Light Detection And Ranging Datasets Research Articles

Development of a Method for Soil Tilth Quality Evaluation from Crumbling Roller Baskets Using Deep Machine Learning Models

A combination tillage with disks, rippers, and roller baskets allows the loosening of compacted soils and the crumbling of soil clods. Statistical methods for evaluating the soil tilth quality of combination tillage are limited. Light Detection and Ranging (LiDAR) data and machine learning models (Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN)) are proposed to investigate roller basket pressure settings on soil tilth quality. Soil profiles were measured using LiDAR (stop and go and on-the-go) and RGB visual images from a Completely Randomized Design (CRD) tillage experiment on clay loam soil with treatments of roller basket down, roller basket up, and no-till in three replicates. Utilizing RF, SVM, and NN methods on the LiDAR data set identified median, mean, maximum, and standard deviation as the top features of importance variables that were statistically affected by the roller settings. Applying multivariate discriminatory analysis on the five statistical measures, three soil tilth classes were predicted with mean prediction rates of 77% (Roller-basket down), 64% (Roller-basket up), and 90% (No till). The LiDAR data analytics-inspired soil tilth classes correlated well with the RGB image discriminatory analysis. Soil tilth machine learning models were shown to be successful in classifying soil tilth with regard to onboard operator pressure control settings on the roller basket of the combination tillage implement.

HeLiPR: Heterogeneous LiDAR dataset for inter-LiDAR place recognition under spatiotemporal variations

Place recognition is crucial for robot localization and loop closure in simultaneous localization and mapping (SLAM). Light Detection and Ranging (LiDAR), known for its robust sensing capabilities and measurement consistency even in varying illumination conditions, has become pivotal in various fields, surpassing traditional imaging sensors in certain applications. Among various types of LiDAR, spinning LiDARs are widely used, while non-repetitive scanning patterns have recently been utilized in robotics applications. Some LiDARs provide additional measurements such as reflectivity, Near Infrared (NIR), and velocity from Frequency modulated continuous wave (FMCW) LiDARs. Despite these advances, there is a lack of comprehensive datasets reflecting the broad spectrum of LiDAR configurations for place recognition. To tackle this issue, our paper proposes the HeLiPR dataset, curated especially for place recognition with heterogeneous LiDARs, embodying spatiotemporal variations. To the best of our knowledge, the HeLiPR dataset is the first heterogeneous LiDAR dataset supporting inter-LiDAR place recognition with both non-repetitive and spinning LiDARs, accommodating different field of view (FOV)s and varying numbers of rays. The dataset covers diverse environments, from urban cityscapes to high-dynamic freeways, over a month, enhancing adaptability and robustness across scenarios. Notably, HeLiPR dataset includes trajectories parallel to MulRan sequences, making it valuable for research in heterogeneous LiDAR place recognition and long-term studies. The dataset is accessible at https://sites.google.com/view/heliprdataset .

Quantitative assessment of earthquake-induced building damage at regional scale using LiDAR data

Regional-scale assessment of the damage caused by earthquakes to structures is crucial for post-disaster management. While remote sensing techniques can be of great help for a quick post-event structural assessment of large areas, currently available methods are limited to the detection of severely-damaged buildings. Furthermore, remote sensing-based assessment methods typically provide only qualitative results, as they lack integration with information on the building’s behaviour in response to seismic-induced ground shaking. In this study, we developed a new methodology that uses airborne Light Detection And Ranging (LiDAR) data in combination with structural indicators of building response to provide a quantitative assessment of earthquake-induced damage at a regional scale. LiDAR datasets collected before and after an earthquake are used to measure residual displacements of building roofs. The resulting lateral drift estimations are used to quantify the level of damage for a specific building typology. Application to the LiDAR datasets collected before and after the 2014 earthquake in Napa Valley, California, demonstrates the capability of the proposed method to detect moderate levels of structural damage, proving its potential for faster and more accurate support to post-disaster management.

Characterization modeling of wake vortex circulation decay under reasonable worst case conditions with cuckoo search algorithm

Wake vortex (WV) produced by a large aircraft has the potential to cause serious damage to smaller aircraft following it. In this context, characterization of WV circulation decay under the reasonable worst case (RWC) conditions allows the separation minima to be found safely. In this study, modeling of dimensionless decay curves, which were developed using three experimental LIDAR (Light Detection and Ranging) datasets in the RECAT-EU project and is a useful tool to characterize the wake vortex circulation decay under RWC conditions, was carried out using cuckoo search algorithm (CSA). The decay curves used in the modeling are the median (P50), 10th (P10), and 90th (P90) percentile decay curves of the RWC tracks, which constitute the top 2% longest lasting wakes. The fact that the correlation coefficient (R) values are very close to 1 for all datasets as a result of the error analysis shows that the prediction success of the CSA model is quite high.

Genetic Programming Guided Mapping of Forest Canopy Height by Combining LiDAR Satellites with Sentinel-1/2, Terrain, and Climate Data

Accurately mapping the forest canopy height is vital for conserving forest ecosystems. Employing the forest height measured by satellite light detection and ranging (LiDAR) systems as ground samples to establish forest canopy height extrapolation (FCHE) models presents promising opportunities for mapping large-scale wall-to-wall forest canopy height. However, despite the potential to provide more samples and alleviate the stripe effect by synergistically using the data from two existing LiDAR datasets, Global Ecosystem Dynamics Investigation (GEDI) and Ice, Cloud, and land Elevation Satellite-2 (ICESat-2), the fundamental differences in their operating principles create measurement biases, and thus, there are few studies combining them for research. Furthermore, previous studies have typically employed existing regression algorithms as FCHE models to predict forest canopy height, without customizing a model that achieves optimal performance based on the current samples. These shortcomings constrain the accuracy of predicting forest canopy height using satellite LiDAR data. To surmount these difficulties, we proposed a genetic programming (GP) guided method for mapping forest canopy height by combining the GEDI and ICESat-2 LiDAR data with Sentinel-1/2, terrain, and climate data. In this method, GP autonomously constructs the fusion model of the GEDI and ICESat-2 datasets (hereafter GIF model) and the optimal FCHE model based on the explanatory variables for the specific study area. The outcomes demonstrate that the fusion of the GEDI and ICESat-2 data shows high consistency (R2 = 0.85, RMSE = 2.2m, pRMSE = 11.24%). The synergistic use of the GEDI and ICESat-2 data, coupled with the optimization of the FCHE model, substantially improves the precision of forest canopy height predictions, and finally achieves R2, RMSE, and pRMSE of 0.64, 3.38m, and 16.08%, respectively. In summary, our research presents a reliable approach to accurately estimate forest canopy height using remote sensing data by addressing measurement biases between the GEDI and ICESat-2 data and overcoming the limitations of traditional FCHE models.

Failure process and three-dimensional motions of mining-induced Jianshanying landslide in China observed by optical, LiDAR and SAR datasets

ABSTRACT The occurrence of collapses and landslides due to underground mining has its unique failure mechanism, especially in the Karst mountainous regions of China. Spaceborne and airborne remote sensing observations provide rapid and effective tools for assessing surface changes and monitoring surface deformation of such landslides. In this study, we take the Jianshanying landslide, a typical mining-induced and fast-deformed landslide, as an example, and reveal the failure mechanism of such landslide by investigating the historical surface displacement. First, the complete evolution of the landslide surface was investigated from its original state to the overall sliding. The data include the satellite and Unmanned Aerial Vehicle (UAV) optical images, UAV three-dimensional (3-D) real scene models, high-resolution Light Detection and Ranging (LiDAR) DEM, and field survey. The results show that the head region entered the high deformation stage after 2019, the maximum deformation rate was 12.3 m/yr. The landslide morphology was formed after the overall slide occurred in September 2020. Then, the pre-event 3-D surface deformation after the landslide entered the high deformation stage was recovered using Interferometric Synthetic Aperture Radar (InSAR), differential DEM, and SAR/optical offset-tracking techniques. The vertical deformation was recovered around −30 m from 2019 to 2020. In particular, we solved the problem of unequal accuracy of SAR and optical offset-tracking observations in 3-D deformation inversion by employing the Helmert variance component estimation method. The maximum deformation was 6 m and 3 m within 4 months in the NS and EW directions, respectively. Finally, we revealed the failure mechanism of the Jianshanying landslide based on the disparity of horizontal and vertical deformation. That is, underground mining causes a significant subsidence of the rear part of the landslide body, resulting in different stress changes in the rear and front parts of the landslide body, which eventually led to sliding of the front part of the slope along the free surface. This work investigates and monitors the typical underground mining-induced Jianshanying landslide by using multi-sensor remote sensing approaches to trace the pre-event surface motions and to reveal its failure mechanism.

RS-Aug: Improve 3D Object Detection on LiDAR With Realistic Simulator Based Data Augmentation

Light detection and ranging (LiDAR) is an essential sensor for three dimensional (3D) object detection via generating 3D point cloud of the surroundings, and it has been widely used in the various visual applications, especially autonomous driving. However, limited numbers of labeled LiDAR datasets brutally restrain the development of 3D object detector, and this situation breeds an urgent demand on data augmentation in this field. By far, most of the traditional methods reuse the labeled samples, while those unlabeled are hastily untaken. Motivated by this, we propose a Realistic Simulator based data augmentation (RS-Aug). It aims to construct augmented real scenes to enrich the diversity of training dataset. To train 3D object detector in a supervised learning way, the first step of RS-Aug is auto-annotation. Time-continuous LiDAR frames are used to construct the dense scene, which is beneficial to annotation and the subsequent rendering augmentation. However, 3D points with incorrect semantic labels are naturally gathered during multi-view reconstruction, causing the negative effect on auto-annotation. We propose an algorithm of cluster guided <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$</tex-math> </inline-formula> -nearest neighbor (c- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$</tex-math> </inline-formula> NN). It emphasizes on de-nosing semantic labels of clustered points using distance and intensity constraints. Then, the next step of RS-Aug is rendering augmentation on the real scene. To enhance the rendering quality using collision and distance constraints with the less computation complexity, we propose a scheme of heuristic search (HS) based object insertion. It estimates the proper position of the inserted object from 2D bird’s eye view (BEV). Experiments demonstrate the de-noising accuracy of c- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$</tex-math> </inline-formula> NN, rendering quality of HS based object insertion, and improvement of RS-Aug on object detection.

Assessment of the solar energy potential of rooftops using LiDAR datasets and GIS based approach

The importance of solar energy as a global energy source is expected to grow. Solar power's future looks bright, especially with an aged and deteriorating energy grid and rising fossil fuel prices. More precise methods for assessment of solar capacity are needed as more homes and companies investigate the possibility of small-scale photovoltaic (PV) solar installations. In this study, a spatial solar energy PV potential assessment method based on the combination of LiDAR (Light Detection and Ranging) datasets and GIS (Geographic Information System) is proposed. The proposed methodology is applied to an area in the capital city of Skopje in N. Macedonia, from where the results of the possible annual energy output of PV systems for the selected rooftops were presented. The results of the study were presented in a map showing rooftops that are most suitable for installing PV systems. From this map, three random roofs were selected to perform manual estimates of the number of panels that could fit on them and the potential energy output of the solar PV systems. This study provides crucial results for financial and urban planning, policy formulation for future energy projects and also allows to analyze different mechanisms to promote PV installations on publicly available rooftops.

Detecting Recent Dynamics in Large-Scale Landslides via the Digital Image Correlation of Airborne Optic and LiDAR Datasets: Test Sites in South Tyrol (Italy)

Large-scale slow-moving deep-seated landslides are complex and potentially highly damaging phenomena. The detection of their dynamics in terms of displacement rate distribution is therefore a key point to achieve a better understanding of their behavior and support risk management. Due to their large dimensions, ranging from 1.5 to almost 4 km2, in situ monitoring is generally integrated using satellite and airborne remote sensing techniques. In the framework of the EFRE-FESR SoLoMon project, three test-sites located in the Autonomous Province of Bolzano (Italy) were selected for testing the possibility of retrieving significant slope displacement data from the analysis of multi-temporal airborne optic and light detection and ranging (LiDAR) surveys with digital image correlation (DIC) algorithms such as normalized cross-correlation (NCC) and phase correlation (PC). The test-sites were selected for a number of reasons: they are relevant in terms of hazard and risk; they are representative of different type of slope movements (earth-slides, deep seated gravitational slope Deformation and rockslides), and different rates of displacement (from few cm/years to some m/years); and they have been mapped and monitored with ground-based systems for many years (DIC results can be validated both qualitatively and quantitatively). Specifically, NCC and PC algorithms were applied to high-resolution (5 to 25 cm/px) airborne optic and LiDAR-derived datasets (such as hillshade and slope maps computed from digital terrain models) acquired during the 2019–2021 period. Qualitative and quantitative validation was performed based on periodic GNSS surveys as well as on manual homologous point tracking. The displacement maps highlight that both DIC algorithms succeed in identifying and quantifying slope movements of multi-pixel magnitude in non-densely vegetated areas, while they struggle to quantify displacement patterns in areas characterized by movements of sub-pixel magnitude, especially if densely vegetated. Nonetheless, in all three landslides, they proved to be able to differentiate stable and active parts at the slope scale, thus representing a useful integration of punctual ground-based monitoring systems.

Multimodal Attention-Aware Convolutional Neural Networks for Classification of Hyperspectral and LiDAR Data

The attention mechanism is one of the most influential ideas in the deep learning community, which has shown excellent efficiency in various computer vision tasks. Thus, this article proposes the convolution neural network method with the attention mechanism to enhance the feature extraction of light detection and ranging (LiDAR) data. Meanwhile, our elaborately designed cascaded block contains a short path architecture beneficial for multistage information exchange. With the full exploitation of elevation information from LiDAR data and efficient utilization of the spatial-spectral information underlying hyperspectral data, our method provides a novel solution for multimodal feature fusion. Experiments are conducted on the LiDAR and hyperspectral dataset provided by the 2013 IEEE GRSS Data Fusion Contest and multisource Trento dataset to demonstrate the effectiveness of the proposed method. The experimental results have shown the superior results of the proposed method on both LiDAR and multimodality remote sensing data in comparison with several popular baselines.

Monitoring Critical Infrastructure Using 3D LiDAR Point Clouds

Monitoring critical infrastructure is of great importance for resilience against current and emerging hazards. In Canada, at the national level, critical infrastructure is strategically classified into the following 10 sectors: energy and utilities, finance, food, transportation, government, information and communication technology, health, water, safety, and manufacturing. Many of these critical infrastructures may be effectively monitored using emerging technologies such as light detection and ranging (LiDAR). LiDAR technology enables active remote sensing from airborne and terrestrial systems. Accordingly, LiDAR can be used in a wide range of applications related to the monitoring of critical infrastructure to promote resilience. This survey provides a comprehensive, and structured literature overview of LiDAR technology currently available for commercial and research use, and also provides a detailed review of the relevant applications of LiDAR for critical infrastructure monitoring. Several LiDAR-based applications in areas of critical infrastructure such as terrestrial and air transportation, gas, oil, and water pipelines, energy generation and distribution, and security are discussed. A summary of the LiDAR data sets that are currently available for use is also presented.

Coupled adversarial learning for fusion classification of hyperspectral and LiDAR data

Hyperspectral image (HSI) provides rich spectral–spatial information and the light detection and ranging (LiDAR) data reflect the elevation information, which can be jointly exploited for better land-cover classification. However, due to different imaging mechanisms, HSI and LiDAR data always present significant image difference, current pixel-wise feature fusion classification methods relying on concatenation or weighted fusion are not effective. To achieve accurate classification result, it is important to extract and fuse similar high-order semantic information and complementary discriminative information contained in multimodal data. In this paper, we propose a novel coupled adversarial learning based classification (CALC) method for fusion classification of HSI and LiDAR data. In specific, a coupled adversarial feature learning (CAFL) sub-network is first trained, to effectively learn the high-order semantic features from HSI and LiDAR data in an unsupervised manner. On one hand, the proposed CAFL sub-network establishes an adversarial game between dual generators and discriminators, so that the learnt features can preserve detail information in HSI and LiDAR data, respectively. On the other hand, by designing weight-sharing and linear fusion structure in the dual generators, we can simultaneously extract similar high-order semantic information and modal-specific complementary information. Meanwhile, a supervised multi-level feature fusion classification (MFFC) sub-network is trained, to further improve the classification performance via adaptive probability fusion strategy. In brief, the low-level, mid-level and high-level features learnt by the CAFL sub-network lead to multiple class estimation probabilities, which are then adaptively combined to generate a final accurate classification result. Both the CAFL and MFFC sub-networks are collaboratively trained by optimizing a designed joint loss function, which consists of unsupervised adversarial loss and supervised classification loss. Overall, by optimizing the joint loss function, the proposed CALC network is pushed to learn highly discriminative fusion features from multimodal data, leading to higher classification accuracies. Extensive experiments on three well-known HSI and LiDAR data sets demonstrate the superior classification performance by the proposed CALC method than several state-of-the-art methods. The source code of the proposed method will be made publicly available at https://github.com/Ding-Kexin/CALC.

Object Detection Based on Roadside LiDAR for Cooperative Driving Automation: A Review

Light Detection and Ranging (LiDAR) technology has the advantages of high detection accuracy, a wide range of perception, and not being affected by light. The 3D LiDAR is placed at the commanding height of the traffic scene, the overall situation can be grasped from the perspective of top view, and the trajectory of each object in the traffic scene can be accurately perceived in real time, and then the object information can be distributed to the surrounding vehicles or other roadside LiDAR through advanced wireless communication equipment, which can significantly improve the local perception ability of an autonomous vehicle. This paper first describes the characteristics of roadside LiDAR and the challenges of object detection and then reviews in detail the current methods of object detection based on a single roadside LiDAR and multi-LiDAR cooperatives. Then, some studies for roadside LiDAR perception in adverse weather and datasets released in recent years are introduced. Finally, some current open challenges and future works for roadside LiDAR perception are discussed. To the best of our knowledge, this is the first work to systematically study roadside LiDAR perception methods and datasets. It has an important guiding role in further promoting the research of roadside LiDAR perception for practical applications.

Leveraging Deep Convolutional Neural Networks Pre-Trained on Autonomous Driving Data for Vehicle Detection From Roadside LiDAR Data

Recent technological advancements in computer vision algorithms and data acquisition devices have greatly facilitated the research and applications of deep learning-based traffic object recognition from Light Detection and Ranging (LiDAR) data. The majority of existing methodologies applied deep learning (DL)-based techniques, especially Convolutional Neural Networks (CNNs), for vehicle detection and tracking on autonomous driving datasets. Nevertheless, fewer studies were focused on DL-based vehicle detection using roadside LiDAR data, partially due to the lack of publicly available roadside LiDAR datasets for network training and testing. This paper develops a novel framework based on CNNs and LiDAR data for automated vehicle detection. It leverages the domain knowledge of CNNs trained on large-scale autonomous driving datasets for vehicle detection from roadside LiDAR data. In the experimental study, roadside LiDAR data were collected at a road intersection in Reno, Nevada, U.S. Meanwhile, a CNN architecture was proposed to detect vehicles from LiDAR data through 3D bounding boxes. The proposed CNN was modified from the established PointPillars network by adding dense connections to the convolutional layers to achieve more comprehensive feature extraction. Three CNNs, including the proposed CNN, PointPillars, and YOLOv4, were trained and tested on PandaSet, a publicly available large-scale autonomous driving LiDAR dataset. Subsequently, the trained CNNs were reused for vehicle detection from the captured roadside LiDAR data. The experimental results demonstrated that the proposed CNN outperformed the others in the testing metrics. All three networks showed good performance on vehicle detection from the captured roadside LiDAR data.

Efficient co-registration of UAV and ground LiDAR forest point clouds based on canopy shapes

• Time-efficient co-registration of UAV and ground LiDAR data is proposed for plantation forests. • Coarse alignment of forest point clouds is divided into ground alignment and canopy image matching. • Canopy images are matched by two pairs of canopy corner points and the canopy overlap rate. • The runtime of coarse alignment is less than 1 s for millions of forest points. Registration of unmanned aerial vehicle laser scanning (ULS) and ground light detection and ranging (LiDAR) point clouds in forests is critical to create a detailed representation of a forest structure and an accurate retrieval of forest parameters. However, tree occlusion poses challenges for those registration methods used artificial markers, and some automated registration methods have low time-efficiency due to the process of object (e.g., tree, crown) segmentation. In this study, we propose an automated and time-efficient method to register ULS and ground LiDAR (including terrestrial and backpack laser scanning) forest point clouds. Registration involves coarse alignment and fine registration, where the coarse alignment is divided into vertical and horizontal alignment. The vertical alignment is implemented by rotating grounds to the horizontal plane, and the horizontal alignment is achieved by canopy image matching. During image matching, vegetation points are projected onto the horizontal plane to obtain two binary images, and then, canopy shape feature, which is described by a two-point congruent set and canopy overlap, is used to match the binary images. Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration in six plantation forest plots with sizes of 0.03 ha to 0.25 ha. Experimental results show that the ULS and ground LiDAR data in different plots are registered, of which the coarse alignment errors are less than 0.20 m in the horizontal direction, the final registration accuracy is less than 0.15 m, and the average runtime is less than 1 s. Our study demonstrates the effectiveness of the proposed strategy and has able to perform accurate and quick registration of ULS and ground LiDAR data from plantation forests with different attributes.

Laserfarm – A high-throughput workflow for generating geospatial data products of ecosystem structure from airborne laser scanning point clouds

Quantifying ecosystem structure is of key importance for ecology, conservation, restoration, and biodiversity monitoring because the diversity, geographic distribution and abundance of animals, plants and other organisms is tightly linked to the physical structure of vegetation and associated microclimates. Light Detection And Ranging (LiDAR) — an active remote sensing technique — can provide detailed and high resolution information on ecosystem structure because the laser pulse emitted from the sensor and its subsequent return signal from the vegetation (leaves, branches, stems) delivers three-dimensional point clouds from which metrics of vegetation structure (e.g. ecosystem height, cover, and structural complexity) can be derived. However, processing 3D LiDAR point clouds into geospatial data products of ecosystem structure remains challenging across broad spatial extents due to the large volume of national or regional point cloud datasets (typically multiple terabytes consisting of hundreds of billions of points). Here, we present a high-throughput workflow called ‘Laserfarm’ enabling the efficient, scalable and distributed processing of multi-terabyte LiDAR point clouds from national and regional airborne laser scanning (ALS) surveys into geospatial data products of ecosystem structure. Laserfarm is a free and open-source, end-to-end workflow which contains modular pipelines for the re-tiling, normalization, feature extraction and rasterization of point cloud information from ALS and other LiDAR surveys. The workflow is designed with horizontal scalability and can be deployed with distributed computing on different infrastructures, e.g. a cluster of virtual machines. We demonstrate the Laserfarm workflow by processing a country-wide multi-terabyte ALS dataset of the Netherlands (covering ∼34,000 km2 with ∼700 billion points and ∼ 16 TB uncompressed LiDAR point clouds) into 25 raster layers at 10 m resolution capturing ecosystem height, cover and structural complexity at a national extent. The Laserfarm workflow, implemented in Python and available as Jupyter Notebooks, is applicable to other LiDAR datasets and enables users to execute automated pipelines for generating consistent and reproducible geospatial data products of ecosystems structure from massive amounts of LiDAR point clouds on distributed computing infrastructures, including cloud computing environments. We provide information on workflow performance (including total CPU times, total wall-time estimates and average CPU times for single files and LiDAR metrics) and discuss how the Laserfarm workflow can be scaled to other LiDAR datasets and computing environments, including remote cloud infrastructures. The Laserfarm workflow allows a broad user community to process massive amounts of LiDAR point clouds for mapping vegetation structure, e.g. for applications in ecology, biodiversity monitoring and ecosystem restoration.

Potential and limitations of LiDAR altimetry in archaeological survey. Copper Age and Bronze Age settlements in southern Iberia

Potential and limitations of LiDAR altimetry in archaeological survey. Copper Age and Bronze Age settlements in southern Iberia

Convolutional Autoencoder-Based Deep Learning Approach for Aerosol Emission Detection Using LiDAR Dataset

Quantifying atmospheric aerosols and their linkages to climatic repercussions is necessary to understand the dynamics of climate forcing and enhance our knowledge of climate change. Because of this reactivity to precipitation, temperature, topography, and human activity, the atmospheric boundary layer (ABL) is one of the most dynamic atmospheric regions: ABL aerosols have a big impact on the evolution of climate change’s radiative forcing, human health, food security, and, eventually, the local and global economy. Continuous monitoring and instrumental and computational approaches are required for the detection and analysis of ABL pattern behavior. This paper provides a deep learning-based outer layer aerosol detection system based on Light Detection and Ranging (LiDAR) data fusion. The suggested method applies sequential models to turn low-level data into compressed features using object-based analysis, feature-level fusion, and autoencoder-based dimensionality reduction. Convolutional neural networks (CNNs) were used to convert compressed data into high-level properties that could be used to categorize air particles in the outer layer. This research describes deep learning approaches that allowed for detecting 40% more atmospheric features at a horizontal resolution of 5 km during daytime operations when applied to LiDAR data. Compared to existing deep learning algorithms for edges and complicated near-surface sceneries during the day, a convolutional autoencoder (CAE) trained using LiDAR dataset standard data products showed the potential for improved aerosol discrimination with 98% accuracy.

Point cloud does matter. Selected issues of using airborne LiDAR elevation data in geomorphometric studies of rugged sandstone terrain under forest – Case study from Central Europe

Contemporary airborne Light Detection And Ranging (LiDAR) elevation data provide a high-resolution input to quantitative studies within various branches of geomorphological research. Availability of such data played an especially significant role in the recent developments of geomorphometric studies focused on extremely rugged terrains, such as dissected sandstone plateaus. These are the areas of very complex topography, featuring structurally-controlled landforms such as tabular hills, canyons, cleft-and-valley systems, numerous high and near-vertical rock walls, isolated tors and dense boulder slope covers. In this paper we focus on issues of LiDAR data handling for geomorphometric research in Central European sandstone areas in Czechia, Poland and Germany, where the extremely rugged terrains are usually located in the forest and, thus, usability of LiDAR DEM (Digital Elevation Model) products for morphometric studies can be constrained. The impact of forest density on local decrease of ground point density may be considerable, adversely affecting the quality of DEMs, which become unsuitable to represent properly terrain features. Therefore, the role of DEM pre-processing in geomorphometric workflow is emphasized. Using the original point cloud data one can provide a much more detailed terrain representation that includes numerous convex landforms (tors, boulders) which are erroneously filtered-out from ready-to-use DEMs. Results of such procedure are shown explicitly in the form of Elevation Difference maps, as well as on examples of selected morphometric indices such as Topographic Wetness Index, Terrain Ruggedness Index and Morphometric Protection Index. The awareness of qualities of particular LiDAR datasets should be considered crucial while assessing LiDAR data applicability for morphometric studies on rugged erosional landscapes, especially if the study areas are transboundary.

A method for data density reduction in overlapped airborne LiDAR strips

A partial overlap between adjacent strips during airborne Light Detection And Ranging (LiDAR) data scanning is required to ensure data integrity. The overlap area is observed two times and contains richer target details. To reduce data density yet retaining target details in the overlap area, a method based on reducing the influence of repeated observation data is presented. The proposed method defines the repeated observation data as the multiple samples of the same location from two adjacent strips, identifies them by locating the pairwise closest points from two adjacent strips with their distance below a distance threshold, and eliminates unimportant points inside the repeated observation data according to the criterion that LiDAR points with low curvature or high incidence angle can be removed without affecting the sharp features and the overall quality of data representation of the overlap area. The optimal distance threshold is adaptively determined using a Gaussian fitting model by modeling the mean distance between all the nearest neighbors in one original LiDAR strips. Finally, reduction rate and information entropy metric are put forward to quantitatively evaluate the effectiveness of the proposed method. The developed method is applied to two real airborne LiDAR datasets with urban and forestry scenes for experimental testing. The quantitative accuracy evaluation results show that reduction rate in urban and forestry area can reach to 25.1% and 12.8%, respectively. Furthermore, the data density of the overlap area could be reduced while the information entropy and DTM accuracy still can be maintained.