Spatio-Temporal Wave Pattern using Multi-dimensional Clustering Method for Exploring Ocean Energy Potential

Abstract

Wave is formed from the movement of air caused by pressure variations that make airflow move from high pressure toward places of low pressure. Understanding the wave patterns is challenging since it is highly changeable in space as they travel in variety of directions and heights. Wave are also changing over time especially during the monsoon seasons. Hence, to extract significant information from this highly changeable behaviour of wave this study has utilized a multi-dimensional clustering technique called co-clustering. This technique is able to cluster spatio-temporal data with similar behavior into spatial and temporal components simultaneously. To reveal the spatial and temporal patterns, an algorithm called Bregman Block Average co-clustering with I-divergence (BBAC_I) has been implemented for extracting wave patterns. In order to discover the wave behaviour, the extracted wave patterns were visualized in the form of heatmap that contain information of co-clusters; spatial clusters and temporal clusters dimensions. Then, both spatial and temporal clusters from the heatmap were transformed into geographical maps to depict the variation of wave patterns based on their individual dimension. From these maps, we could observe the distribution of 8 different group of clusters that representing the spatial wave patterns. Furthermore, 5 individual maps have been produced to depict the temporal wave patterns across the study area. Finally, the obtained maps were interpreted in the form of wave height which were found to be within 0.4 to 1.4 m heights. The wave height information can be used for identifying their potential for ocean energy harvesting along the coastal area. In generally, the generated spatio-temporal wave patterns from this study could aid Malaysian marine agencies to provide strategic planning for proposing future ocean energy in Malaysian coastal area.

Revealing Spatial–Temporal Patterns of Sea Surface Temperature in the South China Sea Based on Spatial–Temporal Co-Clustering

“…Chen et al created a visual analysis system for geospatial data based on a Bayesian network, allowing users to interactively investigate anomalous patterns in geographic data [27]. Wu used co-clustering for the first time in 2020 to investigate the temporal and spatial differentiation of spring phenology in China [28]; Rohanap et al used a multidimensional clustering technique to demonstrate a spatial and temporal wave map for the detection of ocean energy potential [29]. Similarly, the methods mostly analyze spatiotemporal data from a single dimension, either time or space, without considering spatial-temporal dependencies.…”