Intelligent geospatial maritime risk analytics using the Discrete Global Grid System

Abstract

Each year, accidents involving ships result in significant loss of life, environmental pollution and economic losses. The promotion of navigation safety through risk reduction requires methods to assess the spatial distribution of the relative likelihood of occurrence. Yet, such methods necessitate the integration of large volumes of heterogenous datasets which are not well suited to traditional data structures. This paper proposes the use of the Discrete Global Grid System (DGGS) as an efficient and advantageous structure to integrate vessel traffic, metocean, bathymetric, infrastructure and other relevant maritime datasets to predict the occurrence of ship groundings. Massive and heterogenous datasets are well suited for machine learning algorithms and this paper develops a spatial maritime risk model based on a DGGS utilising such an approach. A Random Forest algorithm is developed to predict the frequency and spatial distribution of groundings while achieving an R 2 of 0.55 and a mean squared error of 0.002. The resulting risk maps are useful for decision-makers in planning the allocation of mitigation measures, targeted to regions with the highest risk. Further work is identified to expand the applications and insights which could be achieved through establishing a DGGS as a global maritime spatial data structure.

Marine Habitat Mapping using Multibeam Echosounder Survey and Underwater Video Observations: A Case Study from Tioman Marine Park

“…The RF algorithm is highly effective in handling datasets that are intricate and diverse, making it a robust machine learning algorithm [25]. This algorithm works by creating an ensemble of decision trees and combining their predictions to generate a final output [21].…”

A review of data analytics techniques in enhancing environmental risk assessments in the U.S. Geology Sector

“…The use of a Random Forest algorithm to predict the frequency and spatial distribution of ship groundings is a prime example of how machine learning can complement traditional risk assessment methods. The study shows that data analytics can provide deeper insights and more accurate predictions than traditional methods alone (Rawson, Sabeur, & Brito, 2022). Çömert et al (2023) explore the use of 3D data integration for geo-located cave mapping based on unmanned aerial vehicle (UAV) and terrestrial laser scanner (TLS) data.…”

Multi-Scale Flood Mapping under Climate Change Scenarios in Hexagonal Discrete Global Grids

“…Most of the raster data were at 30 m resolution, with the exception of the elevation data acquired from the High Resolution Digital Elevation Model [44] at 1 m resolution. Land cover classes GeoTIFF scc 6 Stand crown closure GeoTIFF tfv 7 Total forest volume GeoTIFF ndvi 8 Normalized difference vegetation index GeoTIFF sol 9 Soil types Geodatabase geo 10 Surficial geology types Geodatabase Meteorological 12 Distance to the nearest major roads Shapefile Modeled meteorological data for the 1950-2100 period in three climate change scenarios are available at the Power Analytics and Visualization for Climate Science (PAVICS) platform (https://pavics.ouranos.ca/index.html (accessed on 16 May 2022)). The gridding process of meteorological data was accomplished by the Natural Resources Canada (NR-Can) using the Australian National University Spline (ANUSPLIN) implementation of the trivariate thin plate splines interpolation method and considering the effects of geospatial locations and altitudes [45].…”

“…These properties make DGGS an ideal framework for heterogeneous geospatial data integration and multi-scale geospatial data queries. In the previous literature, multi-source data have been integrated into DGGS as a common spatial structure to support wildfire modeling [5], ship grounding projections [6], land-sea interface incorporation [7], and consistent elevation service development [8].…”