Search Results (643)

The existing deep learning-based Airborne Laser Scanning (ALS) point cloud semantic segmentation methods require a large amount of labeled data for training, which is not always feasible in practice. Insufficient training data may lead to over-fitting. To address this issue, we propose a novel Multi-branch Feature Extractor (MFE) and a three-stage transfer learning strategy that conducts pre-training on multi-source ALS data and transfers the model to another dataset with few samples, thereby improving the model’s generalization ability and reducing the need for manual annotation. The proposed MFE is based on a novel multi-branch architecture integrating Neighborhood Embedding Block (NEB) and Point Transformer Block (PTB); it aims to extract heterogeneous features (e.g., geometric features, reflectance features, and internal structural features) by leveraging the parameters contained in ALS point clouds. To address model transfer, a three-stage strategy was developed: (1) A pre-training subtask was employed to pre-train the proposed MFE if the source domain consisted of multi-source ALS data, overcoming parameter differences. (2) A domain adaptation subtask was employed to align cross-domain feature distributions between source and target domains. (3) An incremental learning subtask was proposed for continuous learning of novel categories in the target domain, avoiding catastrophic forgetting. Experiments conducted on the source domain consisted of DALES and Dublin datasets and the target domain consists of ISPRS benchmark dataset. The experimental results show that the proposed method achieved the highest OA of 85.5% and an average F1 score of 74.0% using only 10% training samples, which means the proposed framework can reduce manual annotation by 90% while keeping competitive classification accuracy. Full article

Hundreds of Japanese features of war (field positions, tunnels, and fortifications) were constructed in Hong Kong during World War II. However, most of them were poorly documented and were left unknown but still in relatively good condition because of their durable design, workmanship, and remoteness. These features of war form parts of Hong Kong’s brutal history. Conservation, at least in digital form, is worth considering. With the authors coming from multidisciplinary and varied backgrounds, this paper aims to explore these features using a scientific workflow. First, we reviewed the surviving archival sources of the Imperial Japanese Army and Navy. Second, airborne LiDAR data were used to form territory digital terrain models (DTM) based on the Red Relief Image Map (RRIM) for identifying suspected locations. Third, field expeditions of searching for features of war were conducted through guidance of Global Navigation Satellite System—Real-Time Kinetics (GNSS-RTK). Fourth, the found features were 3D-laser scanned to generate mesh models as a digital archive and validate the findings of DTM-RRIM. This study represents a reverse-engineering effort to reconstruct the planned Japanese defense tactics of guerilla fight and Kamikaze grottos that were never used in Hong Kong. Full article

This paper explores ways to improve the coordinate transformation of maps from the First and Second Military Surveys of the Austro-Hungarian Monarchy using airborne laser scanning (ALS) data. The paper analyses the current positional accuracy of georeferenced maps from the first two military mappings from available spatial data sources. Several areas of interest with different terrain ruggedness (plain, undulated terrain, mountains) were selected for analysis to investigate whether terrain ruggedness has an impact on the accuracy of these maps. The next part of the paper deals with the georeferencing of military mapping maps using current, mid-20th-century maps and ALS data using affine and second-degree polynomial transformations. The paper concludes with a statistical analysis and evaluation of the potential of ALS data for solving this type of problem. The results obtained in the paper indicate that ALS data can be a suitable source for finding control points to transform early topographic maps. Full article

The pre-training and fine-tuning paradigm has significantly advanced satellite remote sensing applications. However, its potential remains largely underexplored for airborne laser scanning (ALS), a key technology in domains such as forest management and urban planning. In this study, we address this gap by constructing a large-scale ALS point cloud dataset and evaluating its effectiveness in downstream applications. We first propose a simple, generalizable framework for dataset construction, designed to maximize land cover and terrain diversity while allowing flexible control over dataset size. We instantiate this framework using ALS, land cover, and terrain data collected across the contiguous United States, resulting in a dataset geographically covering 17,000 + ${\mathrm{km}}^2$ (184 billion points) with diverse land cover and terrain types included. As a baseline self-supervised learning model, we adopt BEV-MAE, a state-of-the-art masked autoencoder for 3D outdoor point clouds, and pre-train it on the constructed dataset. The resulting models are fine-tuned for several downstream tasks, including tree species classification, terrain scene recognition, and point cloud semantic segmentation. Our results show that pre-trained models consistently outperform their counterparts trained from scratch across all downstream tasks, demonstrating the strong transferability of the learned representations. Additionally, we find that scaling the dataset using the proposed framework leads to consistent performance improvements, whereas datasets constructed via random sampling fail to achieve comparable gains. Full article

As the frequency of strong storms and cyclones increases, understanding wind risk in both existing and newly established plantation forests is becoming increasingly important. Recent advances in the quality and availability of remotely sensed data have significantly improved our capability to make large-scale wind risk predictions. This study models the loss of radiata pine (Pinus radiata D.Don) plantations following a severe cyclone within the Gisborne Region of New Zealand through leveraging repeat regional LiDAR acquisitions, optical imagery, and various surfaces describing key climatic, topographic, and storm-specific conditions. A random forest model was trained on 9713 plots classified as windthrow or no-windthrow. Model validation using 50 iterations of 80/20 train/test splits achieved robust accuracy (accuracy = 0.835; F1 score = 0.841; AUC = 0.913). In comparison to most European empirical models (AUC = 0.51–0.90), our framework demonstrated superior discrimination, underscoring its value for regions prone to cyclones. Among the 14 predictor variables, the most influential were mean windspeed during February, the wind exposition index, site drainage, and stand age. Model predictions closely aligned with the estimated 3705 hectares of cyclone-induced forest damage and indicated that 20.9% of unplanted areas in the region would be at risk of windthrow at age 30 if established in radiata pine. The resulting wind risk surface serves as a valuable decision-support tool for forest managers, helping to mitigate wind risk in existing forests and guide adaptive afforestation strategies. Although developed for radiata pine plantations in New Zealand, the approach and findings have broader relevance for forest management in cyclone-prone regions worldwide, particularly where plantation forestry is widely practised. Full article

The monitoring and assessment of forest conditions has traditionally relied on continuous forest inventory (CFI) plots, where all plot trees are regularly measured at discrete locations, then plots are grouped as representative samples of forested areas via stand-based inventory expectations. Remote sensing data acquisitions, such as airborne laser scanning (ALS), are becoming more widely applied to operational forestry to derive similar stand-based inventories. Although ALS systems are widely applied to assess forest metrics associated with crowns and canopies, limited studies have compared ALS-derived digital inventories to CFI datasets. In this study, we conducted an analysis of over 1000 CFI plot locations on ~611,000 acres and compared it to a single-tree derived inventory. Inventory metrics from CFI data were forward modeled from 2016 to 2019 using the USDA Forest Service Forest Vegetation Simulator (FVS) to produce estimates of trees per acre (TPA), basal area (BA) per tree or per plot, basal area per acre (BAA), and volume per acre (VPA) and compared to the ALS-derived Digital Inventory^® (DI) of 2019. The CFI data provided greater on-plot tree counts, BA, and volume compared to the DI when limited to trees ≥5 inches DBH. On-plot differences were less significant for taller trees and increasingly diverged for shorter trees (<20 feet tall) known to be less detectable by ALS. The CFI volume was found to be 44% higher than the ALS-derived DI suggesting mean volume per acre as derived from plot sampling methods may not provide accurate results when expanded across the landscape given variable forest conditions not captured during sampling. These results provide support that when used together, CFI and DI datasets represent a powerful set of tools within the forest management toolkit. Full article

Forests grow under dynamic conditions influenced by vegetation structure and environmental factors. However, empirical models to enhance growing stock volume GSV) estimation are commonly established based on structural information from airborne laser scanning (ALS) data, raising important questions regarding the models’ performance across time (temporal transferability). This study presents the integration of ALS and microclimate and site-specific data to assess the temporal transferability of GSV models at the plot level in a mixed forest located in Milicz, Poland, between 2007 (t₁) and 2015 (t₂). We compared random forest (RF), multiple linear regression (MLR), and generalized additive models (GAMs) across three modelling scenarios, ALS + site type + climate (sa), ALS only (sb), and ALS + site type (sc), and also performed internal and external validation to assess temporal transferability. Among the three modelling approaches, GAMs outperformed the MLR and RF models in internal validation, improving the R² by 6%–8% and reducing the rRMSE by 6%–12%. We found that climate was significant in GSV prediction when integrated with ALS and site conditions, with a permutation test (p ≤ 0.023) based on the rRMSE confirming climate significance. The direct contribution of climate to model performance was marginal on a broad scale. However, its influence on GSV and temporal transferability seem stronger in homogenous sites. In general, RF was the most stable in both the forward (t₁→t₂) and backward (t₂→t₁) directions in the sa scenario unlike the GAM, which was more stable in the backward direction. This study provides a framework for assessing the reliability of GSV models and addresses a critical gap in forest monitoring. Full article

Forest managers need stand-level forest inventories to make operational decisions and model growth and yield to inform long-term planning. However, few studies have quantified errors in field sampling- and airborne laser scanning (ALS)-derived inventories at the stand level, particularly in species-diverse and structurally diverse mixed conifer forests. In this study, we compared stand-level metrics derived from field cruise measurements of a forest-wide stratified sample of variable-radius plots, an ALS-derived area-based approach (ABA) trained and tested using an independent sample of fixed-area stem-mapped plots, and two ALS-derived individual tree approaches. Inventory volume estimates were validated using the gross volume of harvested logs from multi-stand harvest data, tracked by load and location and scaled at the processing mill. Results show that the ABA and individual tree approaches produced stand-level volume estimates with similar errors (−8 to 6%) to the cruise estimated volume (−16 to 6%) when compared with scaled volume. Across the entire forest, regression-based equivalence tests showed that merchantable and total stand volume estimates between the cruise and ALS-derived individual tree methods were more similar than between cruise and ABA methods, potentially due to underestimation of trees by both cruise and individual tree methods in some areas of the study area. Our results also highlight important differences between conventional cruise inventories and ALS-derived inventories, such as the spatial variability of within-stand attributes that ALS inventories provide. Overall, this study improves our understanding of the limitations and advantages of conventional and ALS-derived stand-level inventories in mixed conifer, structurally diverse forests. Full article

Traditional remote sensing techniques face notable limitations in accurately estimating forest canopy height. Optical data often suffer from vegetation occlusion, while radar systems, though capable of penetrating foliage, show reduced accuracy in complex terrains. The Global Ecosystem Dynamics Investigation (GEDI), a spaceborne LiDAR mission, offers high-resolution measurements that address these challenges. However, the complexity of waveform processing and the influence of geolocation uncertainty demand rigorous assessment. This study employs GEDI Version 2.0 data, which demonstrates substantial improvement in geolocation accuracy compared to Version 1.0, and integrates airborne laser scanning (ALS) data from the Changbai Mountain forest region to simulate GEDI waveforms. A Monte Carlo-based approach was used to quantify and correct geolocation offsets, resulting in a reduction in the average relative error (defined as the mean of the absolute differences between estimated and reference canopy heights divided by the reference values) in canopy height estimates from 11.92% to 8.55%. Compared to traditional correction strategies, this method demonstrates stronger robustness in heterogeneous forest conditions. The findings emphasize the effectiveness of simulation-based optimization in enhancing the geolocation accuracy and canopy height retrieval reliability of GEDI data, especially in complex terrain environments. This contributes to more precise global forest structure assessments and provides a methodological foundation for future improvements in spaceborne LiDAR applications. Full article

We applied UAV (Unmanned Aerial Vehicle) and ALS (Airborne Laser Scanning) remote sensing methods to identify terrain obstacles encountered during timber extraction in the skidding process with the aim of proposing accessibility solutions to the inner parts of forest stands using skidding trails. At the Vítovický žleb site, located east of Brno in the South Moravian Region of the Czech Republic, we analysed the accuracy of digital terrain models (DTMs) created from UAV LiDAR (Light Detection and Ranging), RGB (Red–Green–Blue) UAV, ALS data taken on site and publicly available LiDAR data DMR 5G (Digital Model of Relief of the Czech Republic, 5th Generation, based on airborne laser scanning, providing pre-classified ground points with an average density of 1 point/m²). UAV data were obtained using two types of drones: a DJI Mavic 2 mounted with an RGB photogrammetric camera and a GeoSLAM Horizon laser scanner on a DJI M600 Pro hexacopter. We achieved the best accuracy with UAV technologies, with an average deviation of 0.06 m, compared to 0.20 m and 0.71 m for ALS and DMR 5G, respectively. The RMSE (Root Mean Square Error) values further confirm the differences in accuracy, with UAV-based models reaching as low as 0.71 m compared to over 1.0 m for ALS and DMR 5G. The results demonstrated that UAVs are well-suited for detailed analysis of rugged terrain morphology and obstacle identification during timber extraction, potentially replacing physical terrain surveys for timber extraction planning. Meanwhile, ALS and DMR 5G data showed significant potential for use in planning the placement of skidding trails and determining the direction and length of timber extraction from logging sites to forest roads, primarily due to their ability to cover large areas effectively. Differences in the analysis results obtained using GIS (Geographic Information System) cost surface solutions applied to ALS and DMR 5G data DTMs were evident on logging sites with terrain obstacles, where the site-specific ALS data proved to be more precise. While DMR 5G is based on ALS data, its generalised nature results in lower accuracy, making site-specific ALS data preferable for analysing rugged terrain and planning timber extractions. However, DMR 5G remains suitable for use in more uniform terrain without obstacles. Thus, we recommend combining UAV and ALS technologies for terrain with obstacles, as we found this approach optimal for efficiently planning the logging-transport process. Full article

Accurate estimates of aboveground biomass (AGB) are essential for forest policies to reduce carbon emissions. Unmanned aerial laser scanning (UAV-LS) offers unprecedented millimetric detail but is underutilized in monitoring broadleaf Mediterranean forests compared to coniferous ones. This study aims to design and evaluate a procedure for AGB estimates based on the predictive power of crown features. In the first step, we manually created Quantitative Structure Models (QSMs) for 320 trees using data from UAV laser scanning (UAV-LS), airborne laser scanning (ALS), and co-registered terrestrial laser scanning (TLS). This provided the most accurate non-destructive estimate of aboveground biomass (AGB) in the absence of destructive measurements. For each reference tree we also measured crown projection and crown volume to build two separated models relating AGB to such crown features. In the second phase, we evaluated the potential of UAV-LS for quantifying AGB in a pure European beech (Fagus sylvatica) forest and compared it with traditional ALS estimates, using fully automatic procedures. The two obtained tree-level AGB models were then tested using three datasets derived from 35 sampling plots over the same study area: (a) 1130 trees manually segmented (phase-2 reference); (b) trees automatically extracted from ALS data; and (c) trees automatically extracted from UAV-LS data. Results demonstrate that detailed UAV-LS data improve model sensitivity compared to ALS data (RMSE = 45.6 Mg ha⁻¹, RMSE% = 13.4%, R2 = 0.65, for the best ALS model; RMSE = 44.0 Mg ha⁻¹, RMSE% = 12.9%, R2 = 0.67, for the best UAV-LS model), allowing for the detection of AGB differences even in quite homogenous forest structures. Overall, this study demonstrates the combined use of both laser scanner data can foster non-destructive and more precise AGB estimation than the use of only one, in forested areas across hectare scales (1 to 100 ha). Full article

Airborne hyperspectral LiDAR (AHSL) is a technology that integrates the spectral content collected using hyperspectral imaging and the precise 3D descriptions of observed objects obtained using LiDAR (light detection and ranging). AHSL detects the spectral and three-dimensional (3D) information on an object simply using laser measurements. Nevertheless, the advantageous richness of spectral properties also introduces novel issues into the scan unit, the mechanical–optical trade-off. Specifically, the abundant spectral information requires a larger optical aperture, limiting the acceptance of the mechanic load by the scan unit at a demanding rotation speed and flight height. Via the simulation and analysis of scan models, it is exhibited that Palmer scans fit the large optical aperture required by AHSL best. Furthermore, based on the simulation of the Palmer scan model, 45.23% is explored as the optimized ratio of overlap (ROP) for minimizing the diversity of the point density, with a reduction in the coefficient of variation (CV) from 0.47 to 0.19. The other issue is that it is intricate to calibrate the scanning geometry using outside devices due to the complex optical path. A self-calibration strategy is proposed for tackling this problem, which integrates indoor laser vector retrieval and airborne orientation correction. The strategy is composed of the following three improvements: (1) A self-determined laser vector retrieval strategy that utilizes the self-ranging feature of AHSL itself is proposed for retrieving the initial scanning laser vectors with a precision of 0.874 mrad. (2) A linear residual estimated interpolation method (LREI) is proposed for enhancing the precision of the interpolation, reducing the RMSE from 1.517 mrad to 0.977 mrad. Compared to the linear interpolation method, LREI maintains the geometric features of Palmer scanning traces. (3) A least-deviated flatness restricted optimization (LDFO) algorithm is used to calibrate the angle offset in aerial scanning point cloud data, which reduces the standard deviation in the flatness of the scanning plane from 1.389 m to 0.241 m and reduces the distortion of the scanning strip. This study provides a practical scanning method and a corresponding calibration strategy for AHSL. Full article

Precise forest inventory is the key to sustainable forest management. LiDAR technology is widely applied to tree attribute extraction. Therefore, this study compared DBH and tree height derived from Handheld Mobile Laser Scanning (HMLS), Airborne Laser Scanning (ALS), and Integrated ALS and HMLS and determined the applicability of integrating HMLS and ALS scanning methods to estimate individual tree attributes such as diameter at breast height (DBH) and tree height in pine forests of South Korea. There were strong correlations for DBH at the individual tree level (r > 0.95; p < 0.001). HMLS and Integrated ALS-HMLS achieved high accuracy for DBH estimations, showing Root Mean Squared Error (RMSE) of 1.46 cm (rRMSE 3.7%) and 1.38 cm (rRMSE 3.5%), respectively. In contrast, tree height obtained from HMLS was lower than expected, showing an RMSE of 2.85 m (12.74%) along with a bias of −2.34 m. ALS data enhanced the precision of tree height estimations, achieving a RMSE of 1.81 m and a bias of −1.24 m. However, integrating ALS and HMLS data resulted in the most precise tree height estimations resulted in a reduced RMSE to 1.43 m and biases to −0.3 m. Integrated ALS and HMLS and its advantages are a beneficial solution for accurate forest inventory, which in turn supports forest management and planning. Full article

Trees play a critical role in climate regulation, biodiversity, and carbon storage as they cover approximately 30% of the global land area. Nowadays, Machine Learning (ML)is key to automating large-scale tree species classification based on active and passive sensing systems, with a recent trend favoring data fusion approaches for higher accuracy. The use of 3D Deep Learning (DL) models has improved tree species classification by capturing structural and geometric data directly from point clouds. We propose a fully Multimodal Tree Species Classification Network (MMTSCNet) that processes Light Detection and Ranging (LiDAR) point clouds, Full-Waveform (FWF) data, derived features, and bidirectional, color-coded depth images in their native data formats without any modality transformation. We conduct several experiments as well as an ablation study to assess the impact of data fusion. Classification performance on the combination of Airborne Laser Scanning (ALS) data with FWF data scored the highest, achieving an Overall Accuracy (OA) of nearly 97%, a Mean Average F1-score (MAF) of nearly 97%, and a Kappa Coefficient of 0.96. Results for the other data subsets show that the ALS data in combination with or even without FWF data produced the best results, which was closely followed by the UAV-borne Laser Scanning (ULS) data. Additionally, it is evident that the inclusion of FWF data provided significant benefits to the classification performance, resulting in an increase in the MAF of +4.66% for the ALS data, +4.69% for the ULS data under leaf-on conditions, and +2.59% for the ULS data under leaf-off conditions. The proposed model is also compared to a state-of-the-art unimodal 3D-DL model (PointNet++) as well as a feature-based unimodal DL architecture (DSTCN). The MMTSCNet architecture outperformed the other models by several percentage points, depending on the characteristics of the input data. Full article

Remote sensing technologies like airborne laser scanning (ALS) and digital aerial photogrammetry (DAP) have emerged as efficient tools for detecting and analysing canopy gaps (CGs). Comparing these technologies is essential to determine their functionality and applicability in various environments. Thus, this study aimed to assess CG dynamics in the temperate European Białowieża Forest between 2015 and 2022 by comparing ALS data and image-derived point clouds (IPC) from DAP, to evaluate their respective capabilities in describing and analysing forest CG dynamics. Our results demonstrated that ALS-based point clouds provided more detailed and precise spatial information about both the vertical and horizontal structure of forest CGs compared to IPC. ALS detected 27,754 (54%) new CGs between 2015 and 2022, while IPC identified 23,502 (75%) new CGs. Both the average gap area and the total gap area significantly increased over time in both methods. ALS data not only identified a greater number of CGs, particularly smaller ones (below 500 m²), but also produced a more precise representation of CG shape and structure. In conclusion, precise, multi-temporal remote sensing data on the distribution and size of canopy gaps enable effective monitoring of structural changes and disturbances in forest stands, which in turn supports more efficient forest management, e.g., planning of forest regeneration. Full article