AI summary · may contain errors
Daily 1 km PM2.5 exposure estimates for Bangladesh (2020-01-01 to 2025-01-31) were generated with high accuracy (R²=0.95, RMSE=17.41 µg/m³) and capture extreme pollution.
Moving in Environmental Pollution, Environmental Research, medRxiv and Nature Communications.
Rebuilt
Nothing in this topic has moved yet this week.
Newest first · last 60 days
AI summary · may contain errors
Daily 1 km PM2.5 exposure estimates for Bangladesh (2020-01-01 to 2025-01-31) were generated with high accuracy (R²=0.95, RMSE=17.41 µg/m³) and capture extreme pollution.
AI summary · may contain errors
Real-time exceedance forecasting of Ambrosia artemisiifolia pollen in eight Central European urban sites improves 1-day F1 scores in Slovakia (0.67–0.82 vs 0.59–0.72) but converges by day 7.
AI summary · may contain errors
Linear regression best predicted one-day-ahead ambient ammonia (NH 3 ) at most of six Dutch sites, reaching R 2 = 0.84 at Zegveld after correcting for autocorrelation lag.
AI summary · may contain errors
A site-specific regression using nearby 59T fixed-site PM2.5 predicts missing 6-h DustTrak observations in Bangkok with LOOCV RMSE 6.43 μg/m3 and cross-validated R2 0.971.
AI summary · may contain errors
A physics-informed neural network inversion using TROPOMI data estimates NOx emissions over the Yangtze River Delta (2018–2023), resolving spatiotemporal changes including a COVID-19 reduction and later recovery.
AI summary · may contain errors
In central Taiwan, explainable machine learning linked PM 2.5 oxidative potential to nonlinear interactions among transition metals, water-soluble organic carbon, and aerosol liquid water, enabling source-specific mitigation leverage estimates.
AI summary · may contain errors
Winter PM 2.5 and PM 10 trends in northern Transylvania rise by up to +10 μgm -3 decade -1 (Cluj: +10.01 and +10.22 μgm -3 decade -1), with LISA identifying High-High worsening clusters.
AI summary · may contain errors
Long-term monitoring across 40 stations in the North-Eastern Italian Alps (2009–2023) shows NO declines up to -50% and PM declines around -30%, while O3 rises by roughly 20%.
AI summary · may contain errors
An upwind-transition-receptor framework for 1–4-day PM10 forecasts at three northern Taiwan receptors found the upwind-inclusive CatBoost model lowest aggregate RMSE at 11.04 μg m−3.
AI summary · may contain errors
Deep-learning reconstructions show HONO surface levels in global megacities changed from 2005–2021, including Beijing’s -47.4% (2013–2021) decline and Delhi’s +10.0% (2005–2018) rise.
AI summary · may contain errors
In a winter urban forest canopy in Shenyang, China, PM 2.5 and PM 10 were generally higher at 10 and 20 m than at 1.5 m, showing strong height-dependent stratification.
AI summary · may contain errors
XGBoost most competitively estimated marine PM 2.5 over the eastern China seas from 2019–2024, enabling mapping of spatial gradients and seasonal patterns.
AI summary · may contain errors
Deweathered surface ozone in Suzhou (2015–2022) is linked to OVOCs, CO, and alkenes, with OVOCs showing a clear positive relationship and alkenes/CO often negative.
AI summary · may contain errors
Hill-Urban (HU2) underlying surfaces in the Sichuan Basin show high frequencies of PM2.5 and O3 pollution events, exceeding 29% and 27%, respectively.
Journals this month
Topics moving, week to 17 Nov 2026
By field