An official website of the United States government
Abstract Tree death due to lightning influences tropical forest carbon cycling and tree community dynamics. However, the distribution of lightning damage among trees in forests remains poorly understood.We developed models to predict direct and secondary lightning damage to trees based on tree size, crown exposure and local forest structure. We parameterized these models using data on the locations of lightning strikes and censuses of tree damage in strike zones, combined with drone‐based maps of tree crowns and censuses of all trees within a 50‐ha forest dynamics plot on Barro Colorado Island, Panama.The likelihood of a direct strike to a tree increased with larger exposed crown area and higher relative canopy position (emergent > canopy >>> subcanopy), whereas the likelihood of secondary lightning damage increased with tree diameter and proximity to neighbouring trees. The predicted frequency of lightning damage in this mature forest was greater for tree species with larger average diameters.These patterns suggest that lightning influences forest structure and the global carbon budget by non‐randomly damaging large trees. Moreover, these models provide a framework for investigating the ecological and evolutionary consequences of lightning disturbance in tropical forests.Synthesis. Our findings indicate that the distribution of lightning damage is stochastic at large spatial grain and relatively deterministic at smaller spatial grain (<15 m). Lightning is more likely to directly strike taller trees with large crowns and secondarily damage large neighbouring trees that are closest to the directly struck tree. The results provide a framework for understanding how lightning can affect forest structure, forest dynamics and carbon cycling. The resulting lightning risk model will facilitate informed investigations into the effects of lightning in tropical forests.
more »
« less
DeepForest: A Python package for RGB deep learning tree crown delineation
Abstract Remote sensing of forested landscapes can transform the speed, scale and cost of forest research. The delineation of individual trees in remote sensing images is an essential task in forest analysis. Here we introduce a newPythonpackage, DeepForest that detects individual trees in high resolution RGB imagery using deep learning.While deep learning has proven highly effective in a range of computer vision tasks, it requires large amounts of training data that are typically difficult to obtain in ecological studies. DeepForest overcomes this limitation by including a model pretrained on over 30 million algorithmically generated crowns from 22 forests and fine‐tuned using 10,000 hand‐labelled crowns from six forests.The package supports the application of this general model to new data, fine tuning the model to new datasets with user labelled crowns, training new models and evaluating model predictions. This simplifies the process of using and retraining deep learning models for a range of forests, sensors and spatial resolutions.We illustrate the workflow of DeepForest using data from the National Ecological Observatory Network, a tropical forest in French Guiana, and street trees from Portland, Oregon.
more »
« less
- Award ID(s):
- 1926542
- PAR ID:
- 10455274
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Methods in Ecology and Evolution
- Volume:
- 11
- Issue:
- 12
- ISSN:
- 2041-210X
- Page Range / eLocation ID:
- p. 1743-1751
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Grilli, Jacopo (Ed.)Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is to associate sensor data into individual crowns. While dozens of crown detection algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics. There is a need for a benchmark dataset to minimize differences in reported results as well as support evaluation of algorithms across a broad range of forest types. Combining RGB, LiDAR and hyperspectral sensor data from the USA National Ecological Observatory Network’s Airborne Observation Platform with multiple types of evaluation data, we created a benchmark dataset to assess crown detection and delineation methods for canopy trees covering dominant forest types in the United States. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. The benchmark dataset contains over 6,000 image-annotated crowns, 400 field-annotated crowns, and 3,000 canopy stem points from a wide range of forest types. In addition, we include over 10,000 training crowns for optional use. We discuss the different evaluation data sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as overlapping field-annotated crowns. We provide an example submission and score for an open-source algorithm that can serve as a baseline for future methods.more » « less
-
Summary Leaf angle distribution (LAD) in forest canopies affects estimates of leaf area, light interception, and global‐scale photosynthesis, but is often simplified to a single theoretical value. Here, we present TLSLeAF (Terrestrial Laser Scanning Leaf Angle Function), an automated open‐source method of deriving LADs from terrestrial laser scanning.TLSLeAF produces canopy‐scale leaf angle and LADs by relying on gridded laser scanning data. The approach increases processing speed, improves angle estimates, and requires minimal user input. Key features are automation, leaf–wood classification, beta parameter output, and implementation in R to increase accessibility for the ecology community.TLSLeAF precisely estimates leaf angle with minimal distance effects on angular estimates while rapidly producing LADs on a consumer‐grade machine. We challenge the popular spherical LAD assumption, showing sensitivity to ecosystem type in plant area index and foliage profile estimates that translate toc. 25% andc. 11% increases in canopy net photosynthesis (c. 25%) and solar‐induced chlorophyll fluorescence (c. 11%).TLSLeAF can now be applied to the vast catalog of laser scanning data already available from ecosystems around the globe. The ease of use will enable widespread adoption of the method outside of remote‐sensing experts, allowing greater accessibility for addressing ecological hypotheses and large‐scale ecosystem modeling efforts.more » « less
-
Abstract Tropical forests are increasingly threatened by deforestation and degradation, impacting carbon storage, climate regulations and biodiversity. Restoring these ecosystems is crucial for environmental sustainability, yet monitoring these efforts poses significant challenges. Secondary forests are in a constant state of flux, with growth depending on multiple factors.Remote sensing technologies offer cost‐effective, scalable and transferable solutions, advancing forest restoration monitoring towards more accurate, efficient and real‐time data analysis and interpretation. This review provides a comprehensive evaluation of the current state and advancements in remote sensing technologies applied to monitoring tropical forest restoration.Synthesis and applications: This review brings together the state of the art of remote sensing technologies, such as very‐high‐resolution RGB imagery, multi‐ and hyperspectral imaging, lidar, radar and thermal‐infrared technologies and their applicability in monitoring forest restoration. In conclusion, this review emphasizes the potential of remote sensing technologies, coupled with advanced computational techniques, to enhance global efforts towards effective and sustainable forest restoration monitoring.more » « less
-
null (Ed.)Forests provide biodiversity, ecosystem, and economic services. Information on individual trees is important for understanding forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data collection. While advances in remote sensing techniques allow surveys of individual trees at unprecedented extents, there remain technical challenges in turning sensor data into tangible information. Using deep learning methods, we produced an open-source data set of individual-level crown estimates for 100 million trees at 37 sites across the United States surveyed by the National Ecological Observatory Network’s Airborne Observation Platform. Each canopy tree crown is represented by a rectangular bounding box and includes information on the height, crown area, and spatial location of the tree. These data have the potential to drive significant expansion of individual-level research on trees by facilitating both regional analyses and cross-region comparisons encompassing forest types from most of the United States.more » « less
