Significance of Meteorological Feature Selection and Seasonal Variation on Performance and Calibration of a Low-Cost Particle Sensor
Bibliographic record
Abstract
Poor air quality is a major environmental concern worldwide, but people living in low- and middle-income countries are disproportionately affected. Measurement of PM2.5 is essential for establishing regulatory standards and developing policy frameworks. Low-cost sensors (LCS) can construct a high spatiotemporal resolution PM2.5 network, but the calibration dependencies and subject to biases of LCS due to variable meteorological parameters limit their deployment for air-quality measurements. This study used data collected from June 2019 to April 2021 from a PurpleAir Monitor and Met One Instruments’ Model BAM 1020 as a reference instrument at Alberta, Canada. The objective of this study is to identify the relevant meteorological parameters for each season that significantly affect the performance of LCS. The meteorological features considered are relative humidity (RH), temperature (T), wind speed (WS) and wind direction (WD). This study applied Multiple Linear Regression (MLR), k-Nearest Neighbor (kNN), Random Forest (RF) and Gradient Boosting (GB) models with varying features in a stepwise manner across all the seasons, and only the best results are presented in this study. Improvement in the performance of calibration models is observed by incorporating different features for different seasons. The best performance is achieved when RF is applied but with different features for different seasons. The significant meteorological features are PM2.5_LCS in Summer, PM2.5_LCS, RH and T in Autumn, PM2.5_LCS, T and WS in Winter and PM2.5_LCS, RH, T and WS in Spring. The improvement in R2 for each season (values in parentheses) is Summer (0.66–0.94), Autumn (0.73–0.96), Winter (0.70–0.95) and Spring (0.70–0.94). This study signifies selecting the right combination of models and features to attain the best results for LCS calibration.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".