Improving Accuracy in PM2.5 Interpolation Using AI and ML
Bibliographic record
Abstract
Air quality prediction is increasingly critical, especially considering recent events like the Canadian Wildfires releasing hazardous particulate matter over the US. The growing awareness of AI and machine learning have been increasingly used to facilitate applications in scientific studies, notably PM2.5 retrieval. PM2.5 retrieval uses machine learning (ML) techniques to estimate accurate PM2.5 values by considering predictors such as meteorological variables. One of the challenges in PM2.5 retrieval is dealing with different predictors with varying spatial resolutions. Prior to retrieval, predictor variables needed to be interpolated into a uniform grid, which currently lacks a standardized and validated model. Different interpolation methods (Inverse Distance Weighting (IDW), Kriging, and Natural Neighbor) offer techniques for estimating values in PM2.5 retrieval. Understanding the results involves assessing the spatial behavior of the data and validating the interpolation methods using metrics like Root Mean Squared Error (RMSE) and R-squared (R2). In this study, different interpolation models in ArcGIS Pro were used to interpolate meteorological variables. The models employed estimated values at a uniform grid with a spatial resolution of 1 km x 1 km. Interpolation methods were carefully evaluated using validation metrics to assess their effectiveness and accuracy in capturing spatial patterns and variations at this resolution.
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 | 0.005 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".