scholarly journals Weather Forecasting Using Merged Long Short-Term Memory Model (LSTM) and Autoregressive Integrated Moving Average (ARIMA) Model

2018 ◽  
Vol 14 (7) ◽  
pp. 930-938 ◽  
Author(s):  
Afan Galih Salman ◽  
Yaya Heryadi ◽  
Edi Abdurahman ◽  
Wayan Suparta
Keyword(s):  
Short Term Memory ◽  
Weather Forecasting ◽  
Moving Average ◽  
Arima Model ◽  
Memory Model ◽  
Short Term ◽  
Term Memory ◽  
Autoregressive Integrated Moving Average ◽  
Long Short Term Memory

scholarly journals Weather Forecasting Using Merged Long Short-term Memory Model

2018 ◽  
Vol 7 (3) ◽  
pp. 377-385 ◽  
Author(s):  
Afan Galih Salman ◽  
Yaya Heryadi ◽  
Edi Abdurahman ◽  
Wayan Suparta
Keyword(s):  
Short Term Memory ◽  
Weather Forecasting ◽  
Human Life ◽  
Predictor Variable ◽  
Dew Point ◽  
Memory Model ◽  
Short Term ◽  
Research Attention ◽  
Term Memory ◽  
Long Short Term Memory

Over decades, weather forecasting has attracted researchers from worldwide communities due to itssignificant effect to global human life ranging from agriculture, air trafic control to public security. Although formal study on weather forecasting has been started since 19th century, research attention to weather forecasting tasks increased significantly after weather big data are widely available. This paper proposed merged-Long Short-term Memory for forecasting ground visibility at the airpot using timeseries of predictor variable combined with another variable as moderating variable. The proposed models were tested using weather timeseries data at Hang Nadim Airport, Batam. The experiment results showedthe best average accuracy for forecasting visibility using merged Long Short-term Memory model and temperature and dew point as a moderating variable was (88.6%); whilst, using basic Long Short-term Memory without moderating variablewasonly (83.8%) respectively (increased by 4.8%).

scholarly journals A Fuzzy Seasonal Long Short-Term Memory Network for Wind Power Forecasting

Mathematics ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1178
Author(s):  
Chin-Wen Liao ◽  
I-Chi Wang ◽  
Kuo-Ping Lin ◽  
Yu-Ju Lin
Keyword(s):  
Neural Network ◽  
Wind Power ◽  
Power Output ◽  
Short Term Memory ◽  
Moving Average ◽  
Short Term ◽  
Term Memory ◽  
Autoregressive Integrated Moving Average ◽  
Memory Network ◽  
Long Short Term Memory

To protect the environment and achieve the Sustainable Development Goals (SDGs), reducing greenhouse gas emissions has been actively promoted by global governments. Thus, clean energy, such as wind power, has become a very important topic among global governments. However, accurately forecasting wind power output is not a straightforward task. The present study attempts to develop a fuzzy seasonal long short-term memory network (FSLSTM) that includes the fuzzy decomposition method and long short-term memory network (LSTM) to forecast a monthly wind power output dataset. LSTM technology has been successfully applied to forecasting problems, especially time series problems. This study first adopts the fuzzy seasonal index into the fuzzy LSTM model, which effectively extends the traditional LSTM technology. The FSLSTM, LSTM, autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), back propagation neural network (BPNN), least square support vector regression (LSSVR), and seasonal autoregressive integrated moving average (SARIMA) models are then used to forecast monthly wind power output datasets in Taiwan. The empirical results indicate that FSLSTM can obtain better performance in terms of forecasting accuracy than the other methods. Therefore, FSLSTM can efficiently provide credible prediction values for Taiwan’s wind power output datasets.

scholarly journals A Novel Long Short-Term Memory Predicted Algorithm for BDS Short-Term Satellite Clock Offsets

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Tailai Wen ◽  
Gang Ou ◽  
Xiaomei Tang ◽  
Pengyu Zhang ◽  
Pengcheng Wang
Keyword(s):  
Short Term Memory ◽  
Moving Average ◽  
Arima Model ◽  
Communication Link ◽  
Satellite Clock ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Galileo Satellite ◽  
Clock Offset

The satellite clocks carried on the BeiDou navigation System (BDS) are a self-manufactured hydrogen clock and improved rubidium clock, and their on-orbit performance and stabilities are not as efficient as GPS and Galileo satellite clocks caused of the orbital diversity of the BDS and the complexity of the space operating environment. Therefore, the existing BDS clock product cannot guarantee the high accuracy demand for precise point positioning in real-time scenes while the communication link is interrupted. To deal with this problem, we proposed a deep learning-based approach for BDS short-term satellite clock offset modeling which utilizes the superiority of Long Short-Term Memory (LSTM) derived from Recurrent Neural Networks (RNN) in time series modeling, and we call it QPLSTM. The ultrarapid predicted clock products provided by IGS (IGU-P) and four widely used prediction methods (the linear polynomial, quadratic polynomial, gray system (GM (1,1)), and Autoregressive Integrated Moving Average (ARIMA) model) are selected to compare with the QPLSTM. The results show that the prediction residual is lower than clock products of IGU-P during 6-hour forecasting and the QPLSM shows a greater performance than the mentioned four models. The average prediction accuracy has improved by approximately 79.6, 69.2, 80.4, and 77.1% and 68.3, 52.7, 66.5, and 69.8% during a 30 min and 1-hour forecasting. Thus, the QPLSTM can be considered as a new approach to acquire high-precision satellite clock offset prediction.

Sign in / Sign up

Export Citation Format

Share Document