Detecting and mapping individual trees accurately and automatically from remote sensing images is of great significance for precision forest management. Many algorithms, including classical methods and deep learning techniques, have been developed and applied for tree crown detection from remote sensing images. However, few studies have evaluated the accuracy of different individual tree detection (ITD) algorithms and their data and processing requirements. This study explored the accuracy of ITD using local maxima (LM) algorithm, marker-controlled watershed segmentation (MCWS), and Mask Region-based Convolutional Neural Networks (Mask R-CNN) in a young plantation forest with different test images. Manually delineated tree crowns from UAV imagery were used for accuracy assessment of the three methods, followed by an evaluation of the data processing and application requirements for three methods to detect individual trees. Overall, Mask R-CNN can best use the information in multi-band input images for detecting individual trees. The results showed that the Mask R-CNN model with the multi-band combination produced higher accuracy than the model with a single-band image, and the RGB band combination achieved the highest accuracy for ITD (F1 score = 94.68%). Moreover, the Mask R-CNN models with multi-band images are capable of providing higher accuracies for ITD than the LM and MCWS algorithms. The LM algorithm and MCWS algorithm also achieved promising accuracies for ITD when the canopy height model (CHM) was used as the test image (F1 score = 87.86% for LM algorithm, F1 score = 85.92% for MCWS algorithm). The LM and MCWS algorithms are easy to use and lower computer computational requirements, but they are unable to identify tree species and are limited by algorithm parameters, which need to be adjusted for each classification. It is highlighted that the application of deep learning with its end-to-end-learning approach is very efficient and capable of deriving the information from multi-layer images, but an additional training set is needed for model training, robust computer resources are required, and a large number of accurate training samples are necessary. This study provides valuable information for forestry practitioners to select an optimal approach for detecting individual trees.

The use of unmanned aerial vehicles (UAVs) has increased in the science, technology, engineering, and mathematics (STEM) professions. This means there is a growing need to integrate UAV training into STEM education. This study aimed to develop and evaluate a UAV education module and laboratory exercise for natural resource science students. The study used a series of reusable learning objects (RLOs) to assess students’ prior knowledge of remote sensing and UAVs. Students were taught the steps of UAV data acquisition and processing through lectures and UAV simulation videos. Students applied this knowledge by completing a laboratory exercise that used previously collected UAV data. Student knowledge retention and understanding were evaluated using an online quiz to determine the effectiveness of the education module. The average quiz score was 92%, indicating that the UAV laboratory exercise effectively taught students about UAV data acquisition and processing for natural resource research. Overall, students expressed positive opinions about the UAV education module. Student feedback indicated that the laboratory exercise was engaging, but some students would have preferred a hands-on experience for some parts of the exercise. However, in-person UAV instruction may not be accessible for all educators because of UAV cost or lack of instructor training. This study provides educators with crucial recommendations for designing UAV exercises to improve access to UAV-related educational content. This study indicates that online training can effectively introduce students to UAVs. Given the wide range of UAV uses across STEM fields, students in many STEM disciplines would benefit from UAV education.

Soil ecosystem services (ES) (e.g., provisioning, regulation/maintenance, and cultural) and ecosystem disservices (ED) are dependent on soil diversity/pedodiversity (variability of soils), which needs to be accounted for in the economic analysis and business decision-making. The concept of pedodiversity (biotic + abiotic) is highly complex and can be broadly interpreted because it is formed from the interaction of atmospheric diversity (abiotic + biotic), biodiversity (biotic), hydrodiversity (abiotic + biotic), and lithodiversity (abiotic) within ecosphere and anthroposphere. Pedodiversity is influenced by intrinsic (within the soil) and extrinsic (outside soil) factors, which are also relevant to ES/ED. Pedodiversity concepts and measures may need to be adapted to the ES framework and business applications. Currently, there are four main approaches to analyze pedodiversity: taxonomic (diversity of soil classes), genetic (diversity of genetic horizons), parametric (diversity of soil properties), and functional (soil behavior under different uses). The objective of this article is to illustrate the application of pedodiversity concepts and measures to value ES/ED with examples based on the contiguous United States (U.S.), its administrative units, and the systems of soil classification (e.g., U.S. Department of Agriculture (USDA) Soil Taxonomy, Soil Survey Geographic (SSURGO) Database). This study is based on a combination of original research and literature review examples. Taxonomic pedodiversity in the contiguous U.S. exhibits high soil diversity, with 11 soil orders, 65 suborders, 317 great groups, 2026 subgroups, and 19,602 series. The ranking of “soil order abundance” (area of each soil order within the U.S.) expressed as the proportion of the total area is: (1) Mollisols (27%), (2) Alfisols (17%), (3) Entisols (14%), (4) Inceptisols and Aridisols (11% each), (5) Spodosols (3%), (6) Vertisols (2%), and (7) Histosols and Andisols (1% each). Taxonomic, genetic, parametric, and functional pedodiversity are an essential context for analyzing, interpreting, and reporting ES/ED within the ES framework. Although each approach can be used separately, three of these approaches (genetic, parametric, and functional) fall within the “umbrella” of taxonomic pedodiversity, which separates soils based on properties important to potential use. Extrinsic factors play a major role in pedodiversity and should be accounted for in ES/ED valuation based on various databases (e.g., National Atmospheric Deposition Program (NADP) databases). Pedodiversity is crucial in identifying soil capacity (pedocapacity) and “hotspots” of ES/ED as part of business decision making to provide more sustainable use of soil resources. Pedodiversity is not a static construct but is highly dynamic, and various human activities (e.g., agriculture, urbanization) can lead to soil degradation and even soil extinction.

Island ecosystems are particularly susceptible to climate change and human activities. The change of land use and land cover (LULC) has considerable impacts on island ecosystems, and there is a critical need for a free and open-source tool for detecting land cover fluctuations and spatial distribution. This study used Google Earth Engine (GEE) to explore land cover classification and the spatial pattern of major land cover change from 1990 to 2019 on Haitan Island, China. The land cover classification was performed using multiple spectral bands (RGB, NIR, SWIR), vegetation indices (NDVI, NDBI, MNDWI), and tasseled cap transformation of Landsat images based on the random forest supervised algorithm. The major land cover conversion processes (transfer to and from) between 1990 and 2019 were analyzed in detail for the years of 1990, 2000, 2007, and 2019, and the overall accuracies ranged from 88.43% to 91.08%, while the Kappa coefficients varied from 0.86 to 0.90. During 1990–2019, other land, cultivated land, sandy land, and water area decreased by 30.70%, 13.63%, 3.76%, and 0.95%, respectively, while forest and built-up land increased by 30.94% and 16.20% of the study area, respectively. The predominant land cover was other land (34.49%) and cultivated land (26.80%) in 1990, which transitioned to forest land (53.57%) and built-up land (23.07%) in 2019. Reforestation, cultivated land reduction, and built-up land expansion were the major land cover change processes on Haitan Island. The spatial pattern of forest, cultivated land, and built-up land change is mainly explained by the implementation of a ‘Grain for Green Project’ and ‘Comprehensive Pilot Zone’ policy on Haitan Island. Policy and human activities are the major drivers for land use change, including reforestation, population growth, and economic development. This study is unique because it demonstrates the use of GEE for continuous monitoring of the impact of reforestation efforts and urbanization in an island environment.