Airborne Laser Scanning Research Articles

Evaluating the Influence of Row Orientation and Crown Morphology on Growth of Pinus taeda L. with Drone-Based Airborne Laser Scanning.

The tree crown's directionality of growth may be an indicator of how aggressive the tree is in terms of foraging for light. Airborne drone laser scanning (DLS) has been used to accurately classify individual tree crowns (ITCs) and derive size metrics related to the crown. We compare ITCs among 6 genotypes exhibiting different crown architectures in managed loblolly pine (Pinus taeda L.) in the United States. DLS data are classified into ITC objects, and we present novel methods to calculate ITC shape metrics. Tree stems are located using (a) model-based clustering and (b) weighting cluster-based size. We generated ITC shape metrics using 3-dimensional (3D) alphashapes in 2 DLS acquisitions of the same location, 4 years apart. Crown horizontal distance from the stem was estimated at multiple heights, in addition to calculating 3D volume in specific azimuths. Crown morphologies varied significantly (P < 0.05) spatially, temporally, and among the 6 genotypes. Most genotypes exhibited larger crown volumes facing south (150° to 173°). We found that crown asymmetries were consistent with (a) the direction of solar radiation, (b) the spatial arrangement and proximity of the neighboring crowns, and (c) genotype. Larger crowns were consistent with larger increases in stem volume, but that increases in the southern portions of crown volume were consistent with larger stem volume increases, than in the north. This finding suggests that row orientation could influence stem growth rates in plantations, particularly impacting earlier development. These differences can potentially reduce over time, especially if stands are not thinned in a timely manner once canopy growing space has diminished.

Comparison of Semi-Physical and Empirical Models in the Estimation of Boreal Forest Leaf Area Index and Clumping With Airborne Laser Scanning Data

Comparison of Semi-Physical and Empirical Models in the Estimation of Boreal Forest Leaf Area Index and Clumping With Airborne Laser Scanning Data

Usefulness of national airborne laser scanning and aerial survey data in forest canopy gap detection

The forest floor is covered with tree canopy, and the forest canopy gap is a larger or smaller area of the floor that is not covered by the canopy of the dominant tree layer. The size of the gap affects tree species rejuvenation, as well as the vertical and horizontal structure of the forest. In the Pohorje area (Pahernik’s forest estate), which is characterized by forests where trees of different diameters and ages occur in small areas, we analyzed the possibilities of automatic gap detection based on data from the Laser Scanning of Slovenia (LSS) and the Cyclic Aerial Survey of Slovenia (CAS). We used Canopy Height Models (CHM) derived from both data sources. The overall detection accuracy even for the smallest gaps (smaller than 50 m2) was 94.4% based on the LSS data and 83.1% based on the CAS data. A larger number and area of gaps can be detected based on the LSS data, and the gaps derived from the LSS data are more disaggregated and elongated. The detection of gaps with CAS data and LSS data is more comparable with a minimum gap area of 100 m²; the accuracy of detecting such gaps is 85.4 and 94.4 % respectively. The results of the study show that in the absence of LSS data, the use of CAS data to detect forest canopy gaps on a large scale is useful when gaps with an area of more than 100 m² are detected.

Estimating tree species composition from airborne laser scanning data using point-based deep learning models

Airborne laser scanning (ALS) data is increasingly being used for accurate estimations of forest inventory attributes, such as tree height and volume. However, determining tree species information, an important attribute required by inventories for a range of forest management applications, is challenging to extract from ALS data. This is due to complex species assemblages and vertical structures in certain forest environments, and a lack of spectral information for most ALS sensors. Our objective was to estimate tree species compositions in a Canadian boreal forest environment using ALS data and point-based deep learning techniques. To accomplish this, we utilised existing polygonal forest resource information to develop a large comprehensive dataset of tree species compositions across a 630,000 ha forest management area. We then used an adapted PointAugment generative adversarial network (GAN) coupled with the dynamic graph convolutional neural network to estimate tree species proportions. This innovative deep learning approach resulted in an overall R2adj of 0.61 for all tree species proportions. A weighted F1 score of 63% was observed when classifying the leading species of a plot, 66% for leading genus, and 85% when distinguishing between coniferous and deciduous dominated plots. Furthermore, the PointAugment GAN successfully generated augmented point clouds of forest plots which can alleviate issues associated with limited training samples for use in deep learning. This approach demonstrates the capability of point-based deep learning techniques to accurately estimate tree species compositions from ALS point clouds within an expansive forested region, characterized by a complex management history and a diversity of tree species. The source code along with the pretrained models are available at https://github.com/Brent-Murray/point-dl/tree/main/Pytorch/models/PointAugment.

Dwór krzyżacki w Benowie (Polska), jego geneza, historia i znaczenie w świetle analizy historyczno-architektonicznej

This paper deals with the history of the former Teutonic manor in Benowo (German name: Bönhof) in relation to its spatial arrangement. The first part presents the source historical messages relating to this place and an attempt is made to read them again based on the relevant available research by historians and archaeologists regarding the beginnings of the activity of the Teutonic Order in the Prussian land. The available archival cartography concerning the location of the manor house is also described. The following section presents new findings related to the use of modern land registration techniques – aerial and satellite photos and LIDAR airborne laser scanning. The result of the research is the indication of the character and shape of the buildings and the exact location of some of the objects included in the farm buildings, as well as the formulation of a hypothesis regarding the land forms existing in their immediate vicinity.

Assessing the potential of remote sensing-based models to predict old-growth forests on large spatiotemporal scales

Old-growth forests provide a broad range of ecosystem services. However, due to poor knowledge of their spatiotemporal distribution, implementing conservation and restoration strategies is challenging. The goal of this study is to compare the predictive ability of socioecological factors and different sources of remotely sensed data that determine the spatiotemporal scales at which forest maturity attributes can be predicted.We evaluated various remotely sensed data that cover a broad range of spatial (from local to global) and temporal (from current to decades) extents, from Airborne Laser Scanning (ALS), aerial multispectral and stereo-imagery, Sentinel-1, Sentinel-2 and Landsat data. Using random forests, remotely sensed data were related to a forest maturity index available in 688 forest plots across four ranges of the French Alps. Each model also includes socioecological predictors related to topography, socioeconomy, pedology and climatology.We found that the different remotely sensed data provide information on the main forest structural characteristics as defined by ALS, except for Landsat, which has a too coarse resolution, and Sentinel-1, which responds differently to vegetation structure. The predictions were quite similar considering aerial remotely sensed data, on the one hand, and satellite remotely sensed data, on the other hand. Socioecological variables are the most important predictors compared to the remote sensing metrics.In conclusion, our results indicate that a wide range of remotely sensed data can be used to study old-growth forests beyond the use of ALS and despite different abilities to predict forest structure. Accounting for socioecological predictors is indispensable to avoid a significant loss of predictive accuracy. Remotely sensed data can allow for predictions to be made at different spatiotemporal resolutions and extents. This study paves the way to large-scale monitoring of forest maturity, as well as for retrospective analyses which will show to what extent predicted maturity change at different dates.

Characterization of the Fels Landslide (Alaska) Using Combined Terrestrial, Aerial, and Satellite Remote Sensing Data

The characterization of landslides located in remote areas poses significant challenges due to the costs of reaching the sites and the lack of reliable subsurface data to constrain geological interpretations. In this paper, the advantages of combining field and remote sensing techniques to investigate the deformation and stability of rock slopes are demonstrated. The characterization of the Fels landslide, a large, slowly deforming rock slope in central Alaska, is described. Historical aerial imagery is used to highlight the relationship between glacier retreat and developing instability. Airborne laser scanning (ALS) and Structure-from-Motion (SfM) datasets are used to investigate the structural geological setting of the landslide, revealing a good agreement between structural discontinuities at the outcrop and slope scales. The magnitude, plunge, and direction of slope surface displacements and their changes over time are studied using a multi-temporal synthetic aperture radar speckle-tracking (SAR ST) dataset. The analyses show an increase in displacement rates (i.e., an acceleration of the movement) between 2010 and 2020. Significant spatial variations of displacement direction and plunge are noted and correlated with the morphology of the failure surface reconstructed using the vector inclination method (VIM). In particular, steeper displacement vectors were reconstructed in the upper slope, compared to the central part, thus suggesting a change in basal surface morphology, which is largely controlled by rock mass foliation. Through this analytical approach, the Fels landslide is shown to be a slow-moving, compound rockslide, the displacement of which is controlled by structural geological features and promoted by glacier retreat.

Enhancing LiDAR-UAS Derived Digital Terrain Models with Hierarchic Robust and Volume-Based Filtering Approaches for Precision Topographic Mapping

Airborne Laser Scanning (ALS) point cloud classification in ground and non-ground points can be accurately performed using various algorithms, which rely on a range of information, including signal analysis, intensity, amplitude, echo width, and return number, often focusing on the last return. With its high point density and the vast majority of points (approximately 99%) measured with the first return, filtering LiDAR-UAS data proves to be a more challenging task when compared to ALS point clouds. Various algorithms have been proposed in the scientific literature to differentiate ground points from non-ground points. Each of these algorithms has advantages and disadvantages, depending on the specific terrain characteristics. The aim of this research is to obtain an enhanced Digital Terrain Model (DTM) based on LiDAR-UAS data and to qualitatively and quantitatively compare three filtering approaches, i.e., hierarchical robust, volume-based, and cloth simulation, on a complex terrain study area. For this purpose, two flights over a residential area of about 7.2 ha were taken at 60 m and 100 m, with a DJI Matrice 300 RTK UAS, equipped with a Geosun GS-130X LiDAR sensor. The vertical and horizontal accuracy of the LiDAR-UAS point cloud, obtained via PPK trajectory processing, was tested using Check Points (ChPs) and manually extracted features. A combined approach for ground point classification is proposed, using the results from a hierarchic robust filter and applying an 80% slope condition for the volume-based filtering result. The proposed method has the advantage of representing with accuracy man-made structures and sudden slope changes, improving the overall accuracy of the DTMs by 40% with respect to the hierarchical robust filtering algorithm in the case of a 60 m flight height and by 28% in the case of a 100 m flight height when validated against 985 ChPs.

No evidence for fractal scaling in canopy surfaces across a diverse range of forest types

Abstract Canopy structural complexity is a key emergent property of forest ecosystems that directly relates to their ability to store carbon, cycle water and nutrients, and provide habitat for biodiversity. However, we lack a general framework for quantifying the structural complexity of forest canopies, and it remains to be seen if there are simple rules that explain the huge variation in canopy structure that we observe across the world's forests. A leading candidate for characterizing differences in structural complexity among forest ecosystems are fractal scaling laws, or measures of statistical self‐similarity. If forest canopies were fractal in nature, their structural attributes could be distilled into a single coefficient—their fractal dimension—which could then be used to directly compare structural differences within and across biomes. To test this idea, we used airborne laser scanning (ALS) data acquired across nine landscapes in Australia that span a huge environmental gradient and include everything from dry shrublands, tropical savannas, dense rainforests, to 90 m tall Mountain Ash forests. Using the ALS data, we built high‐resolution 3D canopy height models of each landscape so that we could quantify how closely they followed fractal scaling laws, based on a comprehensive set of fractal dimension estimators. Across all ecosystem types, fractal scaling assumptions were consistently violated, with clear and systematic differences between real‐world forest canopies and simulated fractal surfaces. However, deviations from fractality did vary predictably among sites, with forests in less arid environments, dominated by tall trees with large crowns, exhibiting a higher degree of self‐similarity across scales. Synthesis: Our study conclusively shows that canopy surfaces are not fractal beyond the scale of individual tree crowns. Nevertheless, we still observed ecologically meaningful and generalisable patterns in forest structure across scales, which closely reflect biophysical and physiological constraints on tree size and architecture. These patterns point the way towards a more general framework for characterizing ecological complexity.

Snow accumulation, albedo and melt patterns following road construction on permafrost, Inuvik–Tuktoyaktuk Highway, Canada

Abstract. Roads constructed on permafrost can have a significant impact on the surrounding environment, potentially inducing permafrost degradation. These impacts arise from factors such as snow accumulation near the road, which affects the soil's thermal and hydrological regime, and road dust that decreases the snow's albedo, altering the timing of snowmelt. However, our current understanding of the magnitude and the spatial extent of these effects is limited. In this study we addressed this gap by using remote sensing techniques to assess the spatial effect of the Inuvik to Tuktoyaktuk Highway (ITH) in Northwest Territories, Canada, on snow accumulation, snow albedo and snowmelt patterns. With a new, high resolution snow depth raster from airborne laser scanning, we quantified the snow accumulation at road segments in the Trail Valley Creek area using digital elevation model differencing. We found increased snow accumulation up to 36 m from the road center. The magnitude of this snow accumulation was influenced by the prevailing wind direction and the embankment height. Furthermore, by analyzing 43 Sentinel-2 satellite images between February and May 2020, we observed reduced snow albedo values within 500 m of the road, resulting in a 12-days-earlier onset of snowmelt within 100 m from the road. We examined snowmelt patterns before, during and after the road construction using the normalized difference snow index from Landsat-7 and Landsat-8 imagery. Our analysis revealed that the road affected the snowmelt pattern up to 600 m from the road, even in areas which appeared undisturbed. In summary, our study improves our understanding of the spatial impact of gravel roads on permafrost due to enhanced snow accumulation, reduced snow albedo and earlier snowmelt. Our study underscores the important contribution that remote sensing can provide to improve our understanding of the effects of infrastructure development on permafrost environments.

Modeling instream temperature from solar insolation under varying timber harvesting intensities using RPAS laser scanning

Stream temperatures are influenced by the amount of solar insolation they receive. Increasing stream temperatures associated with climate warming pose detrimental health risks to freshwater ecosystems. In British Columbia (BC), Canada, timber harvesting along forested streams is managed using riparian buffer zones of varying widths and designations. Within buffer zones, depending on distance from the stream, selective thinning may be permitted or harvest may be forbidden. In this study, we used airborne laser scanning (ALS) point cloud data acquired via a remotely piloted aircraft system (RPAS) to derive forest canopy characteristics that were then used to estimate daily incoming summer and fall solar insolation for five stream reaches in coastal conifer-dominated temperate forests in Vancouver Island, BC, Canada. We then examined empirical relationships between estimated insolation and actual instream temperature measurements. Based on these empirical relationships, the potential effects of timber harvest on instream temperatures were simulated by comparing scenarios of different riparian forest harvest intensities. Our results indicated that modeled solar insolation explained 43–90 % of the variation in observed stream reach temperatures, and furthermore, when a single cold-water stream reach was excluded explained an overall 81 % of variation. Simulated harvesting scenarios generally projected increases in maximum stream reach temperatures 1–2 °C in summer and early fall months. However, in a full clearcut scenario (i.e. where all trees were removed), maximum stream reach temperatures increased as much as 5.8 °C. Our results emphasize the importance of retaining riparian vegetation for the maintenance of habitable temperatures for freshwater-reliant fish with thermal restrictions. In addition, we demonstrate the feasibility of RPAS-based monitoring of stream reach shading and canopy cover, enabling detailed assessment of environmental stressors faced by fish populations under climate warming.

East African megafauna influence on vegetation structure permeates from landscape to tree level scales

African savanna elephants (Loxodonta africana) can substantially modify their habitat through their interactions with woody vegetation. Nonetheless, the scale, intensity and characteristics of these relations are not yet fully understood. Consequently, it is unclear how vegetation-megafauna interactions can be disrupted by external factors, such as land management. This study attempted to quantify and characterize structural changes in vegetation caused by elephants, from landscape to tree level scales. We applied multi-scale geospatial tools, including airborne (ALS) and terrestrial laser scanning (TLS), to address the following questions: (1) How do elephants shape landscape level vegetation structure in conservation areas? (2) Are the impacts of elephants evident on individual tree architecture? Our study area was located at the Taita Hills Wildlife Sanctuary in South-eastern Kenya. The occurrence of elephants was estimated using elephant observation records and proximity to elephant tracks. Landscape level structure was assessed using tree density maps calculated based on individually detected treetops from ALS data. Next, TLS measurements of 72 trees were processed using quantitative structural modelling to characterize their architecture. Our results demonstrate a widespread influence of elephants on both landscape and tree level structural characteristics. This influence was strongly mediated by management, as we observed differences in vegetation structure inside and outside conservation areas. Tree density was up to 42% lower (5.84 trees/ha) in conservation areas than in non-conservation areas (10.17 trees/ha). Trees were relatively larger with closer proximity to elephant tracks, while smaller trees were more often observed in areas further away from elephants. At an architectural level, trees closer to elephant tracks had lower ratio between the crown length and the tree height, demonstrating a substantial influence of elephants on the morphological characteristics of trees. Our results highlight the importance of accounting for vegetation fauna interactions when planning conservation areas in African savannahs.

A New Approach for Ground Filtering of Airborne Laser Scanning Data Using PointNet++

A New Approach for Ground Filtering of Airborne Laser Scanning Data Using PointNet++

Carbon Losses from Topsoil in Abandoned Peat Extraction Sites Due to Ground Subsidence and Erosion

Peat erosion has a significant impact on soil fertility, agricultural productivity, and climate change dynamics. Through this process, the topsoil rich in organic matter and carbon (C) is removed and can travel long distances, causing a net C loss. Additionally, peat undergoes oxidation, resulting in further C loss. In our study, we evaluated C losses from 11 peat extraction fields in two study sites, abandoned for more than 15 years and overgrown by vegetation of different densities. We used high-resolution airborne laser scanning point clouds and multispectral aerial images acquired periodically within a 9-year period, as well as chemical analyses of the topsoil layer. In our study, we found a strong correlation between peat subsidence, C loss, and the vegetation density (NDVI value). NDVI also determines most of the uncertainty in elevation data. We found also that both erosion and peat subsidence are significant sources of C losses from peat extraction sites. At a site monitored for over 9 years, our estimated ground elevation changes ranged from 0.1 cm y−1 to 0.58 cm y−1; however, at a different site monitored over a 4-year period, the values ranged from 2.14 cm y−1 to 5.72 cm y−1. Accordingly, the mean annual C losses varied from 0.06 to 0.22 kg C m−2 y−1 and from 1.21 to 3.57 kg C m−2 y−1.

VxH: A Systematic Determination of Efficient Hierarchical Voxel Structures

Three-dimensional (3D) maps with many millions to billions of points are now used in an increasing number of applications, with processing rates in the hundreds of thousands to millions of points per second. In mobile applications, power and energy consumption for managing such data and extracting useful information thereof are critical concerns. We have developed structures and methodologies with the purpose of minimizing memory usage and associated energy consumption for indexing and serialization of voxelized point-clouds. The primary source of points in our case is airborne laser scanning, but our methodology is not restricted to only this setting. Our emulated results show a memory usage reduction factor of roughly up to 200× that of Octree/Octomap and a file size reduction factor of up to 1.65× compared with the predominating compression scheme for airborne Lidar data, LASzip. In addition, our structures enable significantly more efficient processing since they are included in a hierarchical structure that captures geometric aspects.

Benchmark for Automatic Clear-Cut Morphology Detection Methods Derived from Airborne Lidar Data

Forest harvest detection techniques have recently gained increased attention due to the varied results they provide. Correctly determining the acreage of clear-cut areas is crucial for carbon sequestration. Detecting clear-cut areas using airborne laser scanning (ALS) could be an accurate method for determining the extent of clear-cut areas and their subsequent map display in forest management plans. The shapes of ALS-detected clear-cut areas have uneven edges with protrusions that might not be readable when displayed correctly. Therefore, it is necessary to simplify these shapes for better comprehension. To simplify the shapes of ALS-scanned clear-cut areas, we tested four simplification algorithms using ArcGIS Pro 3.0.0 software: the retain critical points (Douglas–Peucker), retain critical bends (Wang–Müller), retain weighted effective areas (Zhou–Jones), and retain effective areas (Visvalingam–Whyatt) algorithms. Ground-truth data were obtained from clear-cut areas plotted in the forest management plan. Results showed that the Wang–Müller algorithm was the best of the four ALS algorithms at simplifying the shapes of detected clear-cut areas. Using the simplification algorithm reduced the time required to edit polygons to less than 1% of the time required for manual delineation.

Using repeat UAV-based laser scanning and multispectral imagery to explore eco-geomorphic feedbacks along a river corridor

Abstract. Vegetation plays a critical role in the modulation of fluvial process and morphological evolution. However, adequately capturing the spatial and temporal variability and complexity of vegetation characteristics remains a challenge. Currently, most of the research seeking to address these issues takes place at either the individual plant scale or via larger-scale bulk roughness classifications, with the former typically seeking to characterise vegetation–flow interactions and the latter identifying spatial variation in vegetation types. Herein, we devise a method which extracts functional vegetation traits using UAV (uncrewed aerial vehicle) laser scanning and multispectral imagery and upscale these to reach-scale functional group classifications. Simultaneous monitoring of morphological change is undertaken to identify eco-geomorphic links between different functional groups and the geomorphic response of the system. Identification of four groups from quantitative structural modelling and two further groups from image analysis was achieved and upscaled to reach-scale group classifications with an overall accuracy of 80 %. For each functional group, the directions and magnitudes of geomorphic change were assessed over four time periods, comprising two summers and winters. This research reveals that remote sensing offers a possible solution to the challenges in scaling trait-based approaches for eco-geomorphic research and that future work should investigate how these methods may be applied to different functional groups and to larger areas using airborne laser scanning and satellite imagery datasets.

Diameter, height and species of 42 million trees in three European landscapes generated from field data and airborne laser scanning data.

Ecology and forestry sciences are using an increasing amount of data to address a wide variety of technical and research questions at the local, continental and global scales. However, one type of data remains rare: fine-grain descriptions of large landscapes. Yet, this type of data could help address the scaling issues in ecology and could prove useful for testing forest management strategies and accurately predicting the dynamics of ecosystem services. Here we present three datasets describing three large European landscapes in France, Poland and Slovenia down to the tree level. Tree diameter, height and species data were generated combining field data, vegetation maps and airborne laser scanning (ALS) data following an area-based approach. Together, these landscapes cover more than 100 000 ha and consist of more than 42 million trees of 51 different species. Alongside the data, we provide here a simple method to produce high-resolution descriptions of large landscapes using increasingly available data: inventory and ALS data. We carried out an in-depth evaluation of our workflow including, among other analyses, a leave-one-out cross validation. Overall, the landscapes we generated are in good agreement with the landscapes they aim to reproduce. In the most favourable conditions, the root mean square error (RMSE) of stand basal area (BA) and mean quadratic diameter (Dg) predictions were respectively 5.4 m 2.ha -1 and 3.9 cm, and the generated main species corresponded to the observed main species in 76.2% of cases.

Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models

Abstract Airborne laser scanning data are increasingly used to predict forest biomass over large areas. Biomass information cannot be derived directly from airborne laser scanning data; therefore, field measurements of forest plots are required to build regression models. We tested whether simulated laser scanning data of virtual forest plots could be used to train biomass models and thereby reduce the amount of field measurements required. We compared the performance of models that were trained with (i) simulated data only, (ii) a combination of simulated and real data, (iii) real data collected from different study sites, and (iv) real data collected from the same study site the model was applied to. We additionally investigated whether using a subset of the simulated data instead of using all simulated data improved model performance. The best matching subset of the simulated data was sampled by selecting the simulated forest plot with the highest correlation of the return height distribution profile for each real forest plot. For comparison, a randomly selected subset was evaluated. Models were tested on four forest sites located in Poland, the Czech Republic, and Canada. Model performance was assessed by root mean squared error (RMSE), squared Pearson correlation coefficient (r$^{2}$), and mean error (ME) of observed and predicted biomass. We found that models trained solely with simulated data did not achieve the accuracy of models trained with real data (RMSE increase of 52–122 %, r$^{2}$ decrease of 4–18 %). However, model performance improved when only a subset of the simulated data was used (RMSE increase of 21–118 %, r$^{2}$ decrease of 5–14 % compared to the real data model), albeit differences in model performance when using the best matching subset compared to using a randomly selected subset were small. Using simulated data for model training always resulted in a strong underprediction of biomass. Extending sparse real training datasets with simulated data decreased RMSE and increased r$^{2}$, as long as no more than 12–346 real training samples were available, depending on the study site. For three of the four study sites, models trained with real data collected from other sites outperformed models trained with simulated data and RMSE and r$^{2}$ were similar to models trained with data from the respective sites. Our results indicate that simulated data cannot yet replace real data but they can be helpful in some sites to extend training datasets when only a limited amount of real data is available.

Archaeological site segmentation of ancient city walls based on deep learning and LiDAR remote sensing

Ancient city walls, one of the most notable distinguishing features of Chinese ancient cities, are military defenses constructed of rammed earth. The ancient city walls have considerable study value because they served as the city's boundary and a symbol of power. However, as a result of natural erosion and human activities, many sites have been ruined. Existing optical remote sensing technologies, LiDAR point cloud processing algorithms, and deep learning methods are inadequate for the extraction and segmentation of ancient city wall sites. The novel semantic segmentation method for ancient city wall sites is described in this paper that extracts sites at the pixel level from LiDAR remote sensing data based on deep learning. To begin, the point cloud data collected by airborne laser scanning is processed into DEM data, and the distribution of ancient city walls in the study area is obtained through archaeological survey and expert interpretation. The dataset for deep learning semantic segmentation is then generated using image cropping and data augmentation techniques. Third, implement a U-Net semantic segmentation framework for microtopographic archaeological sites, and predict ancient city wall sites in the testing region after model training. Finally, the deep learning results are optimized using the connected component analysis method, and prediction mistakes such as holes and noise are removed. Taking Jinancheng, the capital city of the Chu kingdom, as an example, the proposed method process can identify and extract the ancient city wall sites at the pixel level, where the evaluation metrics reach 94.12% (Precision) and 81.38% (IoU). The experiment results are excellent due to improvement strategies in the dataset generation, model training, and post-processing steps. Thus, this study is significant for the current survey and protection of ancient city wall sites. The source code will be freely available at https://github.com/wshunli/Open-CHAI-CityWalls.