crown disregard over-segmentation accurate boundaries. This study introduces a combined approach, tested first time, treetop detection tree using UAV–LiDAR data. First, multiscale adaptive local maximum filter treetops accurately, Dalponte region-growing introduced achieve delineation. Then, based on coarse-crown result, mean-shift voxelization supervoxel-weighted fuzzy c-means clustering were identify constrained region each tree. Finally, point clouds obtained. The experiment conducted synthetic uncrewed aerial vehicle (UAV)–LiDAR dataset with 21 approximately 30 × m plots an actual dataset. To evaluate method, accuracy remotely sensed biophysical observations retrieval frameworks determined location, height, area. results show that efficient outperformed other existing methods.

Language: Английский

---

Analysing individual 3D tree structure using the R package ITSMe

Methods in Ecology and Evolution, Journal Year: 2022, Volume and Issue: 14(1), P. 231 - 241

Published: Nov. 15, 2022

Abstract Detailed 3D quantification of tree structure plays a crucial role in understanding tree‐ and plot‐level biophysical processes. Light detection ranging (LiDAR) has led to revolution structural measurements its data are increasingly becoming publicly available. Yet, calculating metrics from LiDAR can often be complex time‐consuming potentially requires expert knowledge. We present the R package Individual Tree Structural Metrics (ITSMe), toolbox that works with point clouds quantitative models (QSMs) derived obtain individual metrics. It serves as robust synthesis framework for researchers who want readily information trees. The includes functions determine basic (tree height, diameter at breast above buttresses, projected crown area, alpha volume) clouds, well more (individual component volumes, branch angle‐, radius‐ length‐related metrics) QSMs. ITSMe is an open‐source hosted on GitHub will make use straightforward transparent range end‐users interested exploiting information.

Language: Английский

---