Why is Short-Time PM2.5 Forecast Difficult? The Effects of Sudden Events

Abstract

The existing forecast models for PM2.5 concentration can be classified into long term and short term models depending on whether the forecast is performed for the next few hours or days. However, short term forecast models feature narrow forecast time and are thus vulnerable in their sensitivity to soaring variations in air quality, defined as sudden events. The purpose of this work is to investigate the causes behind these sudden events. The PM2.5 data were obtained from monitoring devices deployed in Taichung as a part of the Airbox project. The data were fed into the current short-term forecast model to forecast air quality for the next hour. Event timing was detected by feeding the forecast result as an input to the sudden event detection model. We then combined the filtered timing with factors in environment and human activities. With the application of Hierarchy Clustering, the clustering result was analyzed to find the causes of sudden events. In the springtime and summertime, unexpected changes in rainfall and temperature were critical for forecast models. Moreover, unanticipated changes in the intensity of rainfall and wind are important in the autumn and winter. For human activities, crowds of commuters, tourists, and pilgrims also have influence on unusual air quality. By carefully considering the effects of sudden events, we believe that the response ability of short time forecast can improve significantly in the near future.

Combining Machine Learning and Numerical Simulation for High-Resolution PM2.5 Concentration Forecast

“…Without proper indicators of these out-of-domain factors, statistical models alone can hardly capture the associated pollution variations. 48 While CTM is supposed to have the ability to forecast these physical processes, the global GEOS-CF model was shown to unsatisfactorily simulate these processes in this study. We expect the forecast data from regional CTMs at a finer spatial resolution with better emission information and more accurate physical simulation processes, e.g., CMAQ, may help our framework better capture and forecast these sudden events.…”

Vayu: An Open-Source Toolbox for Visualization and Analysis of Crowd-Sourced Sensor Data

“…Correlation allows the user to understand the strength of a relationship between two variables. Such information is useful when building models for calibration [33] or forecasting [34]. The data correlation function allows the user to perform data correlation.…”

Federated Compressed Learning Edge Computing Framework with Ensuring Data Privacy for PM2.5 Prediction in Smart City Sensing Applications

“…These stations are assisted by thousands of small sensor nodes installed throughout Taiwan to generate precise measurements. A study indicates that the rate of pollutant distribution varies depending on the season, wind direction, condition of the industrial area, and how wide the area is monitored [ 38 ]. A large number of data is generated during the data acquisition, and the temporal patterns appear in the process.…”