Sea Level Variability and Predictions Using Artificial Neural Networks and Machine Learning Techniques in the Gulf of Guinea

Abstract

Abstract The rising sea level due to climate change poses a critical threat, particularly affecting vulnerable low-lying coastal areas such as the Gulf of Guinea (GoG). This impact necessitates precise sea level prediction models to guide planning and mitigation efforts for safeguarding coastal communities and ecosystems. This study presents a comprehensive analysis of mean sea level anomaly (MSLA) trends in the GoG between 1993 and 2020. The assessment covers three distinct periods (1993–2002, 2003–2012, and 2013–2020) and investigates connections between interannual sea level variability and large-scale oceanic and atmospheric forcings. Additionally, the performance of artificial neural networks (LSTM and MLPR) and machine learning techniques (MLR, GBM, and RFR) is evaluated to optimize sea level predictions. The findings reveal a consistent rise in MSLA linear trends across the basin, particularly pronounced in the north, with a total linear trend of 88 mm/year over the entire period. The highest decadal trend (38.7 mm/year) emerged during 2013–2020, and the most substantial percentage increment (100%) occurred in 2003–2012. Spatial variation in decadal sea-level trends was influenced by subbasin physical forcings. Strong interannual signals in the spatial sea level distribution were identified, linked to large-scale oceanic and atmospheric phenomena. Seasonal variations in sea level trends are attributed to seasonal changes in the forcing factors. Model evaluation indicates RFR and GBR as accurate methods, reproducing interannual sea level patterns with 97% and 96% accuracy, respectively. These findings contribute essential insights for effective coastal management and climate adaptation strategies in the GoG.