Air quality prediction by machine learning models: A predictive study on the indian coastal city of Visakhapatnam
Bibliographic record
Abstract
Clean air is critical component for health and survival of human and wildlife, as atmospheric pollution is associated with a number of significant diseases including cancer. However, due to rapid industrialization and population growth, activities such as transportation, household, agricultural, and industrial processes contribute to air pollution. As a result, air pollution has become a significant problem in many cities, especially in emerging countries like India. To maintain ambient air quality, regular monitoring and forecasting of air pollution is necessary. For that purpose, machine learning has emerged as a promising technique for predicting the Air Quality Index (AQI) compared to conventional methods. Here we apply the AQI to the city of Visakhapatnam, Andhra Pradesh, India, focusing on 12 contaminants and 10 meteorological parameters from July 2017 to September 2022. For this purpose, we employed several machine learning models, including LightGBM, Random Forest, Catboost, Adaboost, and XGBoost. The results show that the Catboost model outperformed other models with an R2 correlation coefficient of 0.9998, a mean absolute error (MAE) of 0.60, a mean square error (MSE) of 0.58, and a root mean square error (RMSE) of 0.76. The Adaboost model had the least effective prediction with an R2 correlation coefficient of 0.9753. In summary, machine learning is a promising technique for predicting AQI with Catboost being the best-performing model for AQI prediction. Moreover, by leveraging historical data and machine learning algorithms enables accurate predictions of future urban air quality levels on a global scale.
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 | 0.001 | 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 | 0.000 |
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".