A hybrid CNN-LSTM model for typhoon formation forecasting

Development of Drone-Mounted Multiple Sensing System with Advanced Mobility for In Situ Atmospheric Measurement: A Case Study Focusing on PM2.5 Local Distribution

“…As a predictive model, LSTM is an improved recurrent neural network (RNN) architecture that solves the vanishing gradient problem [ 95 ]. LSTM and its derivative models have been used widely in existing studies to forecast typhoon formation and hourly air pollution [ 96 ], to analyze meteorological sensor signals [ 97 ], and to estimate PM concentrations [ 68 , 98 ]. Figure 18 portrays a typical LSTM network architecture of hidden layers.…”

ResNet-LSTM for Real-Time PM2.5 and PM₁₀ Estimation Using Sequential Smartphone Images

“…Using these techniques, efforts have been made on combining CNN with LSTM for extracting spatial-temporal features. Chen [26] used CNN-LSTM models to forecast typhoon formation and hourly air pollution across the city [27], [28]. These models have shown that pollution estimation performance can be improved by combining temporal features with spatial features.…”

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

“…R. Chen, Wang, et al. (2019) employed deep neural networks to forecast global TEC maps. However, the application of machine learning and deep learning methods to study the ionosphere can be considered at its infancy state, especially at high and mid‐latitudes, given the ubiquitously available space and ground based data sets and the recent popularity of machine learning methods (McGranaghan et al., 2018).…”