| Abstract: |
| Accurate reporting and forecasting of $PM_{2.5}$ concentration are important for improving public health. We propose a partial differential equation (PDE), specially, a linear diffusive equation, to describe the spatial-temporal characteristics of $PM_{2.5}$ in order to make short-term prediction. We present the temporal and spatial patterns based on a real dataset from China`s National Environmental
Monitoring and validate the proposed PDE model in terms of predicting the $PM_{2.5}$ concentration of the next day by the former days` history data. Our experiment results show that the PDE model is
able to characterize and predict the process of $PM_{2.5}$ transport. To our knowledge, this
is the first attempt to use PDE-based model to study
the $PM_{2.5}$. |
|