It is anticipated that many of the future forest mapping applications will be based on three-dimensional (3D) point clouds. A comparison study was conducted to verify the explanatory power and information contents of several 3D remote sensing data sources on the retrieval of above ground biomass (AGB), stem volume (VOL), basal area (G), basal-area weighted mean diameter (D_g) and Lorey’s mean height (H_g) at the plot level, utilizing the following data: synthetic aperture radar (SAR) Interferometry, SAR radargrammetry, satellite-imagery having stereo viewing capability, airborne laser scanning (ALS) with various densities (0.8–6 pulses/m²) and aerial stereo imagery. Laser scanning is generally known as the primary source providing a 3D point cloud. However, photogrammetric, radargrammetric and interferometric techniques can be used to produce 3D point clouds from space- and air-borne stereo images. Such an image-based point cloud could be utilized in a similar manner as ALS providing that accurate digital terrain model is available. In this study, the performance of these data sources for providing point cloud data was evaluated with 91 sample plots that were established in Evo, southern Finland within a boreal forest zone and surveyed in 2014 for this comparison. The prediction models were built using random forests technique with features derived from each data sources as independent variables and field measurements of forest attributes as response variable. The relative root mean square errors (RMSEs) varied in the ranges of 4.6% (0.97 m)–13.4% (2.83 m) for H_g, 11.7% (3.0 cm)–20.6% (5.3 cm) for D_g, 14.8% (4.0 m²/ha)–25.8% (6.9 m²/ha) for G, 15.9% (43.0 m³/ha)–31.2% (84.2 m³/ha) for VOL and 14.3% (19.2 Mg/ha)–27.5% (37.0 Mg/ha) for AGB, respectively, depending on the data used. Results indicate that ALS data achieved the most accurate estimates for all forest inventory attributes. For image-based 3D data, high-altitude aerial images and WorldView-2 satellite optical image gave similar results for H_g and D_g, which were only slightly worse than those of ALS data. As expected, spaceborne SAR data produced the worst estimates. WorldView-2 satellite data performed well, achieving accuracy comparable to the one with ALS data for G, VOL and AGB estimation. SAR interferometry data seems to contain more information for forest inventory than SAR radargrammetry and reach a better accuracy (relative RMSE decreased from 13.4% to 9.5% for H_g, 20.6% to 19.2% for D_g, 25.8% to 20.9% for G, 31.2% to 22.0% for VOL and 27.5% to 20.7% for AGB, respectively). However, the availability of interferometry data is limited. The results confirmed the high potential of all 3D remote sensing data sources for forest inventory purposes. However, the assumption of using other than ALS data is that there exist a high quality digital terrain model, in our case it was derived from ALS.

Airborne hyperspectral images are used for crop identification with a high classification accuracy because of their high spectral resolution, spatial resolution, and signal-to-noise ratio (SNR). However, the tradeoffs between the three core parameters of a hyperspectral imager (SNR, spatial resolution, and spectral resolution) should be considered for designing an efficient imaging system. Only a few reported studies on the analysis of the impact of SNR on identification accuracy are available. Further, the tradeoffs and mutual interactions among these parameters are rarely considered. In this empirical study, our aim was to understand the relationship among the core parameters and their effects on crop identification accuracy by analyzing the tradeoffs and mutual interactions among these parameters. We analyzed the hyperspectral images of a typical plain agricultural area in Xiongan, China, acquired by the newly developed sensor airborne multimodular imaging spectrometer (AMMIS). The fundamental images were transformed to form datasets with different ranges of spectral resolution, spatial resolution, and SNR using data reconstruction methods. We adopted the classification and regression tree (CART), random forest (RF), and k-nearest neighbor (kNN) classifiers, and observed the overall accuracy (OA) across the degraded hyperspectral datasets. The experimental results indicated that the OA decreased with a decreasing SNR. As the spectral resolution became coarser, the OA first increased, plateaued, and then decreased. However, the OA increased with decreasing spatial resolution. This study was performed with the goal of bridging the knowledge gap between the back-end hyperspectral sensor designing and its front-end applications.

Digital maps of road networks are a vital part of digital cities and intelligent transportation. In this paper, we provide a comprehensive review on road extraction based on various remote sensing data sources, including high-resolution images, hyperspectral images, synthetic aperture radar images, and light detection and ranging. This review is divided into three parts. Part 1 provides an overview of the existing data acquisition techniques for road extraction, including data acquisition methods, typical sensors, application status, and prospects. Part 2 underlines the main road extraction methods based on four data sources. In this section, road extraction methods based on different data sources are described and analysed in detail. Part 3 presents the combined application of multisource data for road extraction. Evidently, different data acquisition techniques have unique advantages, and the combination of multiple sources can improve the accuracy of road extraction. The main aim of this review is to provide a comprehensive reference for research on existing road extraction technologies.

Multispectral airborne laser scanning (ALS) data have recently become available. The objective of this letter is to study the feasibility of these data for road mapping-for road detection and road surface classification. The results are compared with the results of traditional aerial ortho images using object-based image analysis and Random Forest classification. The results demonstrate that the multispectral ALS data are feasible for automatic road detection and a significant improvement compared to the use of optical aerial imagery is obtained. In a test using ALS data, 80.5% points representing roads were classified correctly. When aerial images were used, the percentage decreased to 71.6%.

The widespread tree mortality caused by the European spruce bark beetle (Ips typographus L.) is a significant concern for Norway spruce-dominated (Picea abies H. Karst) forests in Europe and there is evidence of increases in the affected areas due to climate warming. Effective forest monitoring methods are urgently needed for providing timely data on tree health status for conducting forest management operations that aim to prepare and mitigate the damage caused by the beetle. Unoccupied aircraft systems (UASs) in combination with machine learning image analysis have emerged as a powerful tool for the fast-response monitoring of forest health. This research aims to assess the effectiveness of deep neural networks (DNNs) in identifying bark beetle infestations at the individual tree level from UAS images. The study compares the efficacy of RGB, multispectral (MS), and hyperspectral (HS) imaging, and evaluates various neural network structures for each image type. The findings reveal that MS and HS images perform better than RGB images. A 2D-3D-CNN model trained on HS images proves to be the best for detecting infested trees, with an F1-score of 0.759, while for dead and healthy trees, the F1-scores are 0.880 and 0.928, respectively. The study also demonstrates that the tested classifier networks outperform the state-of-the-art You Only Look Once (YOLO) classifier module, and that an effective analyzer can be implemented by integrating YOLO and the DNN classifier model. The current research provides a foundation for the further exploration of MS and HS imaging in detecting bark beetle disturbances in time, which can play a crucial role in forest management efforts to combat large-scale outbreaks. The study highlights the potential of remote sensing and machine learning in monitoring forest health and mitigating the impacts of biotic stresses. It also offers valuable insights into the effectiveness of DNNs in detecting bark beetle infestations using UAS-based remote sensing technology.

The objective of this study is to investigate the potential of novel neural network architectures for measuring the quality and quantity parameters of silage grass swards, using drone RGB and hyperspectral images (HSI), and compare the results with the random forest (RF) method and handcrafted features. The parameters included fresh and dry biomass (FY, DMY), the digestibility of organic matter in dry matter (D-value), neutral detergent fiber (NDF), indigestible neutral detergent fiber (iNDF), water-soluble carbohydrates (WSC), nitrogen concentration (Ncont) and nitrogen uptake (NU); datasets from spring and summer growth were used. Deep pre-trained neural network architectures, the VGG16 and the Vision Transformer (ViT), and simple 2D and 3D convolutional neural networks (CNN) were studied. In most cases, the neural networks outperformed RF. The normalized root-mean-square errors (NRMSE) of the best models were for FY 19% (2104 kg/ha), DMY 21% (512 kg DM/ha), D-value 1.2% (8.6 g/kg DM), iNDF 12% (5.1 g/kg DM), NDF 1.1% (6.2 g/kg DM), WSC 10% (10.5 g/kg DM), Ncont 9% (2 g N/kg DM), and NU 22% (11.9 N kg/ha) using independent test dataset. The RGB data provided good results, particularly for the FY, DMY, WSC and NU. The HSI datasets provided advantages for some parameters. The ViT and VGG provided the best results with the RGB data, whereas the simple 3D-CNN was the most consistent with the HSI data.