Development and Validation of a Sub-National, Satellite-Based Land-Use Regression Model for Annual Nitrogen Dioxide Concentrations in North-Western China
Bibliographic record
Abstract
Existing national- or continental-scale models of nitrogen dioxide (NO2) exposure have a limited capacity to capture subnational spatial variability in sparsely-populated parts of the world where NO2 sources may vary. To test and validate our approach, we developed a land-use regression (LUR) model for NO2 for Ningxia Hui Autonomous Region (NHAR) and surrounding areas, a small rural province in north-western China. Using hourly NO2 measurements from 105 continuous monitoring sites in 2019, a supervised, forward addition, linear regression approach was adopted to develop the model, assessing 270 potential predictor variables, including tropospheric NO2, optically measured by the Aura satellite. The final model was cross-validated (5-fold cross validation), and its historical performance (back to 2014) assessed using 41 independent monitoring sites not used for model development. The final model captured 63% of annual NO2 in NHAR (RMSE: 6 ppb (21% of the mean of all monitoring sites)) and contiguous parts of Inner Mongolia, Gansu, and Shaanxi Provinces. Cross-validation and independent evaluation against historical data yielded adjusted R2 values that were 1% and 10% lower than the model development values, respectively, with comparable RMSE. The findings suggest that a parsimonious, satellite-based LUR model is robust and can be used to capture spatial contrasts in annual NO2 in the relatively sparsely-populated areas in NHAR and neighbouring provinces.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".