Forecasts of tropospheric ozone in the Metropolitan Area of Rio de Janeiro based on missing data imputation and multivariate calibration techniques

• Published in: Environmental monitoring and assessment Vol. 193; no. 8; p. 531
• Main Authors: de Oliveira, Rafael C. G., Cunha, Camilla L., Tôrres, Alexandre R., Corrêa, Sergio M.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.08.2021; Springer Nature B.V
• Subjects: Air; Air monitoring; Air pollution; Air quality; Algorithms; Atmospheric Protection/Air Quality Control/Air Pollution; Calibration; Carbon monoxide; Earth and Environmental Science; Ecology; Ecotoxicology; Environment; Environmental Management; Environmental monitoring; Environmental science; Mean square errors; Methods; Metropolitan areas; Missing data; Modelling; Monitoring systems; Monitoring/Environmental Analysis; Multivariate analysis; Nitrogen oxides; Ozone; Photochemicals; Pollutants; Predictions; Relative humidity; Solar radiation; Stations; Support vector machines; Troposphere; Tropospheric ozone; Wind speed; Brazil; Rio de Janeiro Brazil; Wilcoxon test; MissForest; Missing data; Ozone; Random forest; Support vector machine

Multivariate calibration based on partial least squares, random forest, and support vector machine methods, combined with the MissForest imputation algorithm, was used to understand the interaction between ozone and nitrogen oxides, carbon monoxide, wind speed, solar radiation, temperature, relative...