Research on Air Quality Prediction Model Based on Bidirectional Gated Recurrent Unit and Attention Mechanism

2020 ◽  
Author(s):  
Yutao Chen ◽  
Chengxu Ye ◽  
Wentao Wang ◽  
Ping Yang
Keyword(s):  
Air Quality ◽  
Prediction Model ◽  
Attention Mechanism ◽  
Quality Prediction ◽  
Model Based ◽  
Air Quality Prediction ◽  
Gated Recurrent Unit

A Gaussian process mixture model-based hard-cut iterative learning algorithm for air quality prediction

2019 ◽  
Vol 85 ◽  
pp. 105789 ◽  
Author(s):  
Yatong Zhou ◽  
Xiangyu Zhao ◽  
Kuo-Ping Lin ◽  
Ching-Hsin Wang ◽  
Lingling Li
Keyword(s):  
Air Quality ◽  
Gaussian Process ◽  
Mixture Model ◽  
Learning Algorithm ◽  
Iterative Learning ◽  
Quality Prediction ◽  
Model Based ◽  
Air Quality Prediction

Statistical oxidant air quality prediction model for land use and transportation planning

1977 ◽  
Vol 11 (5) ◽  
pp. 449-458 ◽  
Author(s):  
J.M. Caporaletti ◽  
L.N. Myrabo ◽  
P. Schleifer ◽  
A. Stanonik ◽  
K.R. Wilson
Keyword(s):  
Land Use ◽  
Air Quality ◽  
Prediction Model ◽  
Transportation Planning ◽  
Quality Prediction ◽  
Air Quality Prediction

scholarly journals Air Quality Prediction Based on a Spatiotemporal Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Xiangyu Zou ◽  
Jinjin Zhao ◽  
Duan Zhao ◽  
Bin Sun ◽  
Yongxin He ◽  
...  
Keyword(s):  
Air Quality ◽  
Spatial Data ◽  
Short Term Memory ◽  
Smart Cities ◽  
Line Graph ◽  
Rapid Development ◽  
Road Networks ◽  
Attention Mechanism ◽  
Quality Prediction ◽  
Air Quality Prediction

With the rapid development of the Internet of Things and Big Data, smart cities have received increasing attention. Predicting air quality accurately and efficiently is an important part of building a smart city. However, air quality prediction is very challenging because it is affected by many complex factors, such as dynamic spatial correlation between air quality detection sensors, dynamic temporal correlation, and external factors (such as road networks and points of interest). Therefore, this paper proposes a long short-term memory (LSTM) air quality prediction model based on a spatiotemporal attention mechanism (STA-LSTM). The model uses an encoder-decoder structure to model spatiotemporal features. A spatial attention mechanism is introduced in the encoder to capture the relative influence of surrounding sites on the prediction area. A temporal attention mechanism is introduced in the decoder to capture the time dependence of air quality. In addition, for spatial data such as point of interest (POI) and road networks, this paper uses the LINE graph embedding method to obtain a low-dimensional vector representation of spatial data to obtain abundant spatial features. This paper evaluates STA-LSTM on the Beijing dataset, and the root mean square error (RMSE) and R-squared ( R 2 ) indicators are used to compare with six benchmarks. The experimental results show that the model proposed in this paper can achieve better performance than the performances of other benchmarks.

scholarly journals Prediction and Analysis of Pollutant using Supervised Machine Learning

2020 ◽  
Vol 9 (2) ◽  
pp. 50-54
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Decision Tree ◽  
Prediction Model ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Quality Prediction ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Air Quality Prediction

Air is the most essential natural resource for the survival of humans, animals, and plants on the planet. Air is polluted due to the burning of fuels, exhaust gases from factories and industries, and mining operations. Now, air pollution becomes the most dangerous pollution that humanity ever faced. This causes many health effects on humans like respiratory, lung, and skin diseases, which also causes effects on plants, and animals to survive. Hence, air quality prediction and evaluation as becoming an important research area. In this paper, a machine learning-based prediction model is constructed for air quality forecasting. This model will help us to find the major pollutant present in the location along with the causes and sources of that particular pollutant. Air Quality Index value for India is used to predict air quality. The data is collected from various places throughout India so that the collected data is preprocessed to recover from null values, missing values, and duplicate values. The dataset is trained and tested with various machine learning algorithms like Logistic Regression, Naïve Bayes Classification, Random Forest, Support Vector Machine, K Nearest Neighbor, and Decision Tree algorithm in order to find the performance measurement of the above-mentioned algorithms. From this, the prediction model is constructed using the Decision Tree algorithm to predict the air quality, because it provides the best and highest accuracy of 100%. The machine learning-based air quality prediction model helps India meteorological department in predicting the future of air quality, and its status and depends on that they can take action.

Sign in / Sign up

Export Citation Format

Share Document