Light detection and ranging (lidar) data is increasingly being used for ecosystem monitoring across geographic scales. This work concentrates on delineating individual trees in topographically-complex, mixed conifer forest across the California’s Sierra Nevada. We delineated individual trees using vector data and a 3D lidar point cloud segmentation algorithm, and using raster data with an object-based image analysis (OBIA) of a canopy height model (CHM). The two approaches are compared to each other and to ground reference data. We used high density (9 pulses/m²), discreet lidar data and WorldView-2 imagery to delineate individual trees, and to classify them by species or species types. We also identified a new method to correct artifacts in a high-resolution CHM. Our main focus was to determine the difference between the two types of approaches and to identify the one that produces more realistic results. We compared the delineations via tree detection, tree heights, and the shape of the generated polygons. The tree height agreement was high between the two approaches and the ground data (r²: 0.93–0.96). Tree detection rates increased for more dominant trees (8–100 percent). The two approaches delineated tree boundaries that differed in shape: the lidar-approach produced fewer, more complex, and larger polygons that more closely resembled real forest structure.

The Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) is one of the most complete and frequently used global-scale DEM products in various applications. However, previous studies have shown that the SRTM DEM is systematically higher than the actual land surface in vegetated mountain areas. The objective of this study is to propose a procedure to calibrate the SRTM DEM over large vegetated mountain areas. Firstly, we developed methods to estimate canopy cover from aerial imagery and tree height from multi-source datasets (i.e., field observations, airborne light detection and ranging (LiDAR) data, Geoscience Laser Altimeter System (GLAS) data, Landsat TM imagery, climate surfaces, and topographic data). Then, the airborne LiDAR derived DEM, covering ~5% of the study area, was used to evaluate the accuracy of the SRTM DEM. Finally, a regression model of the SRTM DEM error depending on tree height, canopy cover, and terrain slope was developed to calibrate the SRTM DEM. Our results show that the proposed procedure can significantly improve the accuracy of the SRTM DEM over vegetated mountain areas. The mean difference between the SRTM DEM and the LiDAR DEM decreased from 12.15 m to −0.82 m, and the standard deviation dropped by 2 m.

The receiver operating characteristic (ROC) and precision–recall (PR) plots have been widely used to evaluate the performance of species distribution models. Plotting the ROC/PR curves requires a traditional test set with both presence and absence data (namely PA approach), but species absence data are usually not available in reality. Plotting the ROC/PR curves from presence‐only data while treating background data as pseudo absence data (namely PO approach) may provide misleading results. In this study, we propose a new approach to calibrate the ROC/PR curves from presence and background data with user‐provided information on a constant c, namely PB approach. Here, c defines the probability that species occurrence is detected (labeled), and an estimate of c can also be derived from the PB‐based ROC/PR plots given that a model with good ability of discrimination is available. We used five virtual species and a real aerial photography to test the effectiveness of the proposed PB‐based ROC/PR plots. Different models (or classifiers) were trained from presence and background data with various sample sizes. The ROC/PR curves plotted by PA approach were used to benchmark the curves plotted by PO and PB approaches. Experimental results show that the curves and areas under curves by PB approach are more similar to that by PA approach as compared with PO approach. The PB‐based ROC/PR plots also provide highly accurate estimations of c in our experiment. We conclude that the proposed PB‐based ROC/PR plots can provide valuable complements to the existing model assessment methods, and they also provide an additional way to estimate the constant c (or species prevalence) from presence and background data.

Many applications of remote sensing only require the classification of a single land type. This is known as the one-class classification problem and it can be performed using either binary classifiers, by treating all other classes as the negative class, or one-class classifiers which only consider the class of interest. The key difference between these two approaches is in their training data and the amount of effort needed to produce it. Binary classifiers require an exhaustively labelled training data set while one-class classifiers are trained using samples of just the class of interest. Given ample and complete training data, binary classifiers generally outperform one-class classifiers. However, what is not clear is which approach is more accurate when given the same amount of labelled training data. That is, for a fixed labelling effort, is it better to use a binary or one-class classifier. This is the question we consider in this article. We compare several binary classifiers, including backpropagation neural networks, support vector machines, and maximum likelihood classifiers, with two one-class classifiers, one-class SVM, and presence and background learning (PBL), on the problem of one-class classification in high-resolution remote sensing imagery. We show that, given a fixed labelling budget, PBL consistently outperforms the other methods. This advantage stems from the fact that PBL is a positive-unlabelled method in which large amounts of readily available unlabelled data is incorporated into the training phase, allowing the classifier to model the negative class more effectively.

Simulating realistic three‐dimensional (3D) forest scenes is useful in understanding the links between forest structure and ecosystem functions (e.g. radiative transfer). Light detection and ranging (LiDAR) technology provides useful 3D data for forest reconstructions since it can characterise 3D structures of individual trees and canopies. High‐density terrestrial LiDAR (terrestrial laser scanning, TLS) is suitable for fine‐scale reconstructions but is limited to smaller forest plots; low‐density airborne LiDAR (airborne laser scanning, ALS) can cover larger areas but is only suitable for coarse‐scale reconstructions. How to take advantage of TLS and ALS to enable fine‐scale forest simulations in large areas needs to be studied. We propose a new voxel‐based method for forest simulations using the integration of TLS and ALS data. TLS data of representative reference trees are used to approximate the detailed architectures of the whole forest scene, with structural information on each individual tree extracted from ALS data. The high‐density point cloud data derived from TLS and ALS data are voxelised using high resolution solid voxels for scene representation. We tested the proposed method using two virtual forests (108 m × 108 m) and a real forest (300 m × 300 m) with conifer and broadleaf species. The physically based ray tracer (PBRT) was used to visualise the true virtual forest scenes, whereas voxel‐based radiative transfer (VBRT) was used to visualise the modelled forest scenes from LiDAR data. For the real forest scene, simulated and real ALS data were compared. Our results demonstrate that the images simulated by VBRT and PBRT are similar in the virtual forest scenes, with average radiance values of 1.02 and 1.72, respectively. In the real forest scene, the distributions of points and individual tree attributes (tree height, crown radius, and tree volume) derived from real and simulated ALS also match well, with Kullback–Leibler divergence ranging from 0.006 to 0.06. We conclude that the new method is capable of modelling fine‐scale 3D forests in large areas (over 1 ha) when TLS and ALS data are available, and it has good potential in studying the process of radiative transfer in conifer and broadleaf forests.

One-class classification is a common situation in remote sensing, where researchers aim to extract a single land type from remotely sensed data. Learning a classifier from labeled positive and unlabeled background data, which is the case-control sampling scenario, is efficient for one-class remote sensing classification because labeled negative data are not necessary for model training. In this study we propose a novel positive and background learning with constraints (PBLC) algorithm to address this one-class classification problem. With user-specified information of maximum probability as the constraint, PBLC infers the posterior probability of positive class directly in one-step model training. We test PBLC on a synthetic dataset and a real aerial photograph to perform different one-class classification tasks. Experimental results demonstrate that PBLC can successfully train linear and nonlinear classifiers including generalized linear model (GLM), artificial neural network (ANN), and convolutional neural network (CNN). Probabilistic and binary predictions by PBLC are more similar to the gold-standard positive-negative method, outperforming the two-step positive and background learning (PBL) algorithm that post-calibrates a naive classifier based on an estimated constant. Hence, the proposed PBLC algorithm has the potential to solve one-class classification problems in the case-control sampling scenario.