A deep learning method to automatically measure tide and surge in coastal areas

Advances in machine learning and deep learning approaches have drawn substantial interest across diverse research domains, including environmental studies. These innovative techniques have transformed the approaches to measuring marine parameters by facilitating automated and remote data collection. This study focuses on the implementation of a deep learning model to automatically assess tide and surge, aiming for precise outcomes through the analysis of surveillance camera imagery. Utilizing the Inception v3 structure, the deep learning model was applied to predict tide and storm surge from surveillance cameras strategically positioned in two distinct coastal regions, namely Santa Lucia in southeastern Sicily and Lignano Sabbiadoro in Friuli Venezia Giulia, Italy. The deep learning model is based on classification methods to assign a value of water level to a given frame. This approach is particularly advantageous in scenarios where traditional tide sensors face inaccessibility or are distant from measurement points, especially during extreme events demanding accurate surge measurements. The dataset used for the training and validation of the deep learning model covers the entire tide values that could be observed in the study areas. Predictions of the deep learning model were compared with tide gauge values in order to assess the system accuracy. The conducted experiments demonstrate the efficiency of the model in remotely and effectively measuring tide and surge, achieving an accuracy exceeding 90% while maintaining a loss value below 1 for the deep learning model. These findings underscore its potential to fill the data collection gap in challenging coastal environments, offering valuable insights for coastal management and hazard assessment. This study makes an important contribution to the rapidly growing field of remote sensing and machine learning applications in environmental monitoring, facilitating greater comprehension and decision-making in coastal areas.