Sea Surface Temperature Prediction Research Articles

The First Operational Version of Taiwan Central Weather Bureau’s One-Tier Global Atmosphere–Ocean Coupled Forecast System for Seasonal Prediction

Abstract The first version of the Taiwan Central Weather Bureau one-tier (TCWB1T) fully coupled global atmospheric and oceanic modeling forecast system had been developed and implemented as a routine operation for seasonal prediction at Central Weather Bureau (CWB) in 2017, with a minor revision in 2020. Based on NCEP CFSv1, the global atmospheric model in NCEP CFSv1 was replaced by CWB’s atmospheric global spectral model (GSM) and coupled with the GFDL MOM3. Several parameters have been tested and tuned in the CWB atmospheric GSM, achieving an optimal configuration with better sea surface temperature (SST) predictions for integration more than one year. Using NCEP CFSR as the initial condition, TCWB1T conducted hindcasts from 1982 to 2011 and forecasts from 2012 to 2019 to analyze its performance. The results of these hindcasts and forecasts show that the TCWB1T can make useful predictions as verified against the observations of OISST, ERSST, CFSR, and GPCP based on the methods of EOF, RMSE, anomaly correlation, ranked probability skill score (RPSS), reliability diagram (RD), and relative operating characteristics (ROCs). TCWB1T also has the same level of skill scores as NCEP CFSv2 and/or the ECMWF fifth-generation seasonal forecast system (SEAS5), based on EOF, anomaly pattern correlation, climatological bias, RMSE, temporal correlation, and anomaly correlation percentage of forecast skill. TCWB1T shows forecast skill that is better in winter than in summer. Overall, it indicates that TCWB1T can be used for seasonal ENSO predictions.

Sea Surface Temperature Prediction in China Sea Based on SAM-LSTM Approach

Sea Surface Temperature (SST), a critical environmental element in the ocean, significantly impacts the global atmosphere-ocean energy balance and holds the potential to trigger severe weather like droughts, floods, and El Niño events. Therefore, the prediction of future SST dynamics is crucial to identifying these extreme events and mitigating the damage they caused. In this study, we introduce a time series prediction method based on the Self-Attention Mechanism-Long Short-Term Memory (SAM-LSTM) model. In addition, the historical time-series satellite data of SST anomaly (SSTA) is used instead of SST itself considering that the fluctuations of SST are very small compared to their absolute magnitudes. The Seasonal-Trend decomposition using Loess (STL) method is adopted to decompose the complex non-linear SSTA time series into trend components, seasonal components, and residual components. Then, the deseasonalized time series data at 6 locations in the Bohai Sea are used to train and valid the developed SAM-LSTM model. After that, the validated models are applied to the Yellow Sea, East China Sea, and South China Sea. The experimental results show that the combination of STL time series decomposition and SAM-LSTM can achieve high-precision prediction of daily SSTA than LSTM. This suggests that the methodology used in this paper has a good application for short-term daily SST prediction.

Influence of the solar penetration depth and heat-fluxes on the sea surface temperature using an ocean mixed layer model

Solar penetration depth is a major factor in modulating the Sea Surface Temperature (SST) and hence influences the air-sea interface processes. This study investigates the influence of solar penetration depth and heat-fluxes on the SST at three RAMA (Research Moored Array for African-Asian-Australian Monsoon Analysis and Prediction) buoy locations (along 90°E at 15°N, 12°N, and 8°N) in the Bay of Bengal (BoB) using the One-Dimensional Price-Weller-Pinkel (1D-PWP) model. The results show that SST has strong dependence on the solar penetration depths with the shortwave component of solar insolation outweighing its longwave component. We found that spatio-temporally varying penetration depths refine the simulated SST, when compared against constant penetration depths. These spatio-temporally varying penetration depths (ranging from 10 to 75 m for the shortwave component; with higher values during monsoon) can be attributed to spatio-temporally changing biological parameters, wind, precipitation, and suspended particulate matter. Upon examination, an antiphase relationship between the penetration depths and total chlorophyll, total primary production, & total phytoplankton was found. Upon including the effect of horizontal advection and vertical entrainment in the 1D-PWP model results, the SST predictions improved albeit by a small amount. Furthermore, the effects of increased heat-fluxes, under the different Representative Concentration Pathway (RCP) equivalent scenarios, coupled with varying penetration depths were estimated. It was found that for the spatio-temporally varying penetration depths, the mean (maximum) increment was 0.52 °C (0.92 °C) under the highest emission scenario, i.e., RCP8.5, across all the locations. The results of the study can potentially be used further for 3D ocean modeling studies, and the characterization of air-sea interaction during monsoon and cyclones in the BoB.

Impact of physical and attention mechanisms on U-Net for SST forecasting

Sea surface temperature (SST) prediction is a subject of great significance to the marine environment and human society. Changes in SST not only impact marine ecosystems and fishery resources but also trigger extreme weather events and disastrous consequences. Therefore, the precise prediction of SST is essential to avoiding these problems. Although numerous data-driven SST prediction models have emerged in recent years, these models are characterized by a lack of physical mechanisms related to sea temperature changes as well as insufficient generalization capabilities and interpretability. In our work, attempts were made to integrate physics-related convection phenomena into deep learning models, and traditional deep learning models were improved by incorporating time and space attention modules. The results of a series of experiments showed that the incorporation of physical mechanisms enhanced the performance of data-driven models. Furthermore, attention mechanisms were similarly helpful, of which temporal attention proved to be more important. The modules proposed in this work also improved the baseline model’s accuracy by 22%. In addition, seven-day SST predictions were carried out for the world’s five major fishing grounds. The results demonstrated that the application of transfer learning strategies yielded superior performance, further improving prediction accuracy by 1%–5%.

Asymmetric Influences of ENSO Phases on the Predictability of North Pacific Sea Surface Temperature

AbstractThe North Pacific sea surface temperature (SST) has a profound climatic influence. The El Niño‐Southern Oscillation (ENSO) significantly impacts the North Pacific SST; however, the influence of the distinct phases of ENSO on SST predictability remains unclear. To overcome the model limitations, this study assessed SST predictability under diverse ENSO phases using reanalysis. The predictability limit of the North Pacific SST under La Niña (8.4 months) is longer than that under Neutral (5.9 months) and El Niño (5.5 months) conditions, which unveils asymmetry. This asymmetry mirrors contemporary multimodal prediction skills. Error growth dynamics reveal La Niña's robust signal strength with a slow error growth rate, in contrast to El Niño's weaker signal and faster error growth. There exhibits intermediate signal strength and elevated error growth in Neutral condition. Physically, predictability signal strength aligns with SST variability, whereas the error growth rate correlates with atmospheric‐ocean heating anomalies. La Niña, which induces positive heating anomalies, minimizes the impact of atmospheric noise, resulting in lower error growth. The result is beneficial for improving North Pacific SST predictions.

A Simple Statistical Postprocessing Scheme for Enhancing the Skill of Seasonal SST Predictions in the Tropics

Abstract Seasonal prediction systems are subject to systematic errors, including those introduced during the initialization procedure, that may degrade the forecast skill. Here we use a novel statistical postprocessing correction scheme that is based on canonical correlation analysis (CCA) to relate errors in ocean temperature arising during initialization with errors in the predicted sea surface temperature fields at 1–12-month lead time. In addition, the scheme uses CCA of simultaneous SST fields from the prediction and corresponding observations to correct pattern errors. Finally, simple scaling is used to mitigate systematic location and phasing errors as a function of lead time and calendar month. Applying this scheme to an ensemble of seven seasonal prediction models suggests that moderate improvement of prediction skill is achievable in the tropical Atlantic and, to a lesser extent, in the tropical Pacific and Indian Ocean. The scheme possesses several adjustable parameters, including the number of CCA modes retained, and the regions of the left and right CCA patterns. These parameters are selected using a simple tuning procedure based on the average of four skill metrics. The results of the present study indicate that errors in ocean temperature fields due to imperfect initialization and SST variability errors can have a sizable negative impact on SST prediction skill. Further development of prediction systems may be able to remedy these impacts to some extent. Significance Statement The prediction of year-to-year climate variability patterns, such as El Niño, offers potential benefits to society by aiding mitigation and adaptation efforts. Current prediction systems, however, may still have substantial room for improvement due to systematic model errors and due to imperfect initialization of the oceanic state at the start of predictions. Here we develop a statistical correction scheme to improve prediction skill after forecasts have been completed. The scheme shows some moderate success in improving the skill for predicting El Niño and similar climate patterns in seven prediction systems. Our results not only indicate a potential for improving prediction skill after the fact but also point to the importance of improving the way prediction systems are initialized.

Prediction of Sea Surface Temperature Using U-Net Based Model

Sea surface temperature (SST) is a key parameter in ocean hydrology. Currently, existing SST prediction methods fail to fully utilize the potential spatial correlation between variables. To address this challenge, we propose a spatiotenporal UNet (ST-UNet) model based on the UNet model. In particular, in the encoding phase of ST-UNet, we use parallel convolution with different kernel sizes to efficiently extract spatial features, and use ConvLSTM to capture temporal features based on the utilization of spatial features. Atrous Spatial Pyramid Pooling (ASPP) module is placed at the bottleneck of the network to further incorporate the multi-scale features, allowing the spatial features to be fully utilized. The final prediction is then generated in the decoding stage using parallel convolution with different kernel sizes similar to the encoding stage. We conducted a series of experiments on the Bohai Sea and Yellow Sea SST data set, as well as the South China Sea SST data set, using SST data from the past 35 days to predict SST data for 1, 3, and 7 days in the future. The model was trained using data spanning from 2010 to 2021, with data from 2022 being utilized to assess the model’s predictive performance. The experimental results show that the model proposed in this research paper achieves excellent results at different prediction scales in both sea areas, and the model consistently outperforms other methods. Specifically, in the Bohai Sea and Yellow Sea sea areas, when the prediction scales are 1, 3, and 7 days, the MAE of ST-UNet outperforms the best results of the other three compared models by 17%, 12%, and 2%, and the MSE by 16%, 18%, and 9%, respectively. In the South China Sea, when the prediction ranges are 1, 3, and 7 days, the MAE of ST-UNet is 27%, 18%, and 3% higher than the best of the other three compared models, and the MSE is 46%, 39%, and 16% higher, respectively. Our results highlight the effectiveness of the ST-UNet model in capturing spatial correlations and accurately predicting SST. The proposed model is expected to improve marine hydrographic studies.

Machine learning methods to predict sea surface temperature and marine heatwave occurrence: a case study of the Mediterranean Sea

Abstract. Marine heatwaves (MHWs) have significant social and ecological impacts, necessitating the prediction of these extreme events to prevent and mitigate their negative consequences and provide valuable information to decision-makers about MHW-related risks. In this study, machine learning (ML) techniques are applied to predict sea surface temperature (SST) time series and marine heatwaves in 16 regions of the Mediterranean Sea. ML algorithms, including the random forest (RForest), long short-term memory (LSTM), and convolutional neural network (CNN), are used to create competitive predictive tools for SST. The ML models are designed to forecast SST and MHWs up to 7 d ahead. For each region, we performed 15 different experiments for ML techniques, progressively sliding the training and the testing period window of 4 years from 1981 to 2017. Alongside SST, other relevant atmospheric variables are utilized as potential predictors of MHWs. Datasets from the European Space Agency Climate Change Initiative (ESA CCI SST) v2.1 and the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA5 reanalysis from 1981 to 2021 are used to train and test the ML techniques. For each area, the results show that all the ML methods performed with minimum root mean square errors (RMSEs) of about 0.1 °C at a 1 d lead time and maximum values of about 0.8 °C at a 7 d lead time. In all regions, both the RForest and LSTM consistently outperformed the CNN model across all lead times. LSTM has the highest predictive skill in 11 regions at all lead times. Importantly, the ML techniques show results similar to the dynamical Copernicus Mediterranean Forecasting System (MedFS) for both SST and MHW forecasts, especially in the early forecast days. For MHW forecasting, ML methods compare favorably with MedFS up to 3 d lead time in 14 regions, while MedFS shows superior skill at 5 d lead time in 9 out of 16 regions. All methods predict the occurrence of MHWs with a confidence level greater than 50 % in each region. Additionally, the study highlights the importance of incoming solar radiation as a significant predictor of SST variability along with SST itself.

On the Role of Indian Ocean SST in Influencing the Differences in Atmospheric Variability Between 2020–2021 and 2021–2022 La Niña Boreal Winters

AbstractThe difference in observed atmospheric anomalies over the Northern Hemisphere winter between 2021–22 and 2020–21 La Niña years indicated a tripole pattern consisting of a Japan cyclone, a Bering Sea anticyclone, and a cyclone over the North American continent. This feature, however, was not replicated in the North American Multi‐Model Ensemble (NMME) forecasts. A set of model sensitivity experiments was performed to better understand the cause of this discrepancy. The results revealed the possible role of the influence of sea surface temperature (SST) anomalies, particularly over the Indian Ocean, on the observed circulation differences that was further modulated by internal atmospheric variability. The failure in predicting circulation changes in NMME was next attributed to the errors in SST predictions over the Indian Ocean and highlights the need for improvements in SST forecasts over this region.

Prediction of the sea surface temperature in Perhentian Islands by EMD-LSTM model

The increase in the sea surface temperature (SST) is currently an important factor in the decline of coral reef ecosystems worldwide, and SST prediction has always been an important research direction in operational oceanography. This paper collects and analyses the buoy data deployed at Malaysian Perhentian islands and combines CRW data to develop coral bleaching warning products for Malaysian Perhentian islands. The Long Short-Term Memory Network(LSTM) and Empirical Mode Decomposition(EMD)-LSTM methods are used to research the SST prediction, and the differences between the two prediction methods were compared. The research results show that both the LSTM prediction model and the EMD-LSTM prediction model can accurately predict SST, with almost all prediction errors at 0.11°C and 0.01°C, respectively.

Prediction of seasonal sea surface temperature based on temperature and salinity of subsurface ocean using machine learning

AbstractThe sea surface temperature (SST) is not only a crucial external factor in the evolution of the atmosphere, but also a primary factor and premonition signal used in climate prediction. It is challenging to obtain a precise SST for generating accurate initial and boundary conditions in numerical models. This study employs a machine learning approach, that is, a convolutional neural network (CNN) algorithm, to predict SST on a seasonal scale. In particular, the subsurface ocean temperature (OT) and ocean salinity (OS) at depths of 5.02, 15.08, 25.16, 35.28, 45.45 and 76.55 m were used as training factors in developing a CNN prediction model. The results indicate that subsurface OT and OS can persist for 6 months or longer, with a maximum persistence of up to 12 months. Using the CNN prediction model, the SST can be reliably predicted 6 months in advance in most cases. The predicted SST has a mean bias of approximately 0–0.8 K on the globe. The bias is small (below 0.5 K) in the open ocean. The root mean square errors (RMSEs) of hindcasting for Interdecadal Pacific Oscillation, North Atlantic Oscillation (NAO) and Atlantic Multidecadal Oscillation indices are all less than 1.0 K. Specifically, the RMSE for El Niño prediction is less than 0.5 K. This study provides a viable method for establishing initial and boundary conditions for climate prediction.

Time series prediction of sea surface temperature based on BiLSTM model with attention mechanism

With the advancement of technology, ocean observation techniques have become increasingly prevalent in estimating marine variables such as Sea Surface Temperature (SST). This progress has led to a substantial surge in the volume of marine data. Presently, the abundance of available data presents a remarkable opportunity for training predictive models. The prediction of SST poses a challenge due to its temporal-dependent structure and multi-level seasonality. In this study, we propose a deep learning approach that combines the Bidirectional Long Short-Term Memory (BiLSTM) model with the attention mechanism to forecast SST. By leveraging the BiLSTM's ability to effectively capture long-term dependencies through both forward and backward LSTM processing, the attention mechanism accentuates salient features, thereby enhancing the model's evaluation accuracy.To evaluate the effectiveness of the Attention-BiLSTM model in predicting SST, we conducted a case study in the Moroccan Sea, focusing on four distinct regions. We compared the performance of the Attention-BiLSTM model against alternative models such as LSTM, Attention-BiGRU, XGBoost, Random Forest (RF), Support Vector Regression (SVR), and Transformers in forecasting the SST time series.The experimental results unequivocally demonstrate that the Attention-BiLSTM model achieves significantly superior prediction outcomes and is a good candidate for deployment in the field.

An Interpretable Deep Learning Approach for Detecting Marine Heatwaves Patterns

Marine heatwaves (MHWs) refer to a phenomenon where the sea surface temperature is significantly higher than the historical average for that region over a period, which is typically a result of the combined effects of climate change and local meteorological conditions, thereby potentially leading to alterations in marine ecosystems and an increased incidence of extreme weather events. MHWs have significant impacts on the marine environment, ecosystems, and economic livelihoods. In recent years, global warming has intensified MHWs, and research on MHWs has rapidly developed into an important research frontier. With the development of deep learning models, they have demonstrated remarkable performance in predicting sea surface temperature, which is instrumental in identifying and anticipating marine heatwaves (MHWs). However, the complexity of deep learning models makes it difficult for users to understand how the models make predictions, posing a challenge for scientists and decision-makers who rely on interpretable results to manage the risks associated with MHWs. In this study, we propose an interpretable model for discovering MHWs. We first input variables that are relevant to the occurrence of MHWs into an LSTM model and use a posteriori explanation method called Expected Gradients to represent the degree to which different variables affect the prediction results. Additionally, we decompose the LSTM model to examine the information flow within the model. Our method can be used to understand which features the deep learning model focuses on and how these features affect the model’s predictions. From the experimental results, this study provides a new perspective for understanding the causes of MHWs and demonstrates the prospect of future artificial intelligence-assisted scientific discovery.

Sea Surface Temperature and Marine Heat Wave Predictions in the South China Sea: A 3D U-Net Deep Learning Model Integrating Multi-Source Data

Accurate sea surface temperature (SST) prediction is vital for disaster prevention, ocean circulation, and climate change. Traditional SST prediction methods, predominantly reliant on time-intensive numerical models, face challenges in terms of speed and efficiency. In this study, we developed a novel deep learning approach using a 3D U-Net structure with multi-source data to forecast SST in the South China Sea (SCS). SST, sea surface height anomaly (SSHA), and sea surface wind (SSW) were used as input variables. Compared with the convolutional long short-term memory (ConvLSTM) model, the 3D U-Net model achieved more accurate predictions at all lead times (from 1 to 30 days) and performed better in different seasons. Spatially, the 3D U-Net model’s SST predictions exhibited low errors (RMSE < 0.5 °C) and high correlation (R > 0.9) across most of the SCS. The spatially averaged time series of SST, both predicted by the 3D U-Net and observed in 2021, showed remarkable consistency. A noteworthy application of the 3D U-Net model in this research was the successful detection of marine heat wave (MHW) events in the SCS in 2021. The model accurately captured the occurrence frequency, total duration, average duration, and average cumulative intensity of MHW events, aligning closely with the observed data. Sensitive experiments showed that SSHA and SSW have significant impacts on the prediction of the 3D U-Net model, which can improve the accuracy and play different roles in different forecast periods. The combination of the 3D U-Net model with multi-source sea surface variables, not only rapidly predicted SST in the SCS but also presented a novel method for forecasting MHW events, highlighting its significant potential and advantages.

Long-Term Prediction of Sea Surface Temperature by Temporal Embedding Transformer With Attention Distilling and Partial Stacked Connection

Long-Term Prediction of Sea Surface Temperature by Temporal Embedding Transformer With Attention Distilling and Partial Stacked Connection

Feasibility of an open-source algorithm for predicting sea surface temperature based on three multi-resolution data sources

Feasibility of an open-source algorithm for predicting sea surface temperature based on three multi-resolution data sources

CSACL: A Channel Spatial Attention Convolutional LSTM Model for Short-Term Sea Surface Temperature Prediction

CSACL: A Channel Spatial Attention Convolutional LSTM Model for Short-Term Sea Surface Temperature Prediction

Long term of sea surface temperature prediction for Indonesia seas using multi time-series satellite data for upwelling dynamics projection

Global warming, which impacts global temperatures, has led to an increase in sea surface temperature (SST). This rise significantly affects marine ecological systems, especially in Indonesia. As a result, long-term forecasting of SST dynamics is essential for shaping various policies. However, most studies on SST forecasting have focused on short-term predictions in local or medium-sized areas and often overlook the dynamic upwelling that influences SST. In this paper, we propose a five-year SST prediction for the Indonesian seas, incorporating multi-time-series satellite data to project upwelling dynamics. We utilized two deep learning time series models to construct a predictive model that estimates monthly SST values. This model employs extensive multiple satellite data, encompassing 14,934 points (including SST with a resolution of 0.090, wind, ENSO, heat flux, and solar radiation) from 2003 to 2021. To enrich the training data and mitigate overfitting, we applied data augmentation for time series. Experimental results reveal that all satellite datasets correlate with SST over five years. The 1D-Convolution Neural Network outperformed the Long-Short Term Memory model, exhibiting the lowest mean absolute error of 0.39 °C compared to 0.45 °C. Our model detected a consistent upwelling dynamic over a five-year pattern in the Indonesian seas. These findings suggest that our proposed model offers accurate and efficient long-term monthly SST predictions, crucial for upwelling projections.

Multi‐Year Predictability of Global Sea Surface Temperature Using Model‐Analogs

AbstractThe multi‐year predictability of global sea surface temperature (SST) is examined by applying a model‐analog method to four control simulations to make forecasts at leads of 1–36 months over 1961–2015. The forecasts are found to have skill for annual mean SST at Year 2 (i.e., leads of 13–24 months) or even Year 3 (i.e., leads of 25–36 months) in the tropical Pacific, the North and South Pacific, the southwest Indian Ocean, and the northwestern tropical Atlantic. The seasonality in forecast skill suggests that July is the best time to initialize multi‐year forecasts. The evolution of forecast skill for tropical Pacific SSTs indicates that the predictability of some El Niño Southern Oscillation events is nearly the same at leads of 6 and 18 or 24 months. Further, these El Niño and La Niña events can be predicted at leads of up to 24 and 30 months, respectively.

Statistical Method and Deep Learning Model for Sea Surface Temperature Prediction

Statistical Method and Deep Learning Model for Sea Surface Temperature Prediction