As light detection and ranging (LiDAR) technology advances, it has become common for datasets to be acquired at a point density high enough to capture structural information from individual trees. To process these data, an automatic method of isolating individual trees from a LiDAR point cloud is required. Traditional methods for segmenting trees attempt to isolate prominent tree crowns from a canopy height model. We here introduce a novel segmentation method, layer stacking, which slices the entire forest point cloud at 1-m height intervals and isolates trees in each layer. Merging the results from all layers produces representative tree profiles. When compared to watershed delineation (a widely used segmentation algorithm), layer stacking correctly identified 15% more trees in uneven-aged conifer stands, 7%–17% more in even-aged conifer stands, 26% more in mixedwood stands, and 26%–30% more (with 75% of trees correctly detected) in pure deciduous stands. Overall, layer stacking's commission error was mostly similar to or better than that of watershed delineation. Layer stacking performed particularly well in deciduous, leaf-off conditions, even those where tree crowns were less prominent. We conclude that in the tested forest types, layer stacking represents an improvement in segmentation when compared to existing algorithms.

As light detection and ranging (LiDAR) technology becomes more available, it has become common to use these datasets to generate remotely sensed forest inventories across landscapes. Traditional methods for generating these inventories employ the use of height and proportion metrics to measure LiDAR returns and relate these back to field data using predictive models. Here, we employ a three-dimensional convolutional neural network (CNN), a deep learning technique that scans the LiDAR data and automatically generates useful features for predicting forest attributes. We test the accuracy in estimating forest attributes using the three-dimensional implementations of different CNN models commonly used in the field of image recognition. Using the best performing model architecture, we compared CNN performance to models developed using traditional height metrics. The results of this comparison show that CNNs produced 12% less prediction error when estimating biomass, 6% less in estimating tree count, and 2% less when estimating the percentage of needleleaf trees. We conclude that using CNNs can be a more accurate means of interpreting LiDAR data for forest inventories compared to standard approaches.

Light detection and ranging (LiDAR) has become a commonly-used tool for generating remotely-sensed forest inventories. However, LiDAR-derived forest inventories have remained uncommon at a regional scale due to varying parameters among LiDAR data acquisitions and the availability of sufficient calibration data. Here, we present a model using a 3-D convolutional neural network (CNN), a form of deep learning capable of scanning a LiDAR point cloud, combined with coincident satellite data (spectral, phenology, and disturbance history). We compared this approach to traditional modeling used for making forest predictions from LiDAR data (height metrics and random forest) and found that the CNN had consistently lower uncertainty. We then applied the CNN to public data over six New England states in the USA, generating maps of 14 forest attributes at a 10 m resolution over 85% of the region. Aboveground biomass estimates produced a root mean square error of 36 Mg ha⁻¹ (44%) and were within the 97.5% confidence of independent county-level estimates for 33 of 38 or 86.8% of the counties examined. CNN predictions for stem density and percentage of conifer attributes were moderately successful, while predictions for detailed species groupings were less successful. The approach shows promise for improving the prediction of forest attributes from regional LiDAR data and for combining disparate LiDAR datasets into a common framework for large-scale estimation.

The authors developed a series of ecological metrics (EM) based on mechanistic principles for quantifying light detection and ranging (LiDAR) to develop forest inventories. These fall into 5 categories: canopy height, canopy complexity, individual tree attributes, crowding, and abiotic. The authors compared the effectiveness of the EMs with more traditional metrics (e.g., height percentiles) for modeling biomass, tree count, and species. They then examined each model’s ability to transfer to different LiDAR datasets. They found that models based on the EMs performed similarly to those using traditional metrics on a single dataset, while facilitating transference to LiDAR of different density, seasonality, location, and type. Models based on the EMs resulted in an average of 15% less root mean squared error and 331% less bias when transferred, as opposed to traditional metrics. The authors also noted that different EMs were useful for predicting contrasting attributes. Those EMs that quantify height and size were important predictors of biomass. Those that quantify cover, individual tree tallies, shape, and canopy roughness were important predictors of tree count, while those that quantify canopy roughness and sensor parameters were important predictors of species. The authors conclude that the EMs can be useful predictors of forest attributes, and offer analysts better ecological reasoning for LiDAR-based inventories.

Light detection and ranging (LiDAR) has become a commonly-used tool for generating remotely-sensed forest inventories. However, LiDAR-derived forest inventories have remained uncommon at a regional scale due to varying parameters between LiDAR datasets, such as pulse density. Here we develop a regional model using a three-dimensional convolutional neural network (CNN), a form of deep learning capable of scanning a LiDAR point cloud as well as coincident satellite data, identifying features useful for predicting forest attributes, and then making a series of predictions. We compare this to the standard modeling approach for making forest predictions from LiDAR data, and find that the CNN outperformed the standard approach by a large margin in many cases. We then apply our model to publicly available data over New England, generating maps of fourteen forest attributes at a 10 m resolution over 85 % of the region. Our estimates of attributes that quantified tree size were most successful. In assessing aboveground biomass for example, we achieved a root mean square error of 36 Mg/ha (44 %). Our county-level mapped estimates of biomass were in good agreement with federal estimates. Estimates of attributes quantifying stem density and percent conifer were moderately successful, with a tendency to underestimate of extreme values and banding in low density LiDAR acquisitions. Estimate of attributes quantifying detailed species groupings were less successful. Ultimately we believe these maps will be useful to forest managers, wildlife ecologists, and climate modelers in the region.

Nature-based climate solutions (NBS) have become an important component of strategies aiming to reduce atmospheric CO2 and mitigate climate change impacts. Carbon offsets have emerged as one of the most widely implemented NBS strategies, however, these projects have also been criticized for exaggerating offsets. Verifying the efficacy of NBS-derived carbon offset is complicated by a lack of readily available geospatial boundary data. Herein, we detail methods and present a database of nature-based offset project boundaries. This database provides the locations of 575 NBS projects distributed across 55 countries. Geospatial boundaries were aggregated using a combination of scraping data from carbon project registries (n=433, 75.3%) as well as manual georeferencing and digitization (n=127, 22.1%). Database entries include three varieties of carbon projects: avoided deforestation, afforestation, reforestation and re-vegetation, and improved forest management. An accuracy assessment of the georeferencing and digitizing process indicated a high degree of accuracy (intersection over union score of 0.98 ± 0.015).