Figure - uploaded by Emine Tanir Kayikci
Content may be subject to copyright.
Source publication
Forecasting future sea levels is of great importance in terms of the conservation of coastal areas, monitoring and forecasting coastal ecosystems, and the maintenance and planning of coastal structures. In addition, highly accurate sea level forecasts allow adequate water management policies and coastal infrastructures to be developed. Today, many...
Context in source publication
Context 1
... best-fitting theoretical distribution function was then used to develop the CP model. The results of the model Tables 2 and 3 (( * ) denotes the best-fitting theoretical distribution). The Generalized Extreme Value and Logistic distributions are chosen as the most appropriate theoretical distributions for the Time and Sea Level Anomaly (SLA) variables since they have the lowest AIC and BIC values. ...Citations
... In general, there are two kinds of approaches for SLA prediction: single and hybrid. The single approach involves one processing technique for SLA prediction, such as autoregressive integrated moving average (ARIMA) (Zheng et al., 2022), artificial neural networks (ANNs) (Makarynskyy et al., 2004;Imani et al., 2014a), evolutionary support vector regressions and gene expression programming (Imani et al., 2014b), and the copula approach (Yavuzdogȃn and Tanır Kayıkci, 2021). ...
A novel approach using lag weighted-average least squares (Lag-WALS) is proposed to forecast the interannual sea level anomaly (SLA) in the South China Sea (SCS) using lagged equatorial Pacific El Niño–Southern Oscillation (ENSO)-related quantities. Through empirical orthogonal function (EOF) and wavelet coherence method, we first investigated the relationships between sea surface temperature (SST) and SLA (both steric sea level (SSL) and non-steric sea level (NSSL)) in the equatorial Pacific, and then explored their cross-correlations with the interannual SCS SLA. A robust alignment was found between the first spatiotemporal mode of EOF (i.e. EOF1 and first principal component (PC1)) from SLA/SSL and SST across the equatorial Pacific, both of which exhibited a typical ENSO horseshoe spatial pattern in EOF1. Good consistency between the SCS SLA and the SST/SLA/SSL PC1 was revealed, with the SCS SLA lagging behind the SST, SLA, and SSL by several months at most grid locations. In contrast, the NSSL exhibited large disparities with the SST PC1 or the interannual SCS SLA. The lag-WALS model performed better at the SCS boundaries than in the central region, with an average STD/MAE/Bias (RMSE/MAE/Bias) for internal (external) accuracies of 1.01/0.80/–0.002 cm (1.39/1.13/–0.08 cm), respectively. The altimetric-observed SLA seasonal patterns agreed with the Lag-WALS model-forecasted SLA. A similar situation applies to regionally-averaged SLA time series. These results underscore the ability of the Lag-WALS model to accurately forecast the SCS SLA at the interannual scale, which is crucial for early warning of abnormal sea level changes in the SCS.
... This increase, which is known to have devastating effects on coastal regions that host 60% of the world's population, emphasizes the importance of modeling sea level changes (Church and White, 2011;Ablain et al., 2017;Adebisi and Balogun, 2021). Sea level modeling is critical not only for understanding the effects of climate change on oceans and seas, but also for protecting coastal zones, ecosystems, and coastal infrastructure planning and maintenance (Nicholls and Cazenave, 2010;Kaloop et al., 2016;Yavuzdoğan and Kayıkçı, 2021). ...
Rising sea levels pose significant risks to coastal communities and ecosystems. Accurate modeling of sea level changes is crucial for effective environmental management and disaster mitigation. Machine learning methods are emerging as an important asset in improving sea level predictions and understanding the impacts of climate change. Especially, Long Short-Term Memory (LSTM) models have emerged as a powerful tool for sea level anomaly modelling, but there is an increasing need for more advanced models in this area. This study enhances existing methodologies by introducing a novel approach using an LSTM Auto-Encoder model, designed to compress input data into a lower-dimensional latent space before reconstructing it, thereby capturing complex temporal dependencies and anomalies effectively. We compared LSTM Auto-Encoder model performance with that of a Stacked LSTM network, which learns complex temporal patterns through multiple layers, and a traditional damped-persistence statistical model. Our results demonstrate that the LSTM Auto-Encoder model not only outperformed these models in predicting sea level anomalies across various lead times but also exhibited superior generalization capabilities across both satellite altimeter and in-situ data. These findings highlight the potential of the LSTM Auto-Encoder model as a powerful tool in coastal management and climate change studies, underscoring the critical role of advanced machine learning techniques in enhancing our predictive abilities and informing disaster preparedness strategies.
... This prediction model can directly forecast the time series data of tides per hour, and it achieved a high correlation coefficient even with 1 month's hourly tidal data. Yavuzdogan and Tanır Kayıkçı (2021) validated the feasibility of predicting sea level anomalies based on Copula functions using Black Sea tidal data. The experimental results showed that the Copula-based prediction model had a minimum correlation of 0.95 and a minimum root mean square error (RMSE) of 22 mm, demonstrating its effectiveness in predicting short-term sea level changes. ...
High-precision tidal forecasting plays a crucial role in providing reliable tidal information to coastal communities, ship operators, fishermen, and government agencies. Existing tidal prediction models, such as backpropagation neural networks (BPNN) and genetic algorithm-optimized BPNN (GA-BPNN), frequently difficulty in in achieving high precision because they rely solely on past tidal variations for real-time predictions. Signal-to-Noise Ratio (SNR) data have emerged as a valuable indicator closely related to real-time sea level changes due to the widespread adoption of Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) technology. In this paper, we propose a nowcasting tide level prediction method by adding SNR data to BPNN, i.e., Improved BPNN and Improved GA-BPNN, which predicts the next momentary tide level value by using the previous 15 tidal values and real-time SNR as input factors to BPNN. The results of 100-day, 200-day and 1-year tide prediction based on Astoria and Friday Harbor tide gauge stations show that the improved model prediction accuracies are better than the traditional model. Meanwhile, among the two improved models, Improved GA-BPNN has the higher prediction accuracy and can adapt to different time lengths of tide level prediction.
... Highly accurate SSHA forecasts will also be allowed to provide a sufficient basis for ship navigation, marine engineering, and industrial development, as well as fishery resources forecast (Solanki et al., 2015;Lumban-Gaol et al., 2017). Currently, the study on the SSHA assimilation and, thus, highly accurate SSHA prediction has been a hot topic in physical oceanography and meteorological sciences (Tanajura et al., 2015;Yavuzdogȃn and Tanır Kayıkci, 2020). ...
The sensitivity of the sea surface height anomaly (SSHA) forecasting on the accuracy of mesoscale eddies over the Kuroshio Extension region, which was determined by the conditional non-linear optimal perturbation (CNOP) method using a two-layer quasigeostrophic model, is evaluated by adopting multiply realistic marine datasets through an advanced particle filter assimilation method. It is shown that, if additional observations are preferentially assimilated to the sensitive area of mesoscale eddies identified by the CNOP, where the eddies present a clear high- to low-velocity gradient along the eddy rotation, the forecasting skill of the SSHA can be more significantly improved. It is also demonstrated that the forecasts of the SSHA in the region where the large-scale mean flow possesses much stronger barotropic and/or baroclinic instability tend to exhibit stronger sensitivity to the accuracy of the initial field in the sensitive area of mesoscale eddies. Therefore, more attention should be preferentially paid to the assimilation of the additional observations of the mesoscale eddies for the SSHA forecast in the region with a strong velocity shear of ocean circulation. The present study verifies the sensitivity on mesoscale eddies of SSHA forecasts derived by the two-layer quasigeostrophic model using multiply sets of realistic oceanic data, especially including observation and reanalysis data, which further additionally demonstrates the importance of targeted observations of mesoscale eddies to the SSHA forecast in the regions of strong velocity shear of ocean circulation and provides a more credible scientific basis for the field campaign of the targeted observations for mesoscale eddies associated with the SSHA forecasting.
... The results illustrated that the R between the observed value and the predicted value is as high as 0.87, which proves the reliability of the combined least squares-neural network method in the short-term forecast of coastal sea level change (Zhao, Fan and Mu 2019). Yavuzdoğan et al. verified the feasibility of the copula-based prediction model in predicting short-term changes in sea level based on the weekly mean sea level data from 1993 to 2011, and the results indicated that the copula method had a minimum R of 0.95 and a minimum RMSE of 22 mm (Yavuzdoğan and Tanır Kayıkçı 2021). The previous research time benchmarks mainly focus on half-day, daily, weekly, and monthly mean values. ...
Multi-satellite and Multi-Signal-to-Noise Ratio (SNR) types provide more basic data for the monitoring of sea level height by Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) technology. Few studies predict sea level height with high temporal resolution. This study proposes a theory based on GNSS-IR technology and Auto Regressive Integrated Moving Average (ARIMA) model. Taking the MAYG station as an example, the process of sea level height prediction and the determination of the best prediction scheme are shown. First, the sea level height monitored by the GNSS-IR technology is averaged hour by hour as the sea level height at the instantaneous moment. A linear interpolation method is used to compensate for the missing sea level time series. Then, the number of days to participate in the prediction of GNSS-IR sea level height and its forecast are selected for the experiment of predicting tide level. In the tide level prediction study from DOY125 to DOY153, the results of predicting the future 24 h, 48 h, and 72 h from one tide level period (29 days) illustrate that the accuracy of predicting the sea level height at 24 h is the best (R: 0.967, RMSE: 0.270 m, ME: −0.151 m), and the predicted tide level is highly consistent with the tide level measured at the tide gauge station. In addition, experiments reveal that the prediction accuracy gradually decreases with the increase of prediction time. This study verifies the feasibility of the hour-by-hour sea level prediction theory combined with the GNSS-IR technology and the ARIMA model. It proves that the theory can carry out continuous prediction of sea level, further promoting the breakthrough and transformation of GNSS-IR technology to the application level.
Forecasting sea level is critical for coastal structure building and port operations. There are, however, challenges in making these predictions, resulting from the complicated processes at various periods. This study discussed the continual development of the application and forecasting approaches for sea level rise, in standard and advanced modeling versions. To date, the tide gauge and satellite altimetry are the commonly used approaches for sea level measurement. Tide gauges are mostly deficient in typical offshore circumstances; but however, this may be compensated for with satellite altimetry, a complementing technique. With technological improvement, sea level measurement may be forecasted using a variety of computer science approaches known as artificial intelligence, including machine learning and deep learning; capable of extracting information and formulating relationships from the given dataset. Its potential and extensive advantages led to a sharp growth in its recognition among hydrologists. The most successful techniques for enhancing these approaches include hybridization, ensemble modeling, data decomposition, and algorithm optimization. These advanced techniques are a prominent study area and a viable strategy for determining intelligent forecasts of sea level rise with sufficient lead time. For improved performance, the modeling requires incorporating numerous input parameters, such as precipitation, wind direction, ocean current, and sea surface temperature; for better representing the process, thus reducing forecast error and uncertainty. Deep learning is more effective and enhances existing machine learning models for forecasting future sea level rise due to its automatic feature extraction and memory-storing capability.
Design/methodology/approach – The literature review was used in this study to extract the Public-Private Partnerships (PPPs) Key Performance Indicators (KPIs). Experts’ judgment and interviews, as well as questionnaires, were designed to obtain data. Copula Bayesian network (CBN) has been selected to achieve the research purpose. CBN is one of the most potent tools in statistics for analyzing the causal relationship of different elements and considering their quantitive impact on each other. By utilizing this technique and using Python as one of the best programming languages, this research used machine learning methods, SHAP and XGBoost, to optimize the network.
Purpose - Being an efficient mechanism for the value of money, Public-private partnership (PPP) is one of the most prominent approaches for infrastructure construction. Hence, many controversies about the performance effectiveness of these delivery systems have been debated. This research aims to develop a novel performance management perspective by revealing the causal effect of key performance indicators (KPIs) on PPP infrastructures.
Findings - The sensitivity analysis of the KPIs verified the causation importance in PPPs performance management. This study determined the causal structure of KPIs in PPP projects, assessed each indicator's priority to performance, and found 7 of them as a critical cluster to optimize the network. These KPIs include innovation for financing, feasibility study, macro-environment impact, appropriate financing option, risk identification, allocation, sharing, and transfer, finance infrastructure, and compliance with the legal and regulatory framework.
Practical implications – Identifying the most scenic indicators helps the private sector to allocate the limited resources more rationally and concentrate on the most influential parts of the project. It also provides the KPIs’ critical cluster that should be controlled and monitored closely by PPP project managers. Additionally, the public sector can evaluate the performance of the private sector more accurately. Finally, this research provides a comprehensive causal insight into the PPPs’ performance management that can be used to develop management systems in future research.
Originality/value – For the first time, this research proposes a model to determine the causal structure of KPIs in PPPs and indicate the importance of this insight. The developed innovative model identifies the KPIs' behavior and takes a non-linear approach based on CBN and machine learning methods while providing valuable information for construction and performance managers to allocate resources more efficiently.
Sea level rise is a key feature in a warmer world and its impact can be seen globally. Assessing climate change-induced sea level rise, therefore, is urgently needed particularly in small island nations, where the threats of sea level rise are immediate, but the level of preparedness is low. Here, we propose a stochastic simulator to link changes in Mean Annual Temperature (MAT) to Mean Annual Sea Level (MASEL) at the local scale. This is through what-if scenarios that are developed based on the association between local temperature and sea level. The model can provide a basis for a bottom-up impact assessment by addressing limitations of applying large-scale projections in small islands and facilitating the accessibility of the impact assessment to stakeholders. For this purpose, we decompose the MAT and MASEL signals into their linear trend and autocorrelation components as well as independent and identically distributed residual terms. We further explore the association between trend and residual terms of MAT and MASEL. If such dependencies exist, scenarios of sea level can be synthesized based on the trend and residual terms of temperature. We use linear regression to link trends of MAT and MASEL, and copulas to formulate dependencies between residuals. This allows stochastic sampling of MASEL conditioned to trend and random variability in MAT. This framework is used for retrospective and prospective simulations of MASEL in Nouméa, the capital city of New Caledonia, the Pacific. We set up six different model configurations for developing the stochastic sampler, each including various parametric options. By selecting the best setup from each configuration, we provide a multi-model stochastic projection of MASEL, assuming the persistence in current long-term trend in MAT and MASEL. We demonstrate how such simulations can be used for a risk-based impact assessments and discuss sources of uncertainty in future projections.
The accumulated remote sensing data of altimeters and scatterometers have provided new opportunities for ocean state forecasting and have improved our knowledge of ocean-atmosphere exchanges. Studies on multivariate, multistep, spatiotemporal sequence forecasts of sea level anomalies (SLA) for different modalities, however, remain problematic. In this paper, we present a novel hybrid and multivariate deep neural network, named HMnet3, which can be used for SLA forecasting in the South China Sea (SCS). First, a spatiotemporal sequence forecasting network is trained by an improved convolutional long short-term memory (ConvLSTM) network using a channelwise attention mechanism and multivariate data from 1993 to 2015. Then, a time series forecasting network is trained by an improved long short-term memory (LSTM) network, which is realized by ensemble empirical mode decomposition (EEMD). Finally, the two networks are combined by a successive correction method to produce SLA forecasts for lead times of up to 15 days, with a special focus on the open sea and coastal regions of the SCS. During the testing period of 2016-2018, the performance of HMnet3 with sea surface temperature anomaly (SSTA), wind speed anomaly (SPDA) and SLA data is much better than those of state-of-the-art dynamic and statistical (ConvLSTM, persistence and climatology) forecast models. Stricter testbeds for trial simulation experiments with real-time datasets are investigated, where the eddy classification metrics of HMnet3 are favorable for all properties, especially for those of small-scale eddies.
