Anupam Kamble. PM2.5 Concentration value estimation from images and weather data using image processing and machine learning. Master's Degree(Data Science). Chiang Mai University. Library. : Chiang Mai University, 2024.
PM2.5 Concentration value estimation from images and weather data using image processing and machine learning
Abstract:
Particulate pollution (PM2.5) is an important concern in Asian countries because of its health hazards. When planning outdoor activities, understanding the PM2.5 concentration measurement is essential. Because of the lower number of government-run Air Quality Monitoring Stations, other options for obtaining location-specific PM2.5 concentration values are sought. This research proposes to use photo image processing to estimate the PM2.5 concentration. This research aims to improve the efficacy and reduce the computational complexity of the PM2.5 concentration estimation process. The proposed Efficient PM2.5 estimation framework uses EfficientNet-B1 and BiLSTM to estimate PM2.5 concentrations. The Met-EfficientNet-B1-BiLSTM has been designed and implemented to incorporate the Meteorological features, temperature, wind speed, and humidity to improve the estimation accuracy further. The EfficientNet-B1 neural network is applied in the image feature vector extraction process. EfficientNet-B1, with a resolution of 240 x 240 pixels, is determined to be the optimal EfficientNet variant for a small dataset of images needed for PM2.5 concentration value estimation. The BiLSTM is used for the regression of these image features with PM2.5 concentration values to obtain the estimated PM2.5 concentration. A dataset comprising HDR and non-HDR images was explicitly created for this study to compare the types of images that improve the accuracy of PM2.5 concentration estimation and the feature extraction process. The proposed Efficient PM2.5 estimation framework reduces computational complexity and outperforms the ResNet-18-LSTM by improving efficacy by 5.75% in in MAE 11.43% in SMAPE matrices. The proposed Efficient PM2.5 estimation framework with less computational complexity, archives high accuracy when estimating PM2.5 concentration values using photo images.