Application of HHO-CNN-LSTM-based CMAQ correction model in air quality forecasting in Shanghai
Journal Title: Energy Environmental Protection - Year 2023, Vol 37, Issue 6
Abstract
With rising levels of air-pollution, air-quality forecasting has become integral to the dissemination of human health advisories and the preparation of mitigation strategies. Traditional air quality models, such as the Community Multi-scale Air Quality (CMAQ) model, have unsatisfactory accuracy. Accordingly, a correction model, which combines convolutional neural network (CNN) and long-short term memory neural network (LSTM) and optimized by harris hawks optimization algorithm (HHO) was established to enhance the accuracy of CMAQ model's prediction results for six air pollutants (SO_2, NO_2, PM_10, PM_2.5, O_3 and CO). The accuracy of HHO-CNN-LSTM was evaluated using root mean square error (RMSE), mean absolute error (MAE), and the index of agreement (IOA). The results demonstrated a significant improvement in the accuracy of prediction for the six pollutants using the correction model. RMSE decreased by 73.11% to 91.31%, MAE decreased by 67.19% to 89.25%, and IOA increased by 35.34% to 108.29%. To address the propensity of the HHO algorithm to converge on local optima, leading to poor CO correction performance, this study proposed a method for the HHO algorithm with a Gaussian random walk strategy to improve the CO concentration correction performance.
Authors and Affiliations
ZHENG Xinnan|College of Electronics and Information Engineering, Tongji University, China, LIN Kaiyan|Institute of New Rural Development, Tongji University, China, WANG Zijing|College of Electronics and Information Engineering, Tongji University, China, SONG Yuanbo|College of Electronics and Information Engineering, Tongji University, China, SHI Yang|College of Electronics and Information Engineering, Tongji University, China, LU Hanyue|College of Electronics and Information Engineering, Tongji University, China, ZHANG Yalei|Institute of New Rural Development, Tongji University, China, College of Environmental Science and Engineering, Tongji University, SHEN Zheng*|Institute of New Rural Development, Tongji University, China
Keywords
Related Articles
- EP ID EP738051
- DOI 10.20078/j.eep.20231107
- Views 61
- Downloads 0
Present situation and prospect of anaerobic digestion to transform organic wastes to bio-natural gas
Anaerobic digestion, which could transform organic wastes to biological natural gas, emerged from the discovery of biogas. It is drawing mounting attention due to its pollution treatment and energy recovery. The realizat...
Simulation of mixed flow characteristics of distiller′s grains-wastewater for anaerobic fermentation
Anaerobic fermentation of distiller's grains (DG) is an effective method to treat DG. The DG separation technology, based on a hydraulic pulper, simplifies equipment and reduces energy consumption while ensuring the sepa...
Study on NO formation characteristics and ammonia-nitrogen conversion behavior during ammonia-coal co-firing
Experiments were conducted on a laboratory drop tube furnace for the single-firing of ammonia and coal, as well as co-firing, combined with numerical simulations to investigate the NO formation characteristics, intermedi...
Research Progress on Passive NOx Adsorbers (PNAs) for Diesel Vehicles
The cold start phase of diesel engines represents a critical stage for nitrogen oxides (NOx) emissions, which pose significant challenges to environmental sustainability and public health. During this phase, the exhaust...
Research on the performance of Cu(X)/SSZ-13 zeolite catalysts with different Cu contents for simultaneous elimination of soot and NO_x
Diesel engines have been widely applied in heavy industries such as transportation, agriculture, and construction due to their advantages of strong power and durability. However, the pollutants emitted by diesel engines,...