Abstract:The sea level observations from satellite altimetry are characterised by a sparse spatial and temporal coverage. For this reason, along-track data are routinely interpolated into daily grids. These grids are strongly smoothed in time and space and are generated using an optimal interpolation routine requiring several pre-processing steps and covariance characterisation. In this study, we assess the potential of Random Forest Regression to estimate daily sea level anomalies. Along-track sea level data from 2004… Show more
“…RFR is highly effective in handling noise, capturing complex relationships, and generating accurate predictions by leveraging the collective power of multiple trees 72 . Furthermore, the application of RFR for sea level prediction has been extensively documented in the literature 73 – 75 . Figure 11 The architecture of the Random Forest Regression (RFR) Model.…”
The rising sea levels due to climate change are a significant concern, particularly for vulnerable, low-lying coastal regions like the Gulf of Guinea (GoG). To effectively address this issue, it is crucial to gain a comprehensive understanding of historical sea level variability, and the influencing factors, and develop a reliable modeling system for future projections. This knowledge is essential for informed planning and mitigation strategies aimed at protecting coastal communities and ecosystems. This study presents a comprehensive analysis of mean sea level anomaly (MSLA) trends in the GoG between 1993 and 2020, covering three distinct periods (1993–2002, 2003–2012, and 2013–2020). It investigates the connections between interannual sea level variability and large-scale oceanic and atmospheric forcings. Furthermore, the study evaluates the performance of supervised machine learning techniques to optimize sea level modeling. The findings reveal a consistent rise in MSLA linear trends across the basin, particularly pronounced in the northern region, with a total linear trend of 88 mm over the entire period. The highest decadal trend (38.7 mm) emerged during 2013–2020, with the most substantial percentage increment (100%) occurring 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. The evaluation of supervised learning modeling methods indicates that Random Forest Regression and Gradient Boosting Machines are the most accurate, reproducing interannual sea level patterns in the GoG with 97% and 96% accuracy. These models could be used to derive regional sea level projections via downscaling of climate models. These findings provide essential insights for effective coastal management and climate adaptation strategies in the GoG.
“…RFR is highly effective in handling noise, capturing complex relationships, and generating accurate predictions by leveraging the collective power of multiple trees 72 . Furthermore, the application of RFR for sea level prediction has been extensively documented in the literature 73 – 75 . Figure 11 The architecture of the Random Forest Regression (RFR) Model.…”
The rising sea levels due to climate change are a significant concern, particularly for vulnerable, low-lying coastal regions like the Gulf of Guinea (GoG). To effectively address this issue, it is crucial to gain a comprehensive understanding of historical sea level variability, and the influencing factors, and develop a reliable modeling system for future projections. This knowledge is essential for informed planning and mitigation strategies aimed at protecting coastal communities and ecosystems. This study presents a comprehensive analysis of mean sea level anomaly (MSLA) trends in the GoG between 1993 and 2020, covering three distinct periods (1993–2002, 2003–2012, and 2013–2020). It investigates the connections between interannual sea level variability and large-scale oceanic and atmospheric forcings. Furthermore, the study evaluates the performance of supervised machine learning techniques to optimize sea level modeling. The findings reveal a consistent rise in MSLA linear trends across the basin, particularly pronounced in the northern region, with a total linear trend of 88 mm over the entire period. The highest decadal trend (38.7 mm) emerged during 2013–2020, with the most substantial percentage increment (100%) occurring 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. The evaluation of supervised learning modeling methods indicates that Random Forest Regression and Gradient Boosting Machines are the most accurate, reproducing interannual sea level patterns in the GoG with 97% and 96% accuracy. These models could be used to derive regional sea level projections via downscaling of climate models. These findings provide essential insights for effective coastal management and climate adaptation strategies in the GoG.
“…RFR is highly effective in handling noise, capturing complex relationships, and generating accurate predictions by leveraging the collective power of multiple trees (Breiman, 2001). Furthermore, the application of RFR for sea level prediction has been extensively documented in the literature (Hughes et al, 2022;Bellinghausen et al, 2023;Passaro et al, 2023).…”
Section: Random Forrest Regression (Rfr)mentioning
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.
We have analyzed the relationship between wind variability and sea level anomalies (SLA) on the Southwestern Atlantic Continental Shelf, focusing on sub-annual temporal scales. For this, we tested the capability of gridded altimetry to represent wind-driven SLA and compared results using an oceanographic model and tide gauge data. The present study used coherence analysis to analyze frequencies for which SLA and wind stress are coherent. The altimetry-SLA were found to have less energy below the three-month period compared to the model SLA. The coherence of along-shore wind stress and altimetry SLA was only significant for > 50 days (d), while the model SLA showed significant agreement in all periods considered, 20 d to annual. We further showed that geostrophic velocities on the continental shelf agreed significantly with SLA for > 50 d. As a result of an Empirical Orthogonal Function (EOF) analysis, we found that the second mode is highly coherent with the along-shore wind stress and accounts for 18.1% and 10.7% of variability in the model and altimetry sea level anomalies, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
