Air micro-station concentration prediction method based on LSTM neural network

Abstract

The invention discloses an air micro-station concentration prediction method based on an LSTM neural network. An isolated forest algorithm is adopted to preprocess pollutant concentration data obtained by an air micro-station, and a batch gradient descent algorithm is fused in deep learning to improve the stability of the whole system. Meanwhile, a Dropout algorithm and an L2 regularization algorithm are added into an input layer and a hidden layer to avoid the over-fitting phenomenon, and the whole algorithm is used for processing the complex space-time relation of particulate matter concentration, gas concentration input and multiple air quality outputs through a low-cost sensor.

Description

technical field

[0001] The invention relates to the field of environmental monitoring methods based on neural networks, in particular to an air micro-station concentration prediction method based on LSTM neural networks. Background technique

[0002] Air pollution has risen to dangerous levels due to increased transportation, increased population density, increased global warming and abrupt changes in the climate. There is a need to monitor and control pollution to create a healthier and non-toxic environment for human, animal and plant life. Environmental protection agencies and governments have made enormous efforts to reduce the impact of air pollution on communities. Detailed information on air pollution conditions can help researchers, policy makers, and developers manage and improve living conditions, so accurate air quality monitoring is essential. However, due to the complexity of ambient air factors, temperature, humidity, wind speed, etc. will affect the concentr...

Images