Spatio-temporal-Aware Sparse Denoising Autoencoder Neural Network for Air Quality Prediction

摘要

Nowadays, air quality prediction is an important task. The main way to solve this problem is to use neural network, which are robust enough to handle time sensitive data. In this paper, we propose a novel spatio-temporal-aware sparse denoising autoencoding neural network architecture for this task. Our model makes full use of the spatio-temporal characteristics of the data, thus the accuracy of the prediction is improved. Experiments on historical dataset released by China National Environmental Monitoring Station and China Meteorological Administration show that our model achieves better performances than other models.