A new dynamic approach using data-driven and machine learning models for forecasting particulate matter in Dhaka megacity
Bibliographic record
Abstract
This study conducts a comprehensive examination of six machine learning models for forecasting PM 2.5 and PM 10 concentrations in Dhaka, Bangladesh, employing average data from three air monitoring stations - Darus Salam, Parliament Area, and BARC established by the Department of Environment (DoE). The analysis utilizes average data from three air monitoring stations spanning January 2016 to December 2022, with meticulous pre-processing to ensure data quality. The employed models for analysis include ARIMA, ANN, ELM, ETS, NAÏVE, and TBATS. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) are used to validate and rigorously compare model performance. ARIMA shows the best performance for PM 2.5 , while TBATS is slightly better for PM 10 predictions. These insights hold significant value for air quality management in Dhaka, enabling informed and proactive measures to counter particulate pollution and its adverse health implications. Furthermore, this study demonstrates the potential of machine learning models in accounting for local factors influencing air quality, complementing existing research on combining air quality models. This opens doors for further developing even better hybrid models, including weather data and exploring advanced ensemble techniques. • Utilized advanced machine learning model to predict air pollution of Dhaka. • ARIMA and TBATS outperformed other models for PM 2.5 and PM 10 prediction, respectively. • Leveraged real-world air quality data to capture local factors influencing pollution levels. • Demonstrated the potential of machine learning for developing sophisticated air quality forecasting tools. • Findings provide valuable guidance for policymakers to address air pollution challenges.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 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".