Coastal change patterns from time series clustering of permanent laser scan data

Abstract

Abstract. Sandy coasts are constantly changing environments governed by complex, interacting processes. Permanent laser scanning is a promising technique to monitor such coastal areas and to support analysis of geomorphological deformation processes. This novel technique delivers 3-D representations of the coast at hourly temporal and centimetre spatial resolution and allows us to observe small-scale changes in elevation over extended periods of time. These observations have the potential to improve understanding and modelling of coastal deformation processes. However, to be of use to coastal researchers and coastal management, an efficient way to find and extract deformation processes from the large spatiotemporal data set is needed. To enable automated data mining, we extract time series of surface elevation and use unsupervised learning algorithms to derive a partitioning of the observed area according to change patterns. We compare three well-known clustering algorithms (k-means clustering, agglomerative clustering and density-based spatial clustering of applications with noise; DBSCAN), apply them on the set of time series and identify areas that undergo similar evolution during 1 month. We test if these algorithms fulfil our criteria for suitable clustering on our exemplary data set. The three clustering methods are applied to time series over 30 d extracted from a data set of daily scans covering about 2 km of coast in Kijkduin, the Netherlands. A small section of the beach, where a pile of sand was accumulated by a bulldozer, is used to evaluate the performance of the algorithms against a ground truth. The k-means algorithm and agglomerative clustering deliver similar clusters, and both allow us to identify a fixed number of dominant deformation processes in sandy coastal areas, such as sand accumulation by a bulldozer or erosion in the intertidal area. The level of detail found with these algorithms depends on the choice of the number of clusters k. The DBSCAN algorithm finds clusters for only about 44 % of the area and turns out to be more suitable for the detection of outliers, caused, for example, by temporary objects on the beach. Our study provides a methodology to efficiently mine a spatiotemporal data set for predominant deformation patterns with the associated regions where they occur.

Full 4D Change Analysis of Topographic Point Cloud Time Series using Kalman Filtering

“…These objects may also overlap in space or in time, allowing to extract multiple processes that impose change at a single location separately. Kuschnerus et al (2021) use the relative elevation values at spatial locations as features for clustering algorithms. They compare the performance of k-Means, agglomerative clustering, and DBSCAN on a dataset of a sandy beach, where both natural and anthropogenic forces impact the surface morphology.…”

“…hourly) acquire three-dimensional representations of the surrounding topography. To interpret the data for geographic monitoring, especially in terms of topographic change processes acting on the surface, information needs to be extracted in the form of movement patterns (Travelletti et al, 2014), objects (Anders et al, 2020) or clustering (Kuschnerus et al, 2021). This information can then be used by experts to analyse change patterns and magnitudes concerning their underlying causes, predict future events and assess immediate dangers.…”

“…We further derive several features from the smoothed time series, where noise has been reduced, and use them to form clusters of similar change. We also show how the smoothed time series can be used to improve the results obtained with established clustering methods, namely k-Means clustering, which has been applied to 4D point cloud data by Kuschnerus et al (2021) to identify change patterns on a sandy beach.…”

“…For the first approach, we use a k-Means clustering, which has been found to perform well by Kuschnerus et al (2021).…”

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

“…Identifying common properties of the input space between sets of exploratory model runs represents a widely used methodology in the field of decision support. Kuschnerus et al [144] applied time series clustering for the elaboration of coastal change models using permanent laser scan data. Motlagh et al [145] applied clustering techniques to group the customers of electricity supply companies to reduce the extreme dimensionality of the load time series.…”