The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLIV-4/W3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-4/W3-2020, 21–27, 2020
https://doi.org/10.5194/isprs-archives-XLIV-4-W3-2020-21-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-4/W3-2020, 21–27, 2020
https://doi.org/10.5194/isprs-archives-XLIV-4-W3-2020-21-2020

  23 Nov 2020

23 Nov 2020

PREDICTION OF POLLUTANT CONCENTRATIONS BY METEOROLOGICAL DATA USING MACHINE LEARNING ALGORITHMS

K. Alpan and B. Sekeroglu K. Alpan and B. Sekeroglu
  • NEU, Information Systems Engineering, 99138 Nicosia, TRNC, Mersin 10, Turkey

Keywords: Air Pollution, Prediction, Machine Learning, Pollutant Concentrations, Meteorological Data, Smart City

Abstract. Air pollution, which is one of the biggest problems created by the developing world, reaches severe levels, especially in urban areas. Weather stations established at certain points in countries regularly obtain data and inform people about air quality. In Smart City applications, it is aimed to perform this process with higher speed and accuracy by collecting data with thousands of sensors based on the Internet of Things. At this stage, artificial intelligence and machine learning plays a vital role in analyzing the data to be obtained. In this study, six pollutant concentrations; particulate matters (PM2.5 and PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2), Ozone (O3), and carbon monoxide (CO), were predicted using three basic machine learning algorithms, namely, random forest, decision tree and support vector regression, by considering only meteorological data. Experiments on two different datasets showed that the random forest has a high prediction capacity (R2: 0.74–0.86), and high-accuracy predictions can be performed on pollutant concentrations using only meteorological data. This and further studies based on meteorological data would help to reduce the number of devices in Smart City applications and will make it more cost-effective.