
A novel WaveCatBoost architecture that combines the maximal overlapping discrete wavelet transform (MODWT) with the CatBoost model to generate accurate and robust real-time forecasts of air pollutant concentrations.


coremsg

accurate-real-time-forecasting-of-regional-air-pollutant-concentrations-using-a-novel-wavelet-based-catboost-model


Accurate Real-Time Forecasting of Regional Air Pollutant Concentrations using a Novel Wavelet-Based CatBoost Model


title_rewrite


This paper presents a novel forecasting methodology that leverages both past and future covariates, such as weather forecasts and calendar events, to accurately predict NO2 concentrations using Spatiotemporal Graph Neural Networks (STGNNs).


leveraging-future-covariates-for-accurate-no2-forecasting-using-spatiotemporal-graph-neural-networks


Leveraging Future Covariates for Accurate NO2 Forecasting using Spatiotemporal Graph Neural Networks
