Bidirectional enhanced quantile gated recurrent unit for short-term forecasting of PM2.5 with emphasis on extreme events in Sri Lanka
Abstract
Air quality forecasting is critical for mitigating the health impacts of fine particulate matter (PM2.5). This study introduces a hybrid deep learning model, the bidirectional enhanced quantile gated recurrent unit (BEQ-GRU), for short-term forecasting of PM2.5 concentrations with explicit emphasis on extreme pollution occurrences. This model was applied to forecast PM2.5 levels in two high-risk Sri Lankan cities, Colombo and Kandy, delivering 24-hour and 48-hour ahead forecasts. Unlike conventional point-estimation models that optimise for mean accuracy, the BEQ-GRU targets the upper tail of the conditional distribution through an asymmetric quantile objective engineered to capture the heavy-tailed distribution of pollution exceedances. Beyond the architecture, this paper contributes a formal mathematical treatment of the method: (i) it is proved that the quantile loss function recovers the conditional quantile, and its 19:1 gradient asymmetry at τ = 0.95 is quantified; (ii) the “smoothing effect” of mean-optimal training is characterised through a peaks-over-threshold (POT) model, and it is proved that mean-trained detectors systematically miss an identifiable band of exceedances; and (iii) a decision-theoretic result (Theorem 1) is established, showing that thresholding a τ-quantile forecast is Bayes-optimal for cost-sensitive exceedance alarms, with the optimal level fixed by the public-health cost ratio as τ* = CFN/(CFN+CFP). This identity explains, rather than merely reports, the observed high-sensitivity, zero-false-alarm regime. Hourly data from October 2022 to December 2023 were analysed, incorporating meteorological variables and co-pollutant concentrations as predictors. Statistical, machine learning, and deep learning models were compared. Deep learning consistently outperformed conventional approaches, capturing more than 70% of 24-hour and 60% of 48-hour extreme spikes at both stations. The proposed BEQ-GRU achieved the best performance for Colombo, while a standard Bidirectional GRU was most effective for Kandy. The framework can be adapted, with minor modifications, for proactive air-quality management and public-health early warning.
Related
- Bi-Mamba-Load: A bidirectional structured state space model with sequence relationship adaptive perception for electricity load forecasting
- Runout mechanism of landslides in alluvial basins with emphasis on the impact and erosion effects
- Multisystemic effects of nanoplastics in immature rats subjected to prolonged oral exposure with particular emphasis on prooxidant potential
- Mapping soil salinity and prediction uncertainty across different depths using quantile regression forests
- Hybrid stacked bidirectional deep learning with attention based air pollution prediction for environmental sustainability
BibTeX
@misc{jayasinghe2026bidirectional,
title = {{Bidirectional enhanced quantile gated recurrent unit for short-term forecasting of PM2.5 with emphasis on extreme events in Sri Lanka}},
author = {Anjana Jayasinghe and Chandima Tilakaratne},
howpublished = {EarthArXiv},
year = {2026},
month = sep,
doi = {10.31223/x5r219},
url = {https://eartharxiv.org/repository/view/14766/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Bidirectional enhanced quantile gated recurrent unit for short-term forecasting of PM2.5 with emphasis on extreme events in Sri Lanka
AU - Anjana Jayasinghe
AU - Chandima Tilakaratne
PY - 2026
DA - 2026/09/03
PB - EarthArXiv
DO - 10.31223/x5r219
UR - https://eartharxiv.org/repository/view/14766/
AB - Air quality forecasting is critical for mitigating the health impacts of fine particulate matter (PM2.5). This study introduces a hybrid deep learning model, the bidirectional enhanced quantile gated recurrent unit (BEQ-GRU), for short-term forecasting of PM2.5 concentrations with explicit emphasis on extreme pollution occurrences. This model was applied to forecast PM2.5 levels in two high-risk Sri Lankan cities, Colombo and Kandy, delivering 24-hour and 48-hour ahead forecasts. Unlike conventional point-estimation models that optimise for mean accuracy, the BEQ-GRU targets the upper tail of the conditional distribution through an asymmetric quantile objective engineered to capture the heavy-tailed distribution of pollution exceedances. Beyond the architecture, this paper contributes a formal mathematical treatment of the method: (i) it is proved that the quantile loss function recovers the conditional quantile, and its 19:1 gradient asymmetry at τ = 0.95 is quantified; (ii) the “smoothing effect” of mean-optimal training is characterised through a peaks-over-threshold (POT) model, and it is proved that mean-trained detectors systematically miss an identifiable band of exceedances; and (iii) a decision-theoretic result (Theorem 1) is established, showing that thresholding a τ-quantile forecast is Bayes-optimal for cost-sensitive exceedance alarms, with the optimal level fixed by the public-health cost ratio as τ* = CFN/(CFN+CFP). This identity explains, rather than merely reports, the observed high-sensitivity, zero-false-alarm regime. Hourly data from October 2022 to December 2023 were analysed, incorporating meteorological variables and co-pollutant concentrations as predictors. Statistical, machine learning, and deep learning models were compared. Deep learning consistently outperformed conventional approaches, capturing more than 70% of 24-hour and 60% of 48-hour extreme spikes at both stations. The proposed BEQ-GRU achieved the best performance for Colombo, while a standard Bidirectional GRU was most effective for Kandy. The framework can be adapted, with minor modifications, for proactive air-quality management and public-health early warning.
ER -