Combination of data-driven models and interpolation technique to develop of PM10 map for Hanoi, Vietnam

Abstract

The degradation of air quality is the most concerned issue of our society due to its harmful impacts on human health, especially in cities with rapid urbanization and population growth like Hanoi, the capital of Vietnam. This study aims at developing a new approach that combines data-driven models and interpolation technique to develop the PM10 concentration maps from meteorological factors for the central area of Hanoi. Data-driven models that relate the PM10 concentration with the meteorological factors at the air quality monitoring stations in the study area were developed using the Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) algorithms. Models’ performance comparison showed that ANN models yielded better goodness-of-fit indices than MLR models at all stations in the study area with average coefficient of correlation (r) and Nash–Sutcliffe Efficiency Index (NSE) of 0.51 and 0.34 for the former, and 0.7 and 0.49 for the latter. These indices indicates that the ANN-based data-driven models outperformed the MLR-based models. Thus, the ANN-based models and the Inverse Distance Weighting (IDW) interpolation technique were then combined for mapping the monthly PM10 concentration with a spatial resolution of 1 km from global meteorological data. With this combination, the PM10 concentration maps account for both local PM10 concentration and impacts of spatio-temporal variations of meteorological factors on the PM10 concentration. This study provides a promising method to predict the PM concentration with a high spatio-temporal resolution from meteorological data.

Statistical modeling approach for PM10 prediction before and during confinement by COVID-19 in South Lima, Perú

“…9b) presented a moderate correlation (r = 0.5753) unlike the other two 3D models. However, Table 5 shows that the RMSE for the MLR was higher (RMSE= 12.9226) relative to the others, but comparable to the modeling errors of another study (RMSE = 10.64 − 26.08, T − AP − RH − WS) 45 . The 3D models had smaller errors ( RMSE = 0.0989 a 0.2776) because the algorithm for 3D models by regres- www.nature.com/scientificreports/ sion fitting generates more complex interactions between input and output data.…”

“…The 3D models had smaller errors ( RMSE = 0.0989 a 0.2776) because the algorithm for 3D models by regres- www.nature.com/scientificreports/ sion fitting generates more complex interactions between input and output data. The NSE criterion for MLR (NSE=0.3804) was closer to unity, and was also comparable to Nguyen's fitting errors 45 (between 0.26 and 0.53 ).…”

“…Poly2D: Two-dimensional polynomial function For these tests, 95% reliability, correlation coefficient (r) and coefficient of determination (R 2 ) were considered 45,46 .…”

Controlling Phosphorus Transport in Poyang Lake Basin under the Constraints of Climate Change and Crop Yield Increase

“…It is generally considered that a value greater than 0.5 is acceptable [39][40][41]. NSE is in the range of −∞ to 1; NSE = 1 means that the modeling and observation values match perfectly; and NSE ≤ 0 means that the model prediction has the same or lower accuracy as the observation average [42]. Generally, NSE > 0.65 is required to be considered an acceptable model performance [43,44].…”