An Air Quality Prediction Model Based on a Noise Reduction Self-Coding Deep Network

Abstract

Aiming at remedying the problem of low prediction accuracy of existing air pollutant prediction models, a denoising autoencoder deep network (DAEDN) model that is based on long short-term memory (LSTM) networks was designed. This model created a noise reduction autoencoder with an LSTM network to extract the inherent air quality characteristics of original monitoring data and to implement noise reduction processing on monitoring data to improve the accuracy of air quality predictions. The LSTM network structure in the DAEDN model was designed as bidirectional LSTM (Bi-LSTM) to solve the problem of a lag in the unidirectional LSTM prediction results and thereby to further improve the prediction accuracy of the prediction model. Using air pollutant time series data, the DAEDN model was trained using hourly PM2.5 concentration data collected in Beijing over 5 years. The experimental results show that the DAEDN model can extract more stable features from the noisy input after training was completed. The models were evaluated using RMSE and MAE, and the results show that the indexes are 15.504 and 6.789; compared with unidirectional LSTM, it is reduced by 7.33% and 5.87%, respectively. In addition, the new prediction model essentially considered the time series properties of the prediction of the concentration of spatial pollutants and the fully integrated environmental big data, such as air quality monitoring, meteorological monitoring, and forecasting.

Development of ecological management system for planted forest based on ELM deep learning algorithm

“…(2) Prediction model derivation of extreme learning machine deep learning algorithm: the deep learning algorithm of extreme learning machine integrates the idea of self-coding [26] and encodes the output by minimizing reconstruction error so that the output can approach the original input infinitely. This structure provides an abstract representation of the input and thus captures the deep features of the original input.…”

A Deep Learning Approach With Wavelets to Forecasting Tropospheric Ozone in a Tropical Metropolitan Region

“…Several works propose different techniques. In [6], it is proposed a denoising autoencoder deep network (DAEDN) model that is based on long short-term memory (LSTM). They created a noise reduction autoencoder with an LSTM network to extract the inherent air quality characteristics of original monitoring data to implement noise reduction processing to improve accuracy for their predictions, they report improvement versus their unidirectional LSTM model.…”