Aerosol scattering and absorption coefficients are important parameters that characterize the optical properties of aerosols, which have significant impacts on the radiation balance, air quality, and climate change of the Earth. In order to further improve the understanding of the relationship between aerosol optical properties and meteorological parameters in the offshore areas of Guangdong Maoming, the scattering and absorption coefficients of aerosols as well as meteorological parameters such as temperature, humidity, pressure, wind speed, wind direction, and visibility were measured. In this study, a prediction model of aerosol scattering and absorption coefficients based on the CatBoost algorithm was proposed using the measured data. Firstly, the measured data was preprocessed, and then a CatBoost algorithm model based on ensemble learning was constructed and trained. The Optuna framework was used to optimize the hyperparameters of the model to obtain the final aerosol scattering and absorption coefficient prediction model. Finally, the machine learning model was used to predict the scattering and absorption coefficients of aerosols in the offshore areas of Maoming. The model was compared with XGBoost and LightGBM algorithm models, and the mean squared error (MSE) and mean absolute error (MAE) were used as evaluation metrics to assess the accuracy of the model predictions. Based on the evaluation metrics, the CatBoost algorithm model based on Optuna automatic hyperparameter optimization performed the best among several models. The experimental results showed that when the training and testing data came from the same region, the MAE of the CatBoost algorithm model based on Optuna hyperparameter optimization was about 5.33, and the MSE was about 48.764, achieving a prediction accuracy of 90.88% for aerosol scattering and absorption coefficients.
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.
KEYWORDS: Solar radiation models, Solar radiation, Temperature metrology, Thermal modeling, Infrared radiation, Atmospheric modeling, Emissivity, 3D modeling
To estimate spatial distribution of thermal characteristics of stratospheric airships, this paper considers the complex thermodynamic environment in which the airships operate, and establishes a computational model for the thermal characteristics of the airships, including thermal equilibrium equations, direct solar radiation, scattered solar radiation, Earth-reflected radiation, atmospheric infrared radiation, Earth infrared radiation, radiation heat transfer and convective heat transfer between skin units. With this model, theoretical simulations of temperature fields were performed for the airships. The simulation results show that the skin temperature of stratospheric airships are mainly affected by the intensity of solar radiation, which is lower at night and higher during the day. Under floating conditions, the skin temperature field exhibits high non-uniformity and significant temporal variations. The skin solar absorptivity of the stratospheric airship has a significant effect on the skin temperature, as reducing the solar absorptivity from 0.5 to 0.2 decreases the maximum skin temperature from 322.94K to 263.98K, with a decrease of 58.96K. The skin surface infrared emissivity is another factor which has a significant effect on the skin temperature, as increasing the surface infrared emissivity from 0.5 to 0.8 reduces the maximum skin temperature from 297.35K to 274.74K, with a decrease of 22.61K. Different seasons have a certain influence on the skin surface temperature of stratospheric airships, with a temperature difference of about 15K between the summer and the winter solstices, mainly due to the difference in solar radiation intensity received by the skin of the airship, which affects the temperature variation of the skin. The theoretical model established in this paper provide a useful tool for multi-physics simulations and analyses of stratospheric airships.
The complex refractive index of aerosol particles has a vital influence on the radiation effect of aerosols. From July to October 2020, a long-term observation of marine aerosols in the Pacific Ocean was carried out by a surveying vessel.Based on the number concentration of marine aerosol particles measured by optical particle counter (OPC), the extinction coefficient and scattering coefficient of marine aerosol measured by single scattering albedo monitor (CAPS), combined with meteorological data, and through Mie scattering theory, the influence of the change of real and imaginary parts of marine aerosol particle refractive index on particle single scattering albedo is studied. The measurement results show that the range of single scattering albedo of marine aerosol is about 0.7-0.9. The inversion results show that the real part of aerosol refractive index varies from 1.335 to 1.45 and the imaginary part varies from 0.011 to 0.018.
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.
As an important part of the atmospheric environment, aerosols play a critical role in the study of the relationship between light and radiation. However, due to the complex spatiotemporal distribution of aerosols, it is much difficult to measure their microphysical properties and to determine their optical properties in coastal areas. In this paper, basic meteorological elements (e.g., wind speed, temperature, humidity) are simulated with the numerical weather forecasting (WRF) model. Then, the coastal aerosol model (CAM) together with the observation data is used to simulate the aerosol particle size distribution (APSD) and extinction coefficient for the coastal environment of Qingdao. Finally, data measured by the automatic weather station and particle counter in the coastal area are compared to their corresponding simulations. According to the comparisons results, temperature simulations were higher from an overall perspective (<2°C) with the correlation coefficient larger than 0.96; humidity simulations were comparatively lower on the 11th and 12th day (<10%) than those onthe 13th day (<20%), but the correlation coefficient was still larger than 0.8. With the meterological parameters simulations, the CAM model was used to predict the APSDs. It is founded that simulations for large particles are generally larger, while those for giant particles are generally smaller, but the simulated temperature, humidity, APSD and extinction coefficient are very consistent with their corresponding measurements. The method established in this paper is promising for the simulation and forecast of both the meteorological elements and aerosol microphysical properties.
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.