Creation of a coastal evolution prognostic model using shoreline historical data and techniques of digital image processing in a GIS environment for generating future scenarios

Abstract

The process of coastal erosion is a global problem that impacts approximately 70% of coastal regions of the Earth. It causes loss of property, infrastructure, and biodiversity, besides generating major economic impacts. Therefore, the analysis and monitoring of coastal erosion is an issue that needs to be addressed. In this sense, remotesensing data have been widely used in studies that evaluate the spatial and temporal changes of land use. In addition, the use of time series of satellite imagery applied in the investigation of changes in the Earth's coverage and its spatio-temporal pattern has been proven as an extremely efficient approach. Thus, remote sensing and geoprocessing are effective techniques to obtain continuous and dynamic information from coastal regions at different levels and scales. In this context, the main objective of this work was to create a prognostic model for the generation of future scenarios, based on the analysis of the spatialtemporal changes of the shorelines from past decades to the present, having as the pilot area the coast of the municipality of Icapuí, in the State of Ceará, Northeastern Brazil. For that, Statistical Regression technique was used. In addition, the techniques of Digital Image Processing and the extraction of the modified normalized difference water index were used. As a result, the prognosis of coastal erosion was generated for the year 2021, based on the time series of the years 1985, 1991, 1997, 2003, 2009, and 2015. After the extrapolation process, the results were validated through the mean absolute error. Furthermore, through the Python programming language and the OpenCV library, a computational solution was implemented to be executed in a Geographic Information Systems environment that automated the process of generating future prognostic and the extraction of the shoreline in a shapefile format.

Cross-Shore Profile Evolution after an Extreme Erosion Event—Palanga, Lithuania

“…Beach profile features and evolution are essential considerations for coastal engineering projects. In the eastern Baltic Sea, profile dynamics have received comparatively less attention than alongshore processes, and the available knowledge remains partly qualitative and empirical [1,10,[51][52][53][54].…”

Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

“…This type of forecasting method has been employed 30 times in the reviewed literature. The simplest method of a forecast in this category is to fit a linear trend to a time series and calculate future values from the resulting regression equation [119,160,163,164,178,179]. More sophisticated methods of time-series forecasting consider auto-correlation, global trends, and seasonal cycles [17].…”

“…Self-learning iterative and time series methods are used more frequently. While time series-based methods and the hybrid NARX model are used especially for shorter forecasting horizons up to six years [160,161,179], SI are applied for longer lead times up to ten years [52,56,65,66,69,74,75,80,82,83,132,133,157]. Even longer lead times are achieved especially with SI and RP methods.…”

Hierarchical coastline detection in SAR images based on spectral‐textural features and global–local information

“…They are the most important and sensitive regions which encompass a rich ecosystem with a high diversity of species [1]. Coastal areas are exposed to erosion due to both human activities and natural phenomena [2, 3]. Coastal erosion appears as changes in the coastline; therefore, the coastline monitoring has a great significance for identifying the factors causing the coastal erosion [4, 5].…”