Please use this identifier to cite or link to this item:
|SODAR Echograms Based Model Development for Atmospheric Boundary Layer Characterization
|SODAR;Atmospheric Boundary Layer;ABL Structure;Acoustic Antenna;Long-Short Term Memory;Machine-Learning
|SOnic Detection And Ranging (SODAR) is a well-known and widely accepted meteorological tool for supplying continuous real-time and critical Atmospheric Boundary Layer (ABL) data. Data is critical for evaluating environmental impact assessments and city-specific carrying capacity for pollutants. Existing SODAR technology was improved, which included, acoustic antenna advancements, virtual instrumentation, and improved data processing approaches. This advancement will affect the observed data, and data will be more accurate as a result of calibration and testing of equipment and materials. An acoustic antenna was designed using moving-coil transducers, parabolic dish, and acoustic baffle. Several types of Aluminium Composite Panel (ACP) for acoustic baffle were tested to their characteristics like Sound Transmission Coefficient (STC) and Noise Reduction Coefficient (NRC) in the reverberation chamber. A comparison investigation was carried out on transmission loss and absorption. It was concluded that baffle (ACP with foam) is the suitable material with STC (34) and NRC (0.98) for an acoustic antenna. The SODAR echogram for the ABL structure was derived and successfully applied in a highly accurate and reliable machine-learning method. In terms of performance, five functional selection procedures and eight classification methods were examined. From 1698 SODAR echograms, 133 statistic features were calculated. Machine-learning methods were used to ensure the unbiased estimation of different structures. Ten cross-validations were used to determine accuracy. The boosted tree classifier was given the strongest prognostic presentation with 133 features (total prediction rating of 52.02%). After applying the Laplacian method for feature selection, the classifier (overall prediction performance 62.19%) showed the highest prognostic presentation with 20 features. The large variability analysis indicates the choice of a classification method for performance variation. The development of optimal machine-learning methods for SODAR echogram applications was a critical step toward the ABL structure identification, which provides an automatic structure classification method for atmospheric and pollutants studies. A deep learning new model was then employed in temporary/seasonal and annual prediction of ABL height. It presents the outcomes of the Long-Short Term Memory (LSTM) models, based on SODAR observations from December 2018 to February 2020. The LSTM model was used to predict the ABL height and analyse the model's performance. The analysis shows when the number of neurons was 32 it was possible to achieve optimal results in a short period of training when the epoch was 500. To achieve an acceptable prediction accuracy, various types of errors for the measured time-series data were calculated. The relative Root Mean Square Error (rRMSE) and Mean Absolute Percentage Error (MAPE) values for the update network state with predicted values were 7.33 % and 17.3 %, respectively, and for the update network state with observed values, rRMSE and MAPE are 5.95 % and 10.62 %, respectively. This model was also used to compare annual and seasonal predictions of ABL height, as the rRMSE values (7.49 % and 5.59 %) were lowest during post-monsoon prediction and highest (10.29 % and 5.86 %) during annual prediction. Then, during the fireworks (Diwali festival), it deals with the impact on ABL height of pollutants and meteorological parameters. In 2014-2017, ABL height and Ventilation Coefficients (VC) were debated on the effect of firecrackers on air quality. The Forward Section (FS) technique was employing the major parameters affected by the ABL height. The main purpose of this study was to identify the highly effecting parameter for the ABL height regarding air pollution. On the day of Diwali festival, the average ABL height was approximately 25%, 15%, and 6% lower in 2014, 2016, and 2017, respectively, as compared to Pre-Diwali day, but 15% higher in 2015 due to high wind speed associated with elevated pollution levels. The burning of firecrackers during the Diwali festival is a very strong source of air pollution, according to mean comparisons and correlations, contributing significantly to the number of particulate matter and gaseous pollutants in the environment.
|Appears in Collections:
Files in This Item:
|Single File Thesis_PhD_Nishant Kumar_r1 (1).pdf
|View/Open Request a copy
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.