Uncrewed Aerial Systems (UAS) equipped with digital cameras and sensors is an effective remote sensing tool for High Throughput Phenotyping (HTP) in precision agriculture. While studies have established relations to estimate crop height and biomass from UAS data, there has been limited work that examines the relationship between field measured biomass to UAS-Light Detection and Ranging (lidar) estimated biomass for the energy cane crop. This study explored the utility of UAS-lidar for phenotyping energy cane crops. The study collected lidar and ground truth data from an energy cane experimental plot in Weslaco, Texas-USA. Random Forest (RF) regression analysis showed high correlation between modelled crop height from lidar and field measured crop height (r2= 0.94, rmse = 0.12 m, me = −0.002, mae = 0.009, n = 400). Also a RF model between field measured biomass and modelled crop height, point cloud density, intensity, and number of returns generated from the lidar showed high performance (r2= 0.85, rmse = 92.00 g/m2, mae = 76.11, me = 0.50, n = 300). These results buttress the capability of UAS-lidar for high throughput phenotyping as has been reported in other studies.

Structure from Motion (SfM) photogrammetry, in conjunction with the Multi-View Stereo (MVS) technique, collectively known as SfM-MVS, emerges as a cost-effective solution for reconstructing 3D structures in real-world environments through the utilization of overlapping images. While SfM photogrammetry finds widespread use in remote sensing applications, challenges persist regarding reconstruction quality, scene segmentation, and computational complexity and efficiency. This paper introduces a workflow wherein semantically segmented images guide the SfM-MVS processing of overlapping images for reconstruction. The proposed workflow is applied to address two challenging tasks. The first task focuses on reconstructing a narrow pier situated over dynamic open ocean waves, while the second task involves simultaneous reconstruction and scene (point cloud) segmentation. Semantic labels assigned to pixels play a crucial role in determining the inclusion or exclusion of specific pixel sets during SfM-MVS processing. This experimental study underscores the promising potential of the proposed workflow to seamlessly integrate with the conventional SfM-MVS processing workflow. The approach not only augments the reconstruction quality in challenging environments but also advances the level of automation in generating spatial products within established SfM photogrammetry software suites. These findings contribute to the ongoing discourse on improving SfM-MVS methodologies for enhanced reconstruction outcomes and increased efficiency in spatial product generation.

Uncrewed aircraft system (UAS)-based surveying offers an efficient way to produce dense point clouds of roadway corridors within the right-of-way (ROW). Common techniques include structure-from-motion and multi-view stereo (SfM/MVS) photogrammetry, or UAS-SfM, and UAS-based light detection and ranging (lidar), or UAS-Lidar. However, considerations such as measurement fidelity and post-processing workflows are necessary to effectively deploy these technologies. This study examines UAS-SfM and UAS-Lidar survey repeatability of a roadway surface by comparing direct georeferencing solutions with and without the use of a ground control point (GCP) network. Field tests examine differences in vertical accuracy and compare differences in digital terrain model (DTM)-based change detection of road-way surface elevation. Repeat UAS-SfM and UAS-Lidar flights were conducted over a flat runway surface acting as a proxy for a typical state highway roadway corridor. The UAS-SfM surveys were conducted with a platform equipped with a 42 MP RGB digital camera and a post-processed kinematic (PPK) global navigation satellite system (GNSS) receiver for accurate image geopositioning. The UAS-Lidar surveys were conducted using a geodetic-grade RIEGL VUX-1LR long-range scanner and a Livox Avia mapping-grade scanner. Direct georeferencing solutions resulted in vertical change detection errors (i.e., root mean square errors) within 2.9 cm for UAS-SfM and between 1.6 cm and 1.8 cm for UAS-Lidar depending on the lidar sensor. The inclusion of GCPs improved UAS-SfM change detection error to within 2.3 cm while UAS-Lidar improved to 0.9 cm for the survey-grade VUX sensor and degraded to 3.1 cm for the Avia sensor.

Structure from Motion (SfM) photogrammetry in combination with the Multi-View Stereo (MVS) technique (SfM-MVS ) is a low-cost and effective tool to reconstruct the 3D structure of the real-world environments and objects using a set of overlapping images. This is approach is often implemented using imagery collected by a small uncrewed aircraft system (UAS) equipped with a high-resolution digital camera (referred to as UAS-SfM). The generated dense point cloud is typically considered the ultimate product of the workflow in almost all commercial and open-source software packages. Although, currently, UAS photogrammetry is being widely used in many remote sensing (RS) applications, there are some challenges regarding the efficiency, quality, and computational complexity in deriving some geospatial products in certain environments, especially where frequent mapping of the area is required to monitor certain changes in the surveyed environment. Efficient mapping of the coastal environments can be challenging due to the presence of water or other moving objects in almost all UAS images. It may also be challenging due to the need for accurate classified 2D and 3D land cover maps or digital terrain models (DTMs) which are required to examine the rate of changes in those environments. Providing those products through the SfM-MVS photogrammetry requires processing a large number of UAS images as well as performing expensive and complicated processing on 2D images and/or 3D point clouds which leads to an exponential increase in the computational complexity and cost in coastal mapping. This study proposes a novel approach that integrates semantic UAS image segmentation into the SfM-MVS photogrammetry workflow to address the aforementioned challenges in UAS photogrammetry mapping in coastal environments. The proposed approach leads to a higher level of automation in generating geospatial products with efficient exploitation of the available computation resources for SfM-MVS computations. The proposed approach exploits state-of-the-art deep learning (DL) for semantic UAS image segmentation to predict land cover image masks. Image masks predicted for moving objects, present in the study area, e.g., water bodies, are used to automatically exclude those areas from SfM-MVS computation. That leads to a higher computation efficiency and an lower noise in the reconstructed model. The proposed approach is then expanded to predict image mask through the DL-based image segmentation model for an automatic generation of the classified point cloud simultaneous with the SfM-MVS processing for reconstruction.

The increasing population, thus financial interests, in coastal areas have increased the need to monitor coastal elevation and shoreline change. Though several resources exist to obtain this information, they often lack the required temporal resolution for short-term monitoring (e.g., every hour). To address this issue, this study implements a low-cost ZED 2i stereo camera system and close-range photogrammetry to collect images for generating 3D point clouds, digital surface models (DSMs) of beach elevation, and georectified imagery at a localized scale and high temporal resolution. The main contributions of this study are (i) intrinsic camera calibration, (ii) georectification and registration of acquired imagery and point cloud, (iii) generation of the DSM of the beach elevation, and (iv) a comparison of derived products against those from uncrewed aircraft system structure-from-motion photogrammetry. Preliminary results show that despite its limitations, the ZED 2i can provide the desired mapping products at localized and high temporal scales. The system achieved a mean reprojection error of 0.20 px, a point cloud registration of 27 cm, a vertical error of 37.56 cm relative to ground truth, and georectification root mean square errors of 2.67 cm and 2.81 cm for x and y.

Uncrewed aircraft system (UAS)-based structure-from-motion / multi-view stereo (SfM/MVS) photogrammetry (referred to as UAS-SfM) provides an efficient means for dense 3D mapping of terrain and land cover at local geographic scales. For geospatial applications, UAS-acquired imagery must be accurately georeferenced before the desired mapping products are generated. The traditional method entails a network of precisely surveyed ground control points; referred to as indirect georeferencing. Though accurate, this process is tedious and unsuitable for UAS surveying of some shorelines and remote areas. This study examines the accuracy and repeatability of three different global navigation satellite system (GNSS) solutions for direct georeferencing of UAS imagery: real-time kinematic (RTK), post-processed kinematic (PPK), and precise point positioning (PPP). Specifically, the study evaluates whether these techniques can achieve a UAS-SfM point cloud vertical positional accuracy within 50 cm at the 95% confidence level for shoreline mapping and charting purposes. UAS-SfM field experiments relying on RTK and PPK consistently yielded root mean square errors within 10 cm, whereas PPP showed promising results but was unable to meet the accuracy requirements. Evaluation of baseline distance and sample rate on PPK solutions showed that the best accuracies are achievable when using base stations located within 30 km from the survey site, and the PPK fix percentage is influenced by the base station observation rate.

Information derived from full-waveform (FW) data collected by FW laser scanning systems has already been shown to be relevant for point cloud analysis tasks. Relevant waveform attributes to populate the corresponding point’s feature vector are typically provided through a post-processing FW analysis (FWA) technique based on fitting the echo waveform with a parametric function describing the shape and location of the echo pulse in the waveform. Samples of the digitized echo are the primary source for any waveform analysis using parametric functions. On the other hand, for some FW laser scanning systems, describing the complex system response model using a simple parametric function seems challenging or impractical. Earlier studies have shown the potential of waveform’s digital samples as relevant waveform attributes, for point cloud classification. The main goal of this study is to extend earlier experiments on direct exploitation of returned waveform signals collected by a FW terrestrial laser scanning (TLS) system in a built environment for point cloud classification, to multi-return waveform signals. Furthermore, the classification performance on feature vectors containing calibrated waveform attributes, derived from a waveform processing approach performed in real-time by the FW TLS system, is evaluated on multiple-echo waveforms and compared with the classification performance derived from the proposed FW data classification technique. Classification performance derived through the proposed technique demonstrates high information content of raw digitized waveform samples. Results show that feature vectors containing samples of digitized echoes carry more information about physical properties of the target than those containing calibrated waveform attributes.

Automatically detection the wet/dry shoreline would facilitates several applications in geological, and societal tasks such as biodiversity or beach management in coastal areas. High resolution remote imagery from UAVs simplifies detecting tiny wet/dry lines. Recently, deep learning models have shown much success compared to conventional image processing techniques for line/edge detection in terms of accuracy and automation. In this paper, an end-to-end deep learning model originated from Holistically-Nested Edge Detection (HED) model has been proposed to automatically detect the wet/dry shoreline in Fish Pass area, Texas, USA. The results shown 81% ODS (Optimal Dataset Scale), 100% OIS (per-Image best threshold), and 78.1% AP (Average Precision) score.

Full-waveform (FW) data collected by FW light detection and ranging (lidar) system have long been used to enhance the characterization of the surveyed area. It has already been shown that attributes describing the shape of the echo sig-nal in the feature vector of lidar points improves the performance of land cover classification. In this experiment, rather than fitting the echo waveform with an appropriate parametric model, typically a Gaussian, for feature extraction, the feature vector of each illuminated target is populated with the sam-ples of corresponding digitized waveform. Waveform data is collected over a built environment including both natural and built objects using a full-waveform (FW) terrestrial laser scanning (TLS) system. Results show that samples of raw digitized waveform carry useful information about the physi-cal properties of illuminated targets which lead to a relatively high performance in a multi -class TLS point cloud classifi-cation, where discriminative waveform features are extracted automatically within a proposed convolutional neural network (CNN) model.

In this study, the potential of raw samples of digitized echo waveforms collected by full-waveform (FW) terrestrial laser scanning (TLS) for point cloud classification is investigated. Two different TLS systems are employed, both equipped with a waveform digitizer for access to the raw waveform and online waveform processing which assigns calibrated waveform attributes to each point measurement. Point cloud classification based on samples of the raw single-peak echo waveform is compared with point cloud classification based on the calibrated online waveform attributes. A deep convolutional neural network (DCNN) is designed for the supervised classification. Random forest classifier is used as a benchmark to evaluate the performance of the proposed DCNN model. In addition, feature importance and temporal stability of the raw waveform samples versus the calibrated waveform attributes for point cloud classification are reported. Classification results are evaluated at two study sites, a built environment on a university campus and a coastal wetland environment. Results show that direct classification of the raw waveform samples outperforms classification based on the set of waveform attributes at both study sites. Results also show that the contribution of the range, as the only geometric attribute in the raw waveform feature vector, significantly increases the classification performance. Finally, the performance of the DCNN for filtering ground points to generate a digital terrain model (DTM) based on classification of the raw waveform samples is assessed and compared to a DTM generated from a progressive morphological filter and to real-time kinematic (RTK) GNSS survey data.

This study assesses a lower-cost mobile lidar system along with a 360-degree spherical camera for use in coastal environments, with a focus on rapid post-storm data collection. Testing was completed to create a ‘best methods procedure for planning, data collection and post-processing. The system being used is called the HiWay Mapper, integrated by LidarUSA and consists of a Velodyne HDL-32E lidar sensor, a NovAtel global navigation satellite system (GNSS) receiver and inertial navigation system (INS), and a FLIR Ladybug 360-degree camera. Results show that an initialization driving procedure is needed for better positioning, the point cutoff distance should be, at a maximum, 55 meters, and ground control targets allow greater vertical accuracy. Lastly, the “best methods” procedure is used to collect post-storm data from hurricane Hanna and vertical accuracy assessments were completed to determine the performance of the sensor.

Full-waveform analysis (FWA) through modeling and decomposition of the digitized echo waveform, measured by a full-waveform (FW) laser scanning system, is typically employed to derive the waveform attributes, including the number of echoes, amplitude and width of each detected echo in the backscattered waveform signal. It has already been shown that such attributes in the feature vector of each measured point can enhance the performance of semantic point cloud segmentation. In this experiment, however, rather than modeling the waveform, the feature vector of each measured target is populated with the raw samples of the waveform related to the target. Random forest classification is used to classify a 3D scene consisting of both natural and man-made targets. The results show that the raw samples of the digitized waveform are discriminative enough to be used as independent features for a multi-class classification task, where, in this experiment, the overall accuracy of 90% was achieved for classifying the$3D$scene.

This study utilizes airborne lidar and unmanned aircraft system (UAS) structure-from-motion (SfM) derived elevation models to examine the impact of Hurricane Michael on Little St. George Island's subaerial beach and foredune system and its respective short-term recovery. Volumetric change detection, horizontal shoreline movement, and feature extraction analyses were conducted for the purposes of monitoring its geomorphic evolution succeeding the storm event. Results of the study indicate Hurricane Michael had considerable impacts on the island, causing a net loss of 198,786 m3of sediment and an average reduction of dune crest elevations by 0.62 m. Derived results of the recovery period suggest that, despite an average increase of dune crests elevations by 0.04 m, Little St. George Island has sustained a net loss of approximately 14,340 m3.

This study utilized a mobile lidar system (MLS) for rapid post-storm damage assessment of the beach and foredune structure along a section of sandy beach on North Padre Island, Texas, located roughly 50 km south of San Jose Island where Hurricane Harvey first made landfall. Strong winds, storm surge levels, and flooding resulted in rapid change of the beach and foredune structures. MLS data were collected on September 5, 2017, only 11 days after Harvey made landfall. The system used is called a Velodyne HDL-32E (made by LidarUSA) and is a lower cost, shorter range scanner. Tests were conducted to ensure scanner accuracy and a “best practices” procedure for initialization of the positioning and orientation system was produced. Results concluded that more tests must be completed before using the scanner in dynamic driving patterns. However, post-Harvey scans aligned well with pre-Harvey airborne lidar data collected over the region, and these data were used to measure beach erosion stemming from the storm.

This work proposes a mechanism which can be used as a basis for allowing camera POSE information to be maintained reliably during loss or interference with inertial motion unit or positioning system integration. This basis is formed by employing image synthesis networks with atypical data for the network type: inputs are normal down scaled source imagery while outputs are native resolution images composed of the contents of the same scene viewed from a fixed offset position. The goal of this application is to simulate the presence of a binary camera from monocular hardware, which makes feasible certain POSE estimation workflows which would normally require binary cameras on monocular platforms. Being able to rapidly synthesize images of additional camera positions without having to physically navigate to those positions allows for two methods to build off each other. First, knowing that the model should consistently maintain a specific POSE from the source camera allows synthetic images to be used to artificially inflate available data during structure from motion processing with confidence in the accuracy of synthetic points. It also enables the comparison of an image at an actual physical location with the synthetic one later as a measure of POSE accuracy which can be incorporated into a solution for computing POSE of the image source.

Bathymetry, or the measurement of depth in any body of water, has been an area of research since man began to venture out onto the open waters. Historically, researching the near-shore surf zone has been a time consuming and expensive process. The tools and methods used to gather data points in the surf zone are either time inefficient, expensive, or both. This is an issue considering how dynamic the surf zone environment can be. It is possible that by the time the surf zone bathymetry measurements have been completed, they are already out of date. This project utilizes unmanned aerial systems (UAS) to gather high-quality video of the near-shore surf zone waves crest. This footage is then processed using particle image velocimetry (PIV), a method for determining the velocity of particles in sequential images. This velocity is then processed using linear-wave theory shallow water approximations for calculating wave celerity from depth, but ran in reverse, to obtain the bathymetry itself. Ground-truth field measurements are used to verify the resulting velocity and depth.

This study uses a small Unmanned Aircraft System (sUAS) equipped with a multispectral sensor to assess various Vegetation Indices (VIs) for their potential to monitor iron chlorosis levels in a grain sorghum crop. Iron chlorosis is a nutritional disorder that affects various crops grown in high- pH, calcareous soils. Weekly flights were completed over the growing season and processed using Structure-from- Motion (SfM) photogrammetry to create orthorectified, multispectral reflectance maps in the red, green, red-edge, and near-infrared wavelengths. Ground data collection was used to analyze stress and chlorophyll levels, correlating them to the imagery. 25 VIs were calculated using reflectance maps and soil-removed reflectance maps. The separability for each VI was calculated using a two-class distance measure. The field-acquired data was used to conclude which VIs achieved the best results. In conclusion, the soil-removed MERIS Terrestrial Chlorophyll (MTCI), Normalized Difference Red-Edge (NDRE), and Normalized Green (NG) indices achieved the highest amount of separation.

Coastal wetlands are among the most productive ecosystems in the world providing numerous valuable services for people and wildlife including recreation, fish and wildlife protection, sediment control and flood prevention. Changes in land cover/use have great impact on the functionality and productivity of wetlands. Therefore, accurate and fast monitoring of land cover/use allow policy makers and wetland users to devise and implement policies and management practices to lessen the side effects of any potential change on wetlands. In this study, we apply deep convolutional neural network (DCNN) to infer complex wetland classes in a semantic segmentation task on hyperspatial resolution UAS images. We examine the capacity of the well-known FCN-VGG architecture for wetland mapping. Results illustrate that fine-tuning the network using transfer learning with UAS hyper-resolution images provide state-of-the art semantic segmentation accuracy of 89.98%.

In this work we explore a combination of methods that allow us to analyze and study hyper-local environmental phenomena. Developing a unique application of monoplotting enables visualization of the results of deep-learning object detection and traditional object tracking processes applied to a perspective view of a parking lot on aerial imagery in realtime. Additionally, we propose a general algorithm to extract some scene understanding by inverting the monoplotting process and applying it to digital elevation models. This allows us to derive estimations of perspective image areas causing object occlusions. Connecting the real world and perspective spaces, we can create a resilient object tracking environment using both coordinate spaces to adapt tracking methods when objects encounter occlusions. We submit that this novel composite of techniques opens avenues for more intelligent, robust object tracking and detailed environment analysis using GIS in complex spatial domains provided video footage and UAS products.

Over recent years, light detection and ranging (lidar) sensor technology has rapidly evolved and miniaturized. The reduced sensor size and weight have opened more doors for lidar sensors to be carried onboard unmanned aircraft systems (UASs) [1]. Compared with traditional airborne lidar mapping, UAS platforms offer more flexibility in terms of flight design and data collection, rapid response capabilities, and potentially cost at local mapping scales.

Unmanned aircraft systems (UAS) imagery-based crop height measurements are usually determined by mean of canopy height models (CHMs) without describing specific metrics in detail. In this paper, a crop height estimation method was proposed based on UAS imagery: 1) the centerline for each crop row was determined first on the CHM raster, 2) row polygons were then drawn according to the centerlines and predefined width. The length of each polygon depends on the actual row length, and 3) the percentile height was computed by using the signals in each delineated polygon from the CHM raster. In this method, the polygon width is adjustable in accordance with appearance and shape of different types of crops. The study was conducted over an experimental maize field using multiple UAS platforms and cameras at the Texas A&M AgriLife Research and Extension Center at Corpus Christi, TX, during the growing season in 2016. The results showed that different platforms can recover canopy height in a similar pattern using structure-from-motion photogrammetry while the height statistical results differed in scale at the maize field due to different camera resolution and flight altitude.

Accurate and inexpensive mapping of the littoral zone has implications in land management, cadastral systems, and erosion monitoring. In this study, a small unmanned aircraft system (UAS) equipped with a consumer-grade RGB digital camera is used to evaluate structure-from motion (SfM) photogrammetry and optimal inversion, individually and infusion, for deriving topography and bathymetry elevation. The study area consists of an engineered beach with a shallow littoral zone. First, a comparison is made between 3D point cloud measurements derived from SfM processing and RTK GPS survey data. A denoising method is developed to filter accurate SfM substrate points. Next, a method of band ratio optimization, or optical bathymetric inversion, is evaluated where the water surface occludes and disrupts the SfM feature matching process. Results show that a complementary data fusion method enables generation of a seamless topo-bathymetric elevation model.

Detection from airborne sensors of near-ground objects occluded by above-ground vegetation is not usually straightforward. Our hypothesis is that the probability of obstruction due to objects above ground at any location in the forest environment can be estimated with measurable uncertainty from airborne lidar data. The essence of our approach is to develop a data-driven learning scheme that creates 2D probability maps for obstructions at the study site. The result shows the effectiveness of the newly developed individual tree detection algorithm (with the accuracy index of 77.1%, tested using ground surveys) and also the usefulness of the clutter and uncertainty maps in the prediction of line-of-sight visibility, mobility and above-ground forest biomass.

Full waveform bathymetric LiDAR allows a detailed examination of laser backscatter from the water surface, water column and benthic layer. The presence of seagrass on the ben-thic layer would also be expected to influence the backscat-tered radiation encapsulated in the full waveform observations. The combination of conventional geometric features, radiometric features and derived geometric features from the waveform analysis may make it possible to identify the presence of seagrass or even classify the different types of sea-grass. An analysis of the correlation of seagrass location with different full waveform LiDAR parameters is presented. Overall, it is found that a high degree of correlation exists between the presence of seagrass and LiDAR intensity, benthic elevation and benthic return pulse width. Surface roughness, curvature and vertical uncertainty are found to have weak correlation with the presence of seagrass.

Terrestrial laser scanning (TLS) is utilized to monitor bank erosion along a stream that has incised through historic millpond (legacy) sediment. A processing workflow is developed to generate digital terrain models (DTMs) of the bank's surface from the TLS point cloud data. Differencing of the DTMs reveals that the majority of sediment loss stems from the legacy sediment layer. The DTM time series is stacked into a voxel model to form a space-time cube (STC). The STC provides a compact representation of the bank's spatiotemporal evolution captured by the TLS scans. The continuous STC extends this approach by generating a voxel model with equal temporal resolution directly from the point cloud data. Novel visualizations are extracted from the STCs to explore patterns in surface evolution. Results show that erosion is highly variable in space and time, with large-scale erosion being episodic due to bank failure within legacy sediment.

Airborne light detection and ranging (LiDAR) surveys provide a rich data source of topographic information. However, beach monitoring with LiDAR data has been mostly limited to visualization and first-order measures derived from digital elevation models (DEMs). To exploit more information from multitemporal LiDAR data acquired over a beach, we extract surface features to detect morphologies that are indicative of shoreline change patterns. First, through cross-shore profile sampling of LiDAR-derived DEMs, the continuous 3-D beach surface is parameterized into several 1-D morphologic features progressing alongshore. Profiles are subsequently partitioned into binary erosion or accretion classes dependent on measured shoreline change between surveys. Then, a feature's class separability is quantified using information divergence measures nonparametrically constructed via Parzen windowing. The more interclass separation provided by a feature, the greater its discriminative potential, and the higher its ranking as a morphologic indicator. Rankings are computed across the survey epochs to evaluate performance stability of the features. Finally, the top-ranked features are implemented within a naive Bayes classifier to assess their ability to segment terrain more likely to erode. Results demonstrate the utility of the developed framework to systematically extract and incorporate useful morphologic information from LiDAR data for discerning patterns in beach change.

Modern airborne laser swath mapping (ALSM) systems measure both elevation and reflection intensity of the terrain. However, this intensity has been under utilized as a feature for image classification because it does not represent true terrain radiance. In areas with minimal topographic relief, such as beaches, we show that segmenting intensity images rather than elevation images has great potential for scene analysis. Several intensity-based features are extracted from ALSM data collected along a beach and partitioned into three classes to detect the water line. Class-conditional probability density functions are estimated for each feature to asses which are most informative. Results indicate significant class separation using centroidal features. Their classification performance is evaluated using a naive Bayes classifier and the area under receiver operating characteristic curves. The method presented provides a novel feature extraction and a systematic feature selection procedure for high-resolution ALSM intensity data.

Airborne lidar data were acquired along St. Augustine Beach, Florida six times between August 2003 and June 2006. To identify sub-aerial morphologies indicative to beach erosion, the data sets were mined extensively by extracting several morphological features using cross-shore profile sampling. For each profile, the features were grouped into erosion or accretion classes and their class-conditional probability density functions (PDFs) estimated via Parzen windowing. PDF separability was ranked using symmetric and normalized measures of relative entropy (i.e. divergence). Results were compared to a simple median metric. The more interclass separation provided by a feature, the greater its potential as an indicator for erosion or accretion. Over short time periods (>1 month), beach slope and beach width ranked highest by providing the most separation and therefore high potential as indicators for erosion. Over longer time periods (>1 year), deviation-from-trend, which is the shoreline's deviation from the natural strike of the beach, ranked highest. This is significant in that the pier region's deviation from the natural trend is believed by coastal researchers to be a strong contributing factor to it being an erosion "hot spot". The method we have developed provides a systematic framework to mine high-resolution airborne lidar data over beaches, detect erosion-prone areas, and numerically rank a feature's potential as an indicator for erosion.