ILF-LSTM: enhanced loss function in LSTM to predict the sea surface temperature

Bhimavarapu, Usharani

doi:10.1007/s00500-022-06899-y

Cited by 24 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM neural network is an RNN (Recurrent Neural Network) aimed at solving the problem of gradient explosion and vanishing that often occur during long-term sequence training [20,21]. They are particularly well-suited for handling time series data [22,23]. LSTM networks are governed by the presence of a forget gate, input gate, and output gate, which collectively control the cell state, the overall structure is shown in Figure 1 and the calculation for the three gates is as follows:…”

Section: Theoretical Basis a Long Short-term Memory Network(lstm)mentioning

confidence: 99%

L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory

Gao,

Wang,

2024

IEEE Access

View full text Add to dashboard Cite

The high-speed vibration rotation of the drill bit during drilling causes the logging tool to be damaged or distorted, resulting in inaccurate or lost data collection. Traditional prediction methods such as dynamic modeling and geological modeling have problems such as incomplete data and difficult modeling, which cannot meet the accuracy and stability requirements of wellbore trajectory prediction. The long shortterm memory neural network (LSTM) for predicting time series can achieve accurate prediction, but there are problems such as difficulty in adjusting the hyperparameters of the LSTM model, slow convergence speed, and easy overfitting. This paper absorbs the advantages of the LSTM algorithm, ridge regression (L2 regularization), and sparrow optimization algorithm (SSA) in machine learning and proposes a well trajectory prediction model of steerable drilling based on L2 regularization and SSA optimized LSTM (L2-SSA-LSTM). The model takes the LSTM hyperparameter as the parameter optimization goal of SSA and adds L2 regularization to the model to prevent model overfitting to complete modeling and prediction. The experiment was conducted using measured data sets from directional drilling in two different oilfields. The results show that compared with the back propagation algorithm (BP), consolidated memory gated recurrent unit (CMGRU), dual-thread gated recurrent unit (DTGRU), Attention-based Spatiotemporal Graph Recurrent Neural Network (ASTG-RNN), LSTM, and the L2-SSA-LSTM prediction model has significantly higher accuracy in predicting directional drilling trajectories than other models and has the better predictive ability.

show abstract

Section: Theoretical Basis a Long Short-term Memory Network(lstm)mentioning

confidence: 99%

L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory

Gao,

Wang,

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In contrast, the curve for Bitcoin is continuous, indicating that Bitcoin is not affected by trading hours. Based on the data and the images obtained, it is easy to see that the two datasets are extremely nonlinear, so we can use AI prediction algorithms such as neural network algorithms to model and analyze [5].…”

Section: Data Pre-processing and Visualizationmentioning

confidence: 99%

Research on Portfolio Model Based on LSTMIS-AMTM and Improved Markowitz

Bi¹

2022

HSET

View full text Add to dashboard Cite

With the development of ﬁnancial market, portfolio investment has become a new hotspot in the ﬁeld of quantitative investment. We develop a model to propose the best strategy of gold and bitcoin portfolio investment. We ﬁrst use LSTMIS to predict the value of gold and bitcoin with input sequence consisting of last 30 days data. Then we use the predicted data and the mean value of last 5 days as long- and short-term moving average input of AMTM model respectively, hence judging whether to buy or sell. Then we improve and modify the existing Markowitz portfolio model by treating gold and bitcoin as two diﬀerent stocks and completing the matching of the two through the model, so as to make quantitative investments and reduce the risk while satisfying a higher rate of return.

show abstract

“…Xie et al [39] proposed a GRU encoder-decoder model (GED) based on SST code and dynamic influence link for SST prediction. 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.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Sea Surface Temperature Using U-Net Based Model

Ren,

Wang,

Sun

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

ILF-LSTM: enhanced loss function in LSTM to predict the sea surface temperature

Cited by 24 publications

References 26 publications

L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory

L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory

Research on Portfolio Model Based on LSTMIS-AMTM and Improved Markowitz

Prediction of Sea Surface Temperature Using U-Net Based Model

Contact Info

Product

Resources

About