Assessing spatial variation of PM2.5 and NO2 across Europe using Geographically Weighted Regression
Bibliographic record
Abstract
OPS 49: Air pollution exposure methods, Room 412, Floor 4, August 27, 2019, 10:30 AM - 12:00 PM Background/ Aim Standard Land Use Regression (LUR) models assume the relationships between air pollution and predictors are constant across spaces, which may not be true. Geographically Weighted Regression (GWR) can deal with spatially varying relationships. We aimed to develop Europe-wide GWR models, and to check whether they model spatial variability of air pollution better than the standard models. Methods: Air pollution models were developed based on 2010 routine monitoring data from the AIRBASE (543 sites for PM2.5 and 2399 sites for NO2), using satellite observations, chemical transport model estimates and land use variables as potential predictor variables. We first built a standard LUR model across Europe using a supervised step-forward linear regression. Predictor variables selected by the standard model were included in a GWR model to allow spatially varying coefficients. Kriging was performed on the residual variation from the LUR models and added to the pollution estimates. We evaluated the models by performing five-fold cross-validation (CV) and by external validation (EV) using annual average concentrations measured at 416 (PM2.5) and 1396 sites (NO2) from the ESCAPE study. Results: The PM2.5 GWR model performed well across Europe (CV-R2 0.68; EV-R2 0.70). Kriging only slightly improved the model performance (CV-R2 0.69; EV-R2 0.73). The GWR model outperformed the standard model (CV-R2 0.60; EV-R2 0.53) and the standard model plus kriging (CV-R2 0.64; EV-R2 0.67). Chemical transport model estimates and satellite observations were two of the most important predictors for the GWR model. The regression coefficient of road density was higher in Western Europe and lower in northern and southern Europe. The NO2 GWR model had similar performance as the standard model. No reliable kriging could be fit through residuals of the NO2 estimates. Conclusions: Geographically weighted regression modestly improved modeling of spatial variation of PM2.5 across Europe compared to a standard model.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".