Search for: All records

The challenges inherent in field validation data, and real-world light detection and ranging (lidar) collections make it difficult to assess the best algorithms for using lidar to characterize forest stand volume. Here, we demonstrate the use of synthetic forest stands and simulated terrestrial laser scanning (TLS) for the purpose of evaluating which machine learning algorithms, scanning configurations, and feature spaces can best characterize forest stand volume. The random forest (RF) and support vector machine (SVM) algorithms generally outperformed k-nearest neighbor (kNN) for estimating plot-level vegetation volume regardless of the input feature space or number of scans. Also, the measures designed to characterize occlusion using spherical voxels generally provided higher predictive performance than measures that characterized the vertical distribution of returns using summary statistics by height bins. Given the difficulty of collecting a large number of scans to train models, and of collecting accurate and consistent field validation data, we argue that synthetic data offer an important means to parameterize models and determine appropriate sampling strategies. 

ABSTRACT Long-term terrestrial ecosystem monitoring is a critical component of documenting outcomes of land management actions, assessing progress towards management objectives, and guiding realistic long-term ecological goals, all through repeated observation and measurement. Traditional monitoring methods have evolved for specific applications in forestry, ecology, and fire and fuels management. While successful monitoring programs have clear goals, trained expertise, and rigorous sampling protocols, new advances in technology and data management can help overcome the most common pitfalls in data quality and repeatability. This paper presents Terrestrial Laser Scanning (TLS), a specific form of LiDAR (Light Detection and Ranging), as an emerging sampling method that can complement and enhance existing monitoring methods. TLS captures in high resolution the 3D structure of a terrestrial ecosystem (forest, grassland, etc.), and is increasingly efficient and affordable (<$30,000). Integrating TLS into ecosystem monitoring can standardize data collection, improve efficiency, and reduce bias and error. Streamlined data processing pipelines can rigorously analyze TLS data and incorporate constant improvements to inform management decisions and planning. The approach described in this paper utilizes portable, push-button TLS equipment that, when calibrated with initial transect sampling, captures detailed forestry, fuels, and ecological features in less than 5 minutes per plot. We also introduce an interagency automated processing pipeline and dashboard viewer for instant, user-friendly analysis, and data retrieval of hundreds of metrics. Forest metrics and inventories produced with these methods offer effective decision-support data for managers to quantify landscape-scale conditions and respond with efficient action. This protocol further supports interagency compatibility for efficient natural resource monitoring across jurisdictional boundaries with uniform data, language, methods, and data analysis. With continued improvement of scanner capabilities and affordability, these data will shape the future of terrestrial ecosystem monitoring as an important means to address the increasingly fast pace of ecological change facing natural resource managers.