Prediction of coastal vulnerability with machine learning techniques, Mediterranean coast of Tangier-Tetouan, Morocco

Abstract

Coastal sites have been recognized to be among the most productive and dynamic regions. Nevertheless, these areas have been disrupted due to the rapid expansion of human interventions and climate change. Coastal ecosystems are becoming more endangered by the probable adverse effects of climate change as revealed by IPCC panel. The main objective of this paper is to integrate Machine Learning (ML) models to spatially predict coastal vulnerability along the Mediterranean coast of (Tangier-Tetouan), Morocco. Different models including Artificial neural network (ANN), Decision Tree (DT), logistic regression (LR), random forest (RF), and Support vector machine (SVM) are used on 10033 points to represent the vulnerability in terms of (high, moderate, and low), determined by the coastal vulnerability index (CVI). Eight coastal vulnerability predictors (Slope, Elevation, Tidal range, Sea level rise, maximum wave height, Natural habitat, Geomorphology, and Shoreline change rate) were considered as input for each model. The obtained dataset was split into two parts: 30% for testing and 70% for training. The presented models were examined on various parameters, such as accuracy, recall, F1 score, root mean square error (RMSE), and kappa index. The findings show that accuracy and Kappa statistics for RF and DT and SVM ranged from (92–99%) which indicates a better performance than other proposed models. The approach is considered an appropriate tool for predicting and mapping coastal vulnerability and can make significant contributions to the successful management of coastal zones. Additionally, it can aid in the development of public interest and promote the planning, creation, and execution of adaption measures. The prediction was applied over (∼124 km) of the shoreline. Results showed that about 19.95% (∼27.73 km) of the shoreline is highly vulnerable, while 20.92% (∼25.95 km) is moderately vulnerable and 59.1% (∼73.32 km) presents a low vulnerability.