DHDaan Hulskemper

Daan Hulskemper

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Daan Hulskemper has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Relating Monthly to Yearly Morphological Changes in Embryonic Coastal Dune Systems

    by R. L. Hulskamp, D. C. Hulskemper, J. A. Á. Antolínez, R. C. Lindenbergh, M. Pregnolato, S. de Vries

    Embryonic coastal dunes are dynamic morphological features shaped by wind, waves, sediment availability, and vegetation. Temporal variability in these drivers controls embryo dune dynamics at short timescales (hours–days), while accreting dune systems often show gradual change over longer timescales (years–decades). How shorter‐term variability translates into longer‐term signals in dune dynamics remains poorly understood, partly due to a lack of frequent high‐resolution measurements and frameworks to analyze their full dimensionality. To bridge the scale gap, we analyze eight high‐resolution UAV laser scanning (ULS) surveys of the Zandmotor dune system captured within 1 year. Our study investigates monthly morphological variability and its contribution to annual dune volume growth. The ULS time series is processed in four steps: (a) volume change estimation across the study area, (b) time series clustering to identify areas of similar elevation change patterns, (c) automatic dune ridge extraction to characterize shape and sediment storage, and (d) vegetation coverage mapping to assess its role in sediment trapping. Results show that episodic redistribution events with high intra‐annual variability drive annual dune dynamics. Monthly sediment redistribution can exceed yearly net growth by an order of magnitude (103 vs. 15 m 3 /m/year). Vegetation establishment enhances sediment stabilization, with vegetated areas growing at 30 cm/year compared to 8 cm/year in unvegetated zones. Intra‐annual dynamics reflect short‐term wind forcing, local topographic feedbacks, and remobilization of sediment temporarily stored in dune ridges. These findings highlight the importance of sediment stabilization processes related to topography, wind forcing, and vegetation in connecting monthly and yearly dune changes.

  • Open Access

    Laser scanning of high frequency tree movement

    by Thomas de Jong, Daan Hulskemper, Roderik Lindenbergh

    Botanical trees demonstrate complicated motion patterns under wind forcing. Studying these motion patterns is relevant as tree parts may become hazardous during storms, and the movement of these trees affects the surrounding wind field, providing, for example, wind shadows. Eventually, wind enforced tree motion may even be incorporated in wind simulation models used to design liveable neighbourhoods. These motion patterns are, however, difficult to assess as in situ sensors lack coverage while video imagery lacks full 3D capacity. Recently, fast 3D laser scanners became available. For one such scanner, the Livox Avia, a workflow is presented that allows scanning tree movement at frequencies of up to 2 Hz. The scanner, possibly triggered to scan by a wind-meter, is building up a space-time array, consisting of range measurements at a give time, in a given direction. In a consecutive step, this space-time array is decomposed into single point clouds of a certain duration. The decomposition can be done over different time intervals; point clouds of shorter duration show lower coverage of measurements, but are also less affected by moving tree parts during scanning. After decomposition, motion vector fields between consecutive point clouds representing different time frames are estimated using the existing PlantMove algorithm. Applications of the workflow on different moving tree scenarios demonstrate how this novel measurement strategy is able to reveal complex and detailed spatial and temporal patterns of tree movement, with observed displacements on the order of decimeters, under wind stress. Extending the setup to e.g. three scanners will enable to capture wind induced complex tree movement at branch level, which is essential input for running reliable wind flow simulations at neighbourhood level.

  • Open Access

    Sand Engine beach state assessment by applying machine learning on massive Argus image data

    by Alex De Jong, Roderik Lindenbergh, Sander Vos, Daan Hulskemper

    Dynamic beaches world-wide are monitored by so-called Argus cameras. Their automatic capturing results in large databases of ∼ 30’ interval coastal images acquired during different illumination conditions. We present a lightweight method to automatically extract sand and supporting classes from ∼ 1 million Argus images, spanning ∼ 10 years, of the Sand Engine, The Netherlands, a nature-based solution for beach erosion. The workflow consists a series of neural networks. First, a ResNet18 model selects images of sufficient quality. Second, 24 pixel-wise shallow multi-layered perceptrons (MLPs) classify pixels into 5 classes, Water, Foam and Eolian, Wet and Armored Sand. The 24 MLPs correspond to 12 cameras with two different lighting conditions. The results from the 24 MLPs are used as pseudo labels for 24 CNNs that improve the initial classification by including spatial awareness. These 24 CNNs are fused in one ensemble CNN, robust to camera choice and lighting condition. At this stage, still a separate CNN is used to additionally detect vegetation pixels. Results show in most cases good agreement with human interpretation, with an overall accuracy of ∼ 88%. Most promising is that ∼ 150.000 images per day can be processed on a high-end consumer PC at a quality difficult to obtain by a human operator. Future work should focus on exploiting the large database of results for improving our understanding of dynamic processes at this challenging environment. As the workflow is generic in nature, it should be easily applicable for other image based monitoring databases.

  • Open Access

    Low-cost Terrestrial Laser Scanners for Permanent Monitoring of Beach-Dune Systems

    by Daan Hulskemper, Hannah Weiser, Ronald Tabernig, Bernhard Höfle, Thomas de Jong, Roderik Lindenbergh

    Permanent laser scanning (PLS) is an effective tool for near-continuous monitoring of topographical changes in beach-dune systems. While PLS systems were traditionally costly, the emergence of affordable LiDAR sensors enables larger-scale setups with multiple scanners or sites. However, the different characteristics compared to high-end devices, create challenges for one-on-one replacement. To assess how low-cost sensors can replace high-end sensors, we compare the performance of a setup with several low-cost Livox AVIA sensors to a single high-end RIEGL VZ-2000i sensor in its ability to capture an embryonic dune field with large variation in topography. This is evaluated using HELIOS++ virtual laser scanning (VLS). To also assess the representativeness of the simulations, we further compare the VLS to real-world measurements with the Livox AVIA. Based on a VLS setup with six AVIAs mounted on tripods at 2 m above ground, a coverage of 52% can be obtained, which is similar to the coverage of a single RIEGL VZ-2000i on a tower 8 m high. The real-world experiments confirm the VLS results with a slightly lower point cloud coverage of 42%. Furthermore, the effective range of the Livox AVIA in a beach-dune system lies around 100-150 m. At larger ranges, only pulses at high incidence angles (angle between surface and incoming beam, >20o) are registered at the scanner. The variations in coverage between the VLS and real-world scans highlight the need for careful consideration of the occlusion potential of different representations of the topography, beam divergence shapes, and the moisture conditions.

  • Open Access

    Coastal process understanding through automated identification of recurring surface dynamics in permanent laser scanning data of a sandy beach

    by Daan Hulskemper, José A. Á. Antolínez, Roderik Lindenbergh, Katharina Anders

    Four-dimensional (4D) topographic datasets are increasingly available at high spatial and temporal resolution, particularly from permanent terrestrial laser scanning (PLS) time series. These data offer unprecedented opportunities to analyse rapid and complex morphological processes occurring in sandy coastal environments, such as sandbar welding or bulldozer activity, as well as their longer-term impacts on sandy beaches. However, studying these processes requires the extraction and recognition of recurrent topographical surface dynamics across time, which in turn demands novel, automated methods. This study presents a novel workflow that combines 4D objects-by-change (4D-OBCs) with unsupervised classification using Self-Organizing Maps (SOMs) and hierarchical clustering. Applied to a three-year PLS time series comprising 21 194 hourly point clouds, the method identifies 4412 instances of short-term surface dynamics. These are organized into two SOMs (64 nodes each) and further grouped into 31 clusters representing distinct dynamic types, such as berm deposition, large-scale backshore erosion, and human interventions (e.g., bulldozer activity). The classification results enable detailed spatiotemporal analyses of coastal morphodynamics. The SOM topology reveals seasonal patterns in surface activity, where, for example, winter is dominated by erosional activity over the whole beach but depositional activity mainly occurs in the intertidal area. The broader clusters facilitate interpretation of environmental responses and identification of changes in cross-shore zonation of types of dynamics, like berm formation. This approach demonstrates the potential of integrating PLS and unsupervised learning to characterize complex surface dynamics, through a fully automated extraction and classification workflow. While the interpretation of clusters and their relation to environmental variables in this study is performed through expert-based analysis, the methods provide a framework for targeted, data-driven investigation and prediction of morphodynamic processes in high-resolution 4D remote sensing datasets.

  • Open Access

    Author's comments in response to both RCs

    by Daan Cornelis Hulskemper, José A. Á. Antolínez, Roderik Lindenbergh, Katharina Anders

    Four-dimensional (4D) topographic datasets are increasingly available at high spatial and temporal resolution, particularly from permanent terrestrial laser scanning (PLS) time series. These data offer unprecedented opportunities to analyse rapid and complex morphological processes occurring in sandy coastal environments, such as sandbar welding or bulldozer activity, as well as their longer-term impacts on sandy beaches. However, studying these processes requires the extraction and recognition of recurrent topographical surface dynamics across time, which in turn demands novel, automated methods. This study presents a novel workflow that combines 4D objects-by-change (4D-OBCs) with unsupervised classification using Self-Organizing Maps (SOMs) and hierarchical clustering. Applied to a three-year PLS time series comprising 21,194 hourly point clouds, the method identifies 4,412 instances of short-term surface dynamics. These are organized into two SOMs (64 nodes each) and further grouped into 31 clusters representing distinct dynamic types, such as berm deposition, large-scale backshore erosion, and human interventions (e.g., bulldozer activity). The classification results enable detailed spatiotemporal analyses of coastal morphodynamics. The SOM topology reveals seasonal patterns in surface activity, where, for example, winter is dominated by erosional activity over the whole beach but depositional activity mainly occurs in the intertidal area. The broader clusters facilitate interpretation of environmental responses and identification of changes in cross-shore zonation of types of dynamics, like berm formation. This approach demonstrates the potential of integrating PLS and unsupervised learning to characterize complex surface dynamics, and provides a framework for targeted, data-driven investigation and prediction of morphodynamic processes in high-resolution 4D remote sensing datasets.

  • Open Access

    Uncovering Causation of Short-Term Sandy Beach Surface Dynamics Measured by Permanent Laser Scanning

    by Daan Hulskemper, Katharina Anders, José A. A. Antolínez, Roderik Lindenbergh

    The causal drivers of short-term changes (days to months) in human-, wind-, and wave-driven sand transport on a sandy beach are not often considered in an integral and data-driven approach. However, improving current knowledge on (urban) sandy beach topographical change requires the incorporation of multi-scale, cross-sectional and human factors. In this research we process a time series of 21,194 hourly point clouds, obtained in a Permanent Terrestrial Laser Scanning setup. From this 3D time series we extract 5,102 short-term temporary surface dynamics, through a method called 4D objects-by-change (4D-OBCs). The causal drivers of two of these 4D-OBCs are investigated in detail. One is interpreted as an aeolian depositional surface dynamic (1), and one as a bulldozer deposit, that consecutively eroded under high wave energy conditions (2). The dynamics show clear correlation to a particular combination of wind direction and intensity (1), and wave height and wave period (2), indicating that point cloud time series derived 4D-OBCs are useful data to study causality of short-term surface dynamics of different origins. However, to study these surface dynamics systematically and derive statistical proof of causal relations we must consider multivariate correlations, as well as spatiotemporal dependence between sediment dynamics and larger scale morphological changes on the beach.

  • Open Access

    Permanent terrestrial laser scanning for environmental monitoring

    by Roderik Lindenbergh, Sander Vos, Daan Hulskemper

    Many topographic scenes demonstrate complex dynamic behavior that is difficult to map and understand. A terrestrial laser scanner fixed on a permanent position can be used to monitor such scenes in an automated way with centimeter to decimeter quality at ranges of up to several kilometers. Laser scanners are active sensors, and can continue operation during night. Their independence from surface texture properties ensures in principle that they provide stable range measurements for varying surface conditions.Recent years have seen an increase in the employment of such systems for different applications in environmental geosciences, including forestry, glaciology and geomorphology. This employment resulted in a new type of 4D topographic data sets (3D point clouds + time) with a significant temporal dimension, as such systems can acquire thousands of consecutive epochs.However, extracting information from these 4D data sets turns out to be challenging, first, because of insufficient knowledge on error budget and correlations, and second, because of lack of algorithms, benchmarks, and best-practice workflows.The presentation will showcase recently active systems that monitored a forest, a glacier, an active rockfall site and a sandy beach respectively. Data from these systems will be used to illustrate different systematic challenges that include instabilities of the sensor system, meteorological and atmospheric influence on the data product and the maybe surprising need for alignment of point clouds from different epochs.In addition, different ways to extract information from these 4D data sets will be discussed, in connection with particular applications. While bi-temporal change detection is often a starting point for exploring 4D data, several methods are being developed that truly exploit the extensive time dimension, including tracking, trend analysis, time series clustering and spatio-temporal region growing.Lessons learned from experiences with these systems in different domains lead to several recommendations for future employment considering field of view design, auxiliary sensors (e.g. IMU, camera, weather station) and the possible deployment of low-cost alternatives, thereby providing a view on the near future of permanent laser scanning.ReferenceLindenbergh, R., Anders, K., Campos, M., Czerwonka-Schröder, D., Höfle, B., Kuschnerus, M., Puttonen, E., Prinz, R., Rutzinger, M., Voordendag, A & Vos, S. (2025). Permanent terrestrial laser scanning for near-continuous environmental observations: Systems, methods, challenges and applications. ISPRS Open Journal of Photogrammetry and Remote Sensing, 17, 100094. DOI: 10.1016/j.ophoto.2025.100094

  • Open Access

    Comment on egusphere-2025-4964

    by Daan Cornelis Hulskemper, José A. Á. Antolínez, Roderik Lindenbergh, Katharina Anders

    Four-dimensional (4D) topographic datasets are increasingly available at high spatial and temporal resolution, particularly from permanent terrestrial laser scanning (PLS) time series. These data offer unprecedented opportunities to analyse rapid and complex morphological processes occurring in sandy coastal environments, such as sandbar welding or bulldozer activity, as well as their longer-term impacts on sandy beaches. However, studying these processes requires the extraction and recognition of recurrent topographical surface dynamics across time, which in turn demands novel, automated methods. This study presents a novel workflow that combines 4D objects-by-change (4D-OBCs) with unsupervised classification using Self-Organizing Maps (SOMs) and hierarchical clustering. Applied to a three-year PLS time series comprising 21,194 hourly point clouds, the method identifies 4,412 instances of short-term surface dynamics. These are organized into two SOMs (64 nodes each) and further grouped into 31 clusters representing distinct dynamic types, such as berm deposition, large-scale backshore erosion, and human interventions (e.g., bulldozer activity). The classification results enable detailed spatiotemporal analyses of coastal morphodynamics. The SOM topology reveals seasonal patterns in surface activity, where, for example, winter is dominated by erosional activity over the whole beach but depositional activity mainly occurs in the intertidal area. The broader clusters facilitate interpretation of environmental responses and identification of changes in cross-shore zonation of types of dynamics, like berm formation. This approach demonstrates the potential of integrating PLS and unsupervised learning to characterize complex surface dynamics, and provides a framework for targeted, data-driven investigation and prediction of morphodynamic processes in high-resolution 4D remote sensing datasets.

  • Open Access

    Comment on egusphere-2025-4964

    by Daan Cornelis Hulskemper, José A. Á. Antolínez, Roderik Lindenbergh, Katharina Anders

    Four-dimensional (4D) topographic datasets are increasingly available at high spatial and temporal resolution, particularly from permanent terrestrial laser scanning (PLS) time series. These data offer unprecedented opportunities to analyse rapid and complex morphological processes occurring in sandy coastal environments, such as sandbar welding or bulldozer activity, as well as their longer-term impacts on sandy beaches. However, studying these processes requires the extraction and recognition of recurrent topographical surface dynamics across time, which in turn demands novel, automated methods. This study presents a novel workflow that combines 4D objects-by-change (4D-OBCs) with unsupervised classification using Self-Organizing Maps (SOMs) and hierarchical clustering. Applied to a three-year PLS time series comprising 21,194 hourly point clouds, the method identifies 4,412 instances of short-term surface dynamics. These are organized into two SOMs (64 nodes each) and further grouped into 31 clusters representing distinct dynamic types, such as berm deposition, large-scale backshore erosion, and human interventions (e.g., bulldozer activity). The classification results enable detailed spatiotemporal analyses of coastal morphodynamics. The SOM topology reveals seasonal patterns in surface activity, where, for example, winter is dominated by erosional activity over the whole beach but depositional activity mainly occurs in the intertidal area. The broader clusters facilitate interpretation of environmental responses and identification of changes in cross-shore zonation of types of dynamics, like berm formation. This approach demonstrates the potential of integrating PLS and unsupervised learning to characterize complex surface dynamics, and provides a framework for targeted, data-driven investigation and prediction of morphodynamic processes in high-resolution 4D remote sensing datasets.