Sea Level Prediction Using Machine Learning

Rifat Tur,Erkin Tas,Ali Danandeh Mehr,Ali Torabi Haghighi

doi:10.3390/w13243566

Rifat Tur, Erkin Tas + Show 2 more

Open Access

https://doi.org/10.3390/w13243566

Copy DOI

Abstract

Sea level prediction is essential for the design of coastal structures and harbor operations. This study presents a methodology to predict sea level changes using sea level height and meteorological factor observations at a tide gauge in Antalya Harbor, Turkey. To this end, two different scenarios were established to explore the most feasible input combinations for sea level prediction. These scenarios use lagged sea level observations (SC1), and both lagged sea level and meteorological factor observations (SC2) as the input for predictive modeling. Cross-correlation analysis was conducted to determine the optimum input combination for each scenario. Then, several predictive models were developed using linear regressions (MLR) and adaptive neuro-fuzzy inference system (ANFIS) techniques. The performance of the developed models was evaluated in terms of root mean squared error (RMSE), mean absolute error (MAE), scatter index (SI), and Nash Sutcliffe Efficiency (NSE) indices. The results showed that adding meteorological factors as input parameters increases the performance accuracy of the MLR models up to 33% for short-term sea level predictions. Moreover, the results contributed a more precise understanding that ANFIS is superior to MLR for sea level prediction using SC1- and SC2-based input combinations.

Highlights

The changing climate has affected both global and regional meteorological conditions and sea level [1]
This study aimed to select the best input combinations, compare the linear-based and nonlinear-based models, and present a methodology with a flowchart that can be used for harbor operations for sea level predictions by practitioners
The adaptive neuro-fuzzy inference system (ANFIS) model produced an acceptable performance for SC1, whereas both ANFIS and models were developed using linear regressions (MLR) models produced accurate performance for SC2

Summary

Introduction

The changing climate has affected both global and regional meteorological conditions and sea level [1]. According to the 4th assessment report of the Intergovernmental Panel on Climate Change, global warming could lead to a global sea level rise of almost 60 cm by 2100 [2]. Such an increase would be nonuniform owing to the different meteorological and climatic conditions at different regions. From a coastal engineering point of view, sea level change may cause erosion and flooding problems. This situation poses a direct threat to individuals and coastal structures. Analyzing and predicting the changes in sea level are essential for sustainable design and operation of coastal structures

Objectives

Methods

Findings

Conclusion