Figure 5 - uploaded by Harrison Ikhumhen
Content may be subject to copyright.
(a) Inverse distance weighted interpolation based on weighted sample point distance. (b) Interpolated IDW surface from elevation vector points (see online version for colours)
Context in source publication
Context 1
... this study, the ArcGIS tool known as the IDW interpolation approach was applied to analyse the spatial data of the PM emission concentration in the study region. This method involves the weighing of sample points during interpolation such that a point in relation to another declines based on distance from an unknown point with the potential of being created (see Figure 5). The weighing of the sample points is assigned through the use of weighing coefficient which is known to control how the influence of the weighing will decline with the increment in distance from the new point. ...
Citations
Air pollution is a significant global environmental challenge that can cause health problems affecting everyone on the planet without any geographical boundary. It has a substantial impact directly or indirectly not only on human health but on social and economic activities as well. Researchers worldwide are working to evaluate and predict the air quality index using advanced computational models. These models have drastically altered how we think about and approach API prediction (Air Pollution Index). The primary intent of this paper is to highlight the suitable machine learning models on remotely sensed Sentinel-5P sensor data in assessing and predicting air pollution before, during, and after the lockdown enforced due to the COVID-19 pandemic. This work includes the assessment and prediction of API using four air-polluting parameters- Nitrogen Dioxide, Ozone, Carbon Monoxide, and Sulphur Dioxide in four metropolitan cities of India - Kolkata, Mumbai, Delhi, and Chennai. The paper used Markov Chain as an operator for predicting the AQI state and verified it using ground-level and satellite data. The model’s accuracy was estimated using the predicted dataset RMSE (Root Mean Square Error). The outcome of the prediction model was also validated with actual data, which substantiates the finding that during this lockdown period of the COVID-19 pandemic, NO\(_2\) concentration was reduced significantly due to less traffic and energy production from industries.
