Evaluating forecast baselines and network representativeness for daily PM2.5 in the Kathmandu Valley, Nepal
Abstract
An order-fair attribution of daily PM2.5 predictability in the Kathmandu Valley assigns 72% of achievable error reduction to persistence, 19% to meteorology and 9% to day-of-year climatology, with the latter two largely redundant; no fitted model, including random forests and gradient boosting tuned by nested chronological cross-validation, outperforms an unfitted lag-1 forecast (11.22 µg m-3). We establish this using four years (2021-2024; 5,138 station-days) of daily PM2.5, PM10 and total suspended particulates from six Department of Environment stations, together with meteorological observations including an hourly 10 m wind record, to test two assumptions common in machine-learning studies of this basin, which report coefficients of determination of 0.80-0.91 pooled across seasons without naive baselines and treat the monitoring network as a set of independent sampling points. Because a three-month season retains a strong sub-seasonal trend, day-to-day relationships are evaluated after removing a day-of-year climatology from both response and predictor, fitted on training data only; confidence intervals account for temporal autocorrelation and for clustering within six stations. Cross-station correlation of daily log PM2.5 is 0.86 (95% CI 0.79-0.91), falling to 0.61 (0.52-0.72) after deseasonalisation, with no decay detectable over the 2-13 km network span, though the design resolves only decay larger than 0.11-0.21 r- units. A pooled model attributes 71% of permutation importance to minimum temperature; after deseasonalisation, held-out R2 falls from 0.64 to 0.10 and that importance disappears. Predictive skill in this basin should be reported against climatology and persistence baselines, and pooled meteorological importances should not be read as physical attribution.
Related
- Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones
- Assessing the vertical representativeness of ERA5 humidity for interpreting satellite upper-tropospheric humidity trends
- The representativeness of observed Δt in calculating formation and growth rates of newly formed atmospheric particles – hypothesis and examination
- Enhancing urban water resilience through green infrastructure in Kathmandu, Nepal
- Evaluating the efficacy of closing the current European network of marine protected areas to mobile bottom-contacting fishing gears
BibTeX
@misc{poudel2026evaluating,
title = {{Evaluating forecast baselines and network representativeness for daily PM2.5 in the Kathmandu Valley, Nepal}},
author = {Buddhi Sagar Poudel and Nita Khatri and Namrata Mishra and Dhiraj Pradhananga},
howpublished = {EarthArXiv},
year = {2026},
month = sep,
doi = {10.31223/x5fj67},
url = {https://eartharxiv.org/repository/view/14784/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Evaluating forecast baselines and network representativeness for daily PM2.5 in the Kathmandu Valley, Nepal
AU - Buddhi Sagar Poudel
AU - Nita Khatri
AU - Namrata Mishra
AU - Dhiraj Pradhananga
PY - 2026
DA - 2026/09/04
PB - EarthArXiv
DO - 10.31223/x5fj67
UR - https://eartharxiv.org/repository/view/14784/
AB - An order-fair attribution of daily PM2.5 predictability in the Kathmandu Valley assigns 72% of achievable error reduction to persistence, 19% to meteorology and 9% to day-of-year climatology, with the latter two largely redundant; no fitted model, including random forests and gradient boosting tuned by nested chronological cross-validation, outperforms an unfitted lag-1 forecast (11.22 µg m-3). We establish this using four years (2021-2024; 5,138 station-days) of daily PM2.5, PM10 and total suspended particulates from six Department of Environment stations, together with meteorological observations including an hourly 10 m wind record, to test two assumptions common in machine-learning studies of this basin, which report coefficients of determination of 0.80-0.91 pooled across seasons without naive baselines and treat the monitoring network as a set of independent sampling points. Because a three-month season retains a strong sub-seasonal trend, day-to-day relationships are evaluated after removing a day-of-year climatology from both response and predictor, fitted on training data only; confidence intervals account for temporal autocorrelation and for clustering within six stations. Cross-station correlation of daily log PM2.5 is 0.86 (95% CI 0.79-0.91), falling to 0.61 (0.52-0.72) after deseasonalisation, with no decay detectable over the 2-13 km network span, though the design resolves only decay larger than 0.11-0.21 r- units. A pooled model attributes 71% of permutation importance to minimum temperature; after deseasonalisation, held-out R2 falls from 0.64 to 0.10 and that importance disappears. Predictive skill in this basin should be reported against climatology and persistence baselines, and pooled meteorological importances should not be read as physical attribution.
ER -