Atmospheric aerosol affects electromagnetic radiation transmission through scattering and absorption, which has great influence on optical satellite remote sensing, environmental monitoring, climate forcing and aerosol-cloud interaction. In2021, based on the data collected in the Yellow Sea and the South China Sea near the coast, we developed the coast aerosol model (CAM) to predict the aerosols size distribution under coastal environments. This work makes a comprehensive model evaluation for the CAM with the atmospheric aerosol observation results at the South China Sea coastal station (Maoming) in November 2023. The comparison results show that the CAM can effectively describe the characteristics of aerosol (number concentration, particle size distribution and extinction coefficient) in this area. During the observation period, the average error of prediction results of aerosol concentration is around 20.6%, indicating that the CAM is promising in prediction coastal aerosol microphysical and optical properties.
Models related to long and short-term memory networks have demonstrated superior performance in short-term prediction, but their prediction ability becomes limited in long sequence time series forecasting (LSTF), and prediction time increases. To address these issues, this paper optimizes the Transformer and Informer models in the following ways: (1) input representation optimization, by adding a time embedding layer representing global timestamps and a positional embedding layer to improve the model's prediction ability for aerosol extinction coefficient (AEC); (2) self-attention mechanism optimization, by using probabilistic self-attention mechanism and self-attention distillation mechanism to reduce memory usage and enhance the model's local modeling ability through convolutional aggregation operations; (3) generative decoding, using dynamic decoding to enhance the model's long sequence prediction ability. Based on these optimizations, a new LSTF model for AEC is proposed in this paper. Experimental results on the atmosphere parameters of the Maoming (APM) dataset and weather dataset show that the proposed model has significant improvements in accuracy, memory usage, and runtime speed compared to other similar Transformer models. In the accuracy experiment, compared to the Transformer model, the MAE of this model on APM dataset decreased from 0.237 to 0.103, and the MSE decreased from 0.345 to 241. In the memory usage experiment, the model can effectively alleviate memory overflow problems when the input length is greater than 720. In the runtime speed experiment, when the input length is 672, the training time per round decreased from 15.32 seconds to 12.39 seconds. These experiments demonstrate the effectiveness and reliability of the proposed model, providing a new approach and method for long sequence prediction of AEC.
Knowledge of the atmospheric optical turbulence profile (AOTP) is critical for atmospheric optics studies. Meteorological sounding of long-term AOTP observations at seas often comes at an outrageous cost. It is necessary to establish a mathematical model driven by conventional meteorological parameters to predicate the AOTPs at high altitudes. Conventional meteorological parameters TUH (i.e., temperature, wind speed and relative humidity), have an important impact on the sea surface turbulence. AOTPs together with TUHs in Maoming were obtained. Based on the artificial neural network (NN) algorithm, an NN model is established according to the data to predict the upper atmospheric turbulence profile. The AOTPs measurements were used to validate the model predictions with the existing estimation theory. Cross-validation between these methods are performed and evaluated with mean absolute error (MAE), mean variance (MSE) and root mean square variance (RMSE). The results show that the predicted values simulated by the NN algorithm agree well with the real values, which proves that it is feasible and reliable to use the NN to simulate the atmospheric turbulence profile.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.