Assessment of spatio-temporal empirical forecasting performance of future shoreline positions

Keywords: Coastal Erosion, Vulnerability, Digital Shoreline Analysis System, Forecasting, Bangladesh
Session Type: Virtual Poster Abstract
Day: Friday
Session Start / End Time: 2/25/2022 05:20 PM (Eastern Time (US & Canada)) - 2/25/2022 06:40 PM (Eastern Time (US & Canada))
Room: Virtual 40

Abstract

Coastlines are highly dynamic in nature, where large changes are expected in the future due to anthropogenic and climatic influences. The prediction of future shoreline positions is of great importance in better planning and management of coastal areas. With an aim to assess different methods of predictions, this study investigates the performance of future shoreline position predictions by quantifying how prediction performance varies depending on the time depths of input historical shoreline data and the time horizons of predicted shorelines. The multi-temporal Landsat imagery from 1988 to 2021 were used to quantify the rate of shoreline movement for different time period. The End Point Rate (EPR), Linear Regression Rate (LRR), Weighted Linear Regression (WLR), and Kalman filtering were used to predict future shoreline positions. The Root Mean Squared Error (RMSE) were used to assess the prediction accuracy. Our results revealed that higher the number of shorelines used in calculating and predicting shoreline is better the performance. The prediction accuracy is much higher for the immediate years compared to the distant future. Our results also suggest that the forecast performance varied over space. Among the regions, the prediction performance was better for the north and south regions compared to central region. Though the location of this study is coastal Bangladesh, this is a methodological innovation with potential for forecasting applications to other deltas and vulnerable shorelines globally. While empirical results are specific to the project’s study area, results can inform the region’s shoreline forecasting ability and associated mitigation and adaptation strategies.