Figure 7 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Spatial distribution of monthly mean sea surface temperature predicted by LSTM model in 2020, the unit of colorbar is degrees Celsius. Spatial distribution of monthly mean sea surface temperature predicted by LSTM model in 2020, the unit of colorbar is degrees Celsius.
Source publication
Sea surface temperature (SST) is an important physical factor in the interaction between the ocean and the atmosphere. Accurate monitoring and prediction of the temporal and spatial distribution of SST are of great significance in dealing with climate change, disaster prevention, disaster reduction, and marine ecological protection. This study esta...
Contexts in source publication
Context 1
... that the RMSE value of the L4 position in Figure 5 is the smallest, the LSTM model trained at the L4 position is selected to predict the SST of the whole study area in 2020 to prove whether the LSTM network has the characteristics of migration. The spatial distribution of SST in 2020 predicted by the LSTM model is shown in Figure 7. The characteristics of SST, such as the Kuroshio, the Min-Zhe coastal current, and the Yangtze River Diluting Water, are clearly displayed in the forecast map and show obvious seasonal changes. ...
Context 2
... that the RMSE value of the L4 position in Figure 5 is the smallest, the LSTM model trained at the L4 position is selected to predict the SST of the whole study area in 2020 to prove whether the LSTM network has the characteristics of migration. The spatial distribution of SST in 2020 predicted by the LSTM model is shown in Figure 7. The characteristics of SST, such as the Kuroshio, the Min-Zhe coastal current, and the Yangtze River Diluting Water, are clearly displayed in the forecast map and show obvious seasonal changes. ...
Similar publications
The simulation of Concrete Gravitational Dam burst floods is an important research content in the field of disaster prevention and mitigation in water conservancy projects. Due to the extreme rainfall, earthquake, structure failure and etc., the concrete gravitational dam usually breaks in a short time period. The dam break flood will give an extre...
Citations
... Therefore, in recent years, prediction methods based on deep learning have rapidly developed and become the main research field of SST prediction. Artificial neural network models such as the feedforward neural network [17,18], which only has forward propagation with fully connected layers; the long short-term memory network (LSTM) [19,20], which can better process long time-series data by introducing a gate control mechanism; gated recurrent units (GRUs) [21,22], which optimize LSTM by simplifying the gate control; and the convolutional neural network (CNN) [23,24], which is able to better capture spatial features; as well as deep learning models composed of these different neural networks, are becoming the popular approach for SST prediction. ...
Sea surface temperature (SST) prediction plays an important role in scientific research, environmental protection, and other marine-related fields. However, most of the current prediction methods are not effective enough to utilize the spatial correlation of SSTs, which limits the improvement of SST prediction accuracy. Therefore, this paper first explores spatial correlation mining methods, including regular boundary division, convolutional sliding translation, and clustering neural networks. Then, spatial correlation mining through a graph convolutional neural network (GCN) is proposed, which solves the problem of the dependency on regular Euclidian space and the lack of spatial correlation around the boundary of groups for the above three methods. Based on that, this paper combines the spatial advantages of the GCN and the temporal advantages of the long short-term memory network (LSTM) and proposes a spatiotemporal fusion model (GCN-LSTM) for SST prediction. The proposed model can capture SST features in both the spatial and temporal dimensions more effectively and complete the SST prediction by spatiotemporal fusion. The experiments prove that the proposed model greatly improves the prediction accuracy and is an effective model for SST prediction.
... Other studies indicated that prediction accuracy depends on various factors, such as the SST pattern, temporal resolution of the data, and parameters utilized (Alonso et al. 2023;Farhangi et al. 2023). Increasing the time span of the input data can improve prediction performance (Jia et al. 2022). Additional approaches such as personalized dynamic graph networks and hierarchical graph recurrent networks have also been developed to tackle the spatiotemporal complexities of SST prediction (Zhang et al. 2023;Yang et al. 2023). ...
Sea surface temperature (SST), with its complex and dynamic behavior, is a major driver of ocean–atmosphere interactions. The purpose of this study is to investigate the behavior of SST and its prediction using a chaotic approach. Average mutual information (AMI) and Cao methods were used to reconstruct the phase space. The Lyapunov exponent and correlation dimension were used to investigate chaos. The Lyapunov exponent index was used to predict SST with a 5-year average prediction horizon using the local prediction method between 2023 and 2027. The results showed a 3-month delay time for the Pacific and Antarctic Oceans, and a 2-month delay time for the Atlantic, Indian, and Arctic Oceans. The optimal embedding dimension for all oceans is between 6 and 7. Our analysis reveals that the dynamics of SST in all oceans exhibit varying degrees of chaos, as indicated by the correlation dimension. The local prediction method achieves relatively accurate short-term SST predictions due to the clustering of SST points around specific attractors in the phase space. However, in the long term, the accuracy of this method decreases as the points in the phase space of SST can spread randomly. The model performance ranking with a Percent Mean Relative Absolute Error shows that the Indian Ocean has the best performance compared to other oceans, while the Atlantic, Pacific, and Antarctic and Arctic Oceans are in the next ranks. This study contributes to understanding the dynamics of SST and has practical value for use in the development of climate models.
... The nudging assimilation method was also used to improve the accuracy of temperature prediction. As a result, the RMS between the temperature simulated by heat flux and the observed data are 1.56 • C, 0.88 • C, and 1.23 • C, respectively [57]. The atmospheric data and model parameter scheme also affected the simulation result even though the model have the same initial and boundary conditions. ...
... Many Different data-driven methods are used to predict the SST in the East China Sea [16,17,34,[57][58][59]. However, this data-driven method only uses a single SST as input data and does not consider the influence of other factors affecting the sea surface temperature on the model prediction. ...
Atmospheric forcings are significant physical factors that influence the variation of sea surface temperature (SST) and are often used as essential input variables for ocean numerical models. However, their contribution to the prediction of SST based on machine-learning methods still needs to be tested. This study presents a prediction model for SST in the East China Sea (ECS) using two machine-learning methods: Random Forest and SA-ConvLSTM algorithms. According to the Random Forest feature importance scores and correlation coefficients R, 2 m air temperature and longwave radiation were selected as the two most important key atmospheric factors that can affect the SST prediction performance of machine-learning methods. Four datasets were constructed as input to SA-ConvLSTM: SST-only, SST-T2m, SST-LWR, and SST-T2m-LWR. Using the SST-T2m and SST-LWR, the prediction skill of the model can be improved by about 9.9% and 9.43% for the RMSE and by about 8.97% and 8.21% for the MAE, respectively. Using the SST-T2m-LWR dataset, the model’s prediction skill can be improved by 10.75% for RMSE and 9.06% for MAE. The SA-ConvLSTM can represent the SST in ECS well, but with the highest RMSE and AE in summer. The findings of the presented study requires much more exploration in future studies.
... Among these, the sea surface temperature (SST) dataset serves as a fundamental indicator of oceanic heat content, measured by microwave or infrared wavelengths in the electromagnetic spectrum [1,2]. Variations in SST play a key role in the exchange of energy and moisture between the atmosphere and the ocean [3,4]. SST databases, established using geospatial artificial intelligence computations, are vital for accurately monitoring SST changes to understand and predict the dynamics of climate change, oceanic processes [3], and the overall health of the marine ecosystem [5][6][7][8]. ...
... Variations in SST play a key role in the exchange of energy and moisture between the atmosphere and the ocean [3,4]. SST databases, established using geospatial artificial intelligence computations, are vital for accurately monitoring SST changes to understand and predict the dynamics of climate change, oceanic processes [3], and the overall health of the marine ecosystem [5][6][7][8]. With the advent of satellite technology, satellite-derived SST data have become an essential resource for studying global oceanic and atmospheric phenomena. ...
Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis , particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model's enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net's potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science.
... The LSTM cell mainly consists of an input gate, a forgetting gate, and an output gate, and the information in the current cell is processed by these three gates to selectively "remember" or "forget" some data points (Figure 4a). The LSTM network and its multiple variants have already demonstrated their ability to accurately predict the sea surface temperature and chlorophyll-a concentrations [12,13], and they have been successfully used for wave prediction [14]. ...
The marine environment of the Arctic Ocean has changed rapidly in recent decades. We used reanalysis data and observational data to explore the variations in the upper ocean heat content (OHC) of the Canadian Basin (CB) and the variations in the temperature profiles of the Southern Canadian Basin (SCB). Both the reanalysis data and observational data show increasing trends for the OHC of the CB from 1993 to 2023. Compared to the World Ocean Atlas data (WOA 18/23), the reanalysis data (ORAS5 or GLORYS12V1) significantly underestimated the values of the upper OHC of the Canadian Basin. To explain the OHC differences, the Ice-Tethered Profiler (ITP) observational data were used to analyze the variations in the vertical temperature profiles. We found that the reanalysis data remarkably underestimated the maximum temperatures of the subsurface Pacific warm water and its increasing trend. Based on the short-term prediction results from the Bi-LSTM neural network, we forecasted that the upper OHC will continue to increase in the SCB, mainly due to the warming of the intermediate Atlantic warm water. The research results provide a valuable reference for assessing and improving climate-coupled models.
... This will help us establish and improve a warning and defense decision-making system for marine meteorology, storm surges, strong winds, floods, and other marine disasters. We will also accelerate the construction of a three-dimensional monitoring and forecasting network system for the ocean to improve our ability to prevent and reduce disasters and respond to sudden maritime accidents [74,75]. Thirdly, the construction project of the coastal protective forest system. ...
The oceans are a treasure trove of natural resources and an essential regulator of the global climate. Still, due to economic development and human activities in recent years, these ecosystems have suffered varying degrees of degradation, so the restoration of marine ecosystems is essential. At the same time, states should strengthen the synergy of marine disaster prevention and mitigation efforts and jointly defend against the impact of maritime disasters on human lives, property, and climate change. On June 28–29, 2023, the Forum on Restoration of Marine Ecological Environment Protection, Disaster Prevention, and Mitigation was held in Qingdao’s West Coast New Area. The forum adopted a combination of “online and offline.” Nearly 150 experts and scholars in marine-related environmental protection, disaster prevention, and mitigation from organizations, universities, and research institutes across multiple countries attended the event.
... Usharani [40] improved the accuracy of LSTM-based SST prediction by introducing a new loss function in LSTM. Jia et al. [41] predicted and analyzed SST in the East China Sea using LSTM. However, the above models only utilize the temporal information of SST, thereby neglecting the spatial information. ...
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.
... AI-Enhanced Sea-Surface Temperature Prediction: Researchers have been working on innovative AI/ML techniques to improve SST predictions, which have significant implications for various fields, including climate research, ecological preservation, and economic progress. These advancements include the use of graph memory neural networks (GMNNs) to encode irregular SST data effectively [1] and long-term and short-term memory neural networks (LSTMs) for SST prediction [2]. Satellite-Based AI Monitoring for Environmental Challenges: Satellite-based monitoring is crucial for addressing environmental challenges such as Sargassum aggregations and suspended sediment dynamics. ...
In the ever-evolving landscape of marine, oceanic, and climate change monitoring, the intersection of cutting-edge artificial intelligence (AI), machine learning (ML), and data analytics has emerged as a pivotal catalyst for transformative advancements [...]
... CNN carries the advantage of being able to ascertain hidden features from input data and process acceleration because it is not a sequentially based model. LSTM includes several benefits in sequence modeling due to its extended memory function and solving the problem of gradient loss and gradient implosion in the long sequence training process (Jia et al., 2022). However, it has drawbacks in parallel processing and always takes longer to train. ...
... Compared to other algorithms, the 1DCNN model proposed in this paper has significantly improved demodulation accuracy. Compared with GRU [23], LSTM [24], and traditional peak detection methods [25], Fig. 9 shows that the 1DCNN form has more minor errors and higher accuracy in predicting temperature values. We compared the 1DCNN model in this article with other models on RMSE, MAE, and R 2 indicators, and the outcomes are depicted in Table 2. ...
In this paper, we propose a new (to us) way of demodulating the grating sensing spectrum using a one-dimensional convolutional neural network (1DCNN) to overcome the limitation of the traditional fitting method of temperature demodulation for subway tunnel fires. This method constructs a one-dimensional convolutional neural network model and combines it with the experimental device of a fiber Bragg grating (FBG) temperature measurement. One thousand eight hundred spectra of experimental data are selected as sample data for training. Adam’s random optimization algorithm is used in training to predict the temperature of multiple periods, with an accuracy of 99.95% and a root-mean-square deviation (RMSE) of 0.0832°C. The experiment shows that the algorithm in this paper is better than the GRU and LSTM algorithms, as traditional maximum peak methods, and can effectively improve the measurement accuracy. This article aims to provide a high-speed demodulation solution for FBG-based sensing systems to meet the practical needs of large-scale real-time monitoring.
