Remote sensing (RS) technologies, particularly light detection and ranging (LiDAR) and multispectral (MS) imagery, provide broad-scale vegetation monitoring capabilities at varying spatial resolutions. Remotely piloted aircraft systems (RPAS) equipped with LiDAR and MS sensors can enhance vegetation assessments by offering flexible flight schedules and capturing fine-resolution data. Further integration of deep learning (DL) models holds promise for automating the post-processing workflow, which is particularly important for vegetation monitoring applications. This protocol outlines a suite of practical methods for collecting, processing, aligning, and merging RPAS-based LiDAR and MS data for individual 3D tree delineation using an interactive DL plugin. The proprietary DL model effectively detects and segments tree boundaries across various sensors, study sites, and data resolutions within forest ecosystems. Our specific application and motivation for developing this protocol and tool is for monitoring forest recovery on reclaimed oil and gas wellsites. Currently field-based assessment methods are time-consuming, labor-intensive, and spatially limited. As reclamation efforts expand, there is a growing need for more efficient, and scalable approaches to monitor reclamation success and ecosystem recovery. By advancing RPAS-based DL applications, this research supports the monitoring of ecological recovery on reclaimed wellsites and is also applicable to other forested landscapes.

Remote sensing (RS) technologies, particularly light detection and ranging (LiDAR) and multispectral (MS) imagery, provide broad-scale vegetation monitoring capabilities at varying spatial resolutions. Remotely piloted aircraft systems (RPAS) equipped with LiDAR and MS sensors can enhance vegetation assessments by offering flexible flight schedules and capturing fine-resolution data. Further integration of deep learning (DL) models holds promise for automating the post-processing workflow, which is particularly important for vegetation monitoring applications. This protocol outlines a suite of practical methods for collecting, processing, aligning, and merging RPAS-based LiDAR and MS data for individual 3D tree delineation using an interactive DL plugin. The proprietary DL model effectively detects and segments tree boundaries across various sensors, study sites, and data resolutions within forest ecosystems. Our specific application and motivation for developing this protocol and tool is for monitoring forest recovery on reclaimed oil and gas wellsites. Currently field-based assessment methods are time-consuming, labor-intensive, and spatially limited. As reclamation efforts expand, there is a growing need for more efficient, and scalable approaches to monitor reclamation success and ecosystem recovery. By advancing RPAS-based DL applications, this research supports the monitoring of ecological recovery on reclaimed wellsites and is also applicable to other forested landscapes.

Responsible resource development in Alberta requires the reclamation of disturbed lands to achieve equivalent land capability to pre-disturbance conditions. Vegetation assessments on reclaimed wellsites and oil sand exploration (OSE) sites currently rely on plots placed in areas deemed representative using professional judgement, which may introduce sampling bias. This study compared woody vegetation attributes derived from conventionally placed plots with those from randomly placed plots on certified reclaimed sites. Furthermore, increased sampling intensity was evaluated on a subset of sites. Site-level plot-based estimates were also compared with estimates from uncrewed aerial vehicle light detection and ranging (UAV-LiDAR) and airborne laser scanning (ALS). Woody stem density and height estimates from random and judgment-based plots were generally comparable; however, on sites with spatially heterogeneous recovery, judgment-based placement tended to overestimate woody stem density relative to larger-area sampling. LiDAR data captured spatial patterns of woody vegetation but underestimated stem densities, particularly on high-density, clustered sites.