Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution ...satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.
Tree height is one of the most important tree attributes in forest inventory. However, using conventional field methods to measure tree height is a laborious and time-consuming process. Despite the ...great interest in the past to facilitate tree height measurements, new, upcoming solutions are not yet thoroughly investigated. In this study, we investigated the applicability of different close-range remote sensing options for tree height measurement in a complex lowland deciduous forest. Six sample plots in a pedunculate oak forest were measured in detail using conventional methods. Close-range remote sensing datasets used in this study represent solutions from low-cost sensors used for hand-held personal laser scanning (PLShh), unmanned–borne laser scanning (ULS) and unmanned aerial vehicle photogrammetry (UAVimage). Each tree in the sample plots was interactively measured directly from the point cloud, and correspondence of the field- and remote sensing measured trees was verified using tree positions collected during fieldwork. Cross-comparisons of different datasets were performed to evaluate the performances of different data sources in the tree height estimation with respect to crown class, tree height and species. All remote sensing data sources correlated well, e.g. biases between remote sensing sources were around ± 1%. The field-measured tree height in general correlated well with remote sensing data sources. The uncertainties and bias of the field measurements were dependent on the tree height and crown class. Field measurements tended to underestimate codominant and intermediate trees at the approximately 1 m magnitude, whilst remote sensing data sources were robust to crown classes. Low-cost ULS used in this study, and very likely in general, may not have enough penetration capability when measuring low and mostly occluded trees, causing missed treetops. PLShh gave tree height estimates closer to the real tree height than those derived from conventional field measurements for trees above 21 m height.
The pre-requisite for sustainable management of natural resources is the availability of timely, cost-effective, and comprehensive information on the status and development trends of the management ...object ...
Quality tree species information gathering is the basis for making proper decisions in forest management. By applying new technologies and remote sensing methods, very high resolution (VHR) satellite ...imagery can give sufficient spatial detail to achieve accurate species-level classification. In this study, the influence of pansharpening of the WorldView-3 (WV-3) satellite imagery on classification results of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) has been evaluated. In order to increase tree species classification accuracy, three different pansharpening algorithms (Bayes, RCS, and LMVM) have been conducted. The LMVM algorithm proved the most effective pansharpening technique. The pixel- and object-based classification were applied to three pansharpened imageries using a random forest (RF) algorithm. The results showed a very high overall accuracy (OA) for LMVM pansharpened imagery: 92% and 96% for tree species classification based on pixel- and object-based approach, respectively. As expected, the object-based exceeded the pixel-based approach (OA increased by 4%). The influence of fusion on classification results was analyzed as well. Overall classification accuracy was improved by the spatial resolution of pansharpened images (OA increased by 7% for pixel-based approach). Also, regardless of pixel- or object-based classification approaches, the influence of the use of pansharpening is highly beneficial to classifying complex, natural, and mixed deciduous forest areas.
The great potential of remote sensing technologies for operational use in sustainable forest management is addressed in this book, which is the reprint of papers published in the Remote Sensing ...Special Issue “Operationalization of Remote Sensing Solutions for Sustainable Forest Management”. The studies come from three continents and cover multiple remote sensing systems (including terrestrial mobile laser scanning, unmanned aerial vehicles, airborne laser scanning, and satellite data acquisition) and a diversity of data processing algorithms, with a focus on machine learning approaches. The focus of the studies ranges from identification and characterization of individual trees to deriving national- or even continental-level forest attributes and maps. There are studies carefully describing exercises on the case study level, and there are also studies introducing new methodologies for transdisciplinary remote sensing applications. Even though most of the authors look forward to continuing their research, nearly all studies introduced are ready for operational use or have already been implemented in practical forestry.
Digital terrain models (DTMs) are important for a variety of applications in geosciences as a valuable information source in forest management planning, forest inventory, hydrology, etc. Despite ...their value, a DTM in a forest area is typically lower quality due to inaccessibility and limited data sources that can be used in the forest environment. In this paper, we assessed the accuracy of close-range remote sensing techniques for DTM data collection. In total, four data sources were examined, i.e., handheld personal laser scanning (PLShh, GeoSLAM Horizon), terrestrial laser scanning (TLS, FARO S70), unmanned aerial vehicle (UAV) photogrammetry (UAVimage), and UAV laser scanning (ULS, LS Nano M8). Data were collected within six sample plots located in a lowland pedunculate oak forest. The reference data were of the highest quality available, i.e., total station measurements. After normality and outliers testing, both robust and non-robust statistics were calculated for all close-range remote sensing data sources. The results indicate that close-range remote sensing techniques are capable of achieving higher accuracy (root mean square error < 15 cm; normalized median absolute deviation < 10 cm) than airborne laser scanning (ALS) and digital aerial photogrammetry (DAP) data that are generally understood to be the best data sources for DTM on a large scale.
The quality and accuracy of Unmanned Aerial System (UAS) products greatly depend on the methods used to define image orientations before they are used to create 3D point clouds. While most studies ...were conducted in non- or partially-forested areas, a limited number of studies have evaluated the spatial accuracy of UAS products derived by using different image block orientation methods in forested areas. In this study, three image orientation methods were used and compared: (a) the Indirect Sensor Orientation (InSO) method with five irregularly distributed Ground Control Points (GCPs); (b) the Global Navigation Satellite System supported Sensor Orientation (GNSS-SO) method using non-Post-Processed Kinematic (PPK) single-frequency carrier-phase GNSS data (GNSS-SO1); and (c) using PPK dual-frequency carrier-phase GNSS data (GNSS-SO2). The effect of the three methods on the accuracy of plot-level estimates of Lorey’s mean height (HL) was tested over the mixed, even-aged pedunculate oak forests of Pokupsko basin located in Central Croatia, and validated using field validation across independent sample plots (HV), and leave-one-out cross-validation (LOOCV). The GNSS-SO2 method produced the HL estimates of the highest accuracy (RMSE%: HV = 5.18%, LOOCV = 4.06%), followed by the GNSS-SO1 method (RMSE%: HV = 5.34%, LOOCV = 4.37%), while the lowest accuracy was achieved by the InSO method (RMSE%: HV = 5.55%, LOOCV = 4.84%). The negligible differences in the performances of the regression models suggested that the selected image orientation methods had no considerable effect on the estimation of HL. The GCPs, as well as the high image overlaps, contributed considerably to the block stability and accuracy of image orientation in the InSO method. Additional slight improvements were achieved by replacing single-frequency GNSS measurements with dual-frequency GNSS measurements and by incorporating PPK into the GNSS-SO2 method.
Digital aerial photogrammetry has recently attracted great attention in forest inventory studies, particularly in countries where airborne laser scanning (ALS) technology is not available. Further ...research, however, is required to prove its practical applicability in deriving three-dimensional (3D) point clouds and canopy surface and height models (CSMs and CHMs, respectively) over different forest types. The primary aim of this study is to investigate the applicability of image-based CHMs at different spatial resolutions (1 m, 2 m, 5 m) for use in stand-level forest inventory, with a special focus on estimation of stand-level merchantable volume of even-aged pedunculate oak (Quercus robur L.) forests. CHMs are generated by subtracting digital terrain models (DTMs), derived from the national digital terrain database, from corresponding digital surface models (DSMs), derived by the process of image matching of digital aerial images. Two types of stand-level volume regression models are developed for each CHM resolution. The first model is based solely on stand-level CHM metrics, whereas in the second model, easily obtainable variables from forest management databases are included in addition to CHM metrics. The estimation accuracies of the stand volume estimates based on stand-level metrics (relative root mean square error RMSE% = 12.53%–13.28%) are similar or slightly higher than those obtained from previous studies in which stand volume estimates were based on plot-level metrics. The inclusion of stand age as an independent variable in addition to CHM metrics improves the accuracy of the stand volume estimates. Improvements are notable for young and middle-aged stands, and negligible for mature and old stands. Results show that CHMs at the three different resolutions are capable of providing reasonably accurate volume estimates at the stand level.
Understorey evaluation is essential in wildlife habitat management, biomass storage and wildfire suppression, among other areas. The lack of a standardised methodology in the field measurements, and ...in their subsequent analysis, forces researchers to look for procedures that effectively extract understorey data to make management decisions corresponding to actual stand conditions. In this sense, when analysing the understorey characteristics from LiDAR data, it is very usual to ask: “what value should we set the understorey height range to?” It is also usual to answer by setting a numeric value on the basis of previous research. Against that background, this research aims to identify the optimal height to canopy base (HCB) filter–LiDAR metric relationship for estimating understorey height (UH) and understorey cover (UC) using LiDAR data in the Pokupsko Basin lowland forest complex (Croatia). First, several HCB values per plot were obtained from field data (measured HCBi—HCBM-i, where i ϵ (minimum, maximum, mean, percentiles)), and then they were modelled based on LiDAR metrics (estimated HCBi—HCBE-i). These thresholds, measured and estimated HCBi per plot, were used as point cloud filters to estimate understorey parameters directly on the point cloud located under the canopy layer. In this way, it was possible to predict the UH with errors (RMSE) between 0.90 and 2.50 m and the UC with errors (RMSE) between 8.8 and 18.6 in cover percentage. Finally, the sensitivity analysis showed the HCB filter (the upper threshold to select the understorey LiDAR points) is the most important factor affecting the UH estimates, while this factor and the LiDAR metric are the most important factors affecting the UC estimates.
Digital terrain models (DTMs) present important data source for different applications in environmental disciplines including forestry. At regional level, DTMs are commonly created using airborne ...digital photogrammetry or airborne laser scanning (ALS) technology. This study aims to evaluate the vertical accuracy of DTMs of different spatial resolutions derived from high-density ALS data and existing photogrammetric (PHM) data in the dense lowland even-aged pedunculate oak forests located in the Pokupsko basin in Central Croatia. As expected, the assessment of DTMs' vertical accuracy using 22 ground checkpoints shows higher accuracy for ALS-derived than for PHM-derived DTMs. Concerning the different resolutions of ALS-derived (0.5 m, 1 m, 2 m, 5 m) and PHM-derived DTMs (0.5 m, 1 m, 2 m, 5 m, 8 m) compared in this research, the ALS-derived DTM with the finest resolution of 0.5 m shows the highest accuracy. The root mean square error (RMSE) and mean error (ME) values for ALS-derived DTMs range from 0.14 m to 0.15 m and from 0.09 to 0.12 m, respectively, and the values decrease with decreasing spatial resolution. For the PHM-derived DTMs, the RMSE and ME values are almost identical regardless of resolution and they are 0.35 m and 0.17 m, respectively. The findings suggest that the 8 m spatial resolution is optimal for a given photogrammetric data, and no finer than 8 m spatial resolution is required. This research also reveals that the national digital photogrammetric data in the study area contain certain errors (outliers) specific to the terrain type, which could considerably affect the DTM accuracy. Thus, preliminary evaluation of photogrammetric data should be done to eliminate possible outliers prior to the DTM generation in lowland forests with flat terrain. In the absence of ALS data, the finding in this research could be of interests to countries, which still rely on similar photogrammetric data for DTM generation. Keywords: DTM, ALS, LiDAR, stereo-photogrammetry, aerial images, even-aged forest stands, Central Croatia
PDF
