Tailpipe NOx Emissions Modeling of a Heavy-Duty Diesel Truck Using Deep Learning Methods
Bibliographic record
Abstract
This study develops deep learning (DL) long–short-term memory (LSTM) models to predict tailpipe nitrogen oxides (NOx) emissions using real-driving on-road data from a heavy-duty Class 8 truck. The dataset comprises over 4 million data points collected across 11,000 km of driving under diverse road, weather, and load conditions. The effects of dataset size, model complexity, and input feature set on model performance are investigated, with the largest training dataset containing around 3.5 million data points and the most complex model consisting of over 0.5 million parameters. Results show that a large and diverse training dataset is essential for achieving accurate prediction of both instantaneous and cumulative NOx emissions. Increasing model complexity only enhances model performance to a certain extent, depending on the size of the training dataset. The best-performing model developed in this study achieves an R2 higher than 0.9 for instantaneous NOx emissions and less than a 2% error for cumulative NOx emissions on the test data. Furthermore, the model achieves an F1 score above 0.9 in determining whether NOx emissions comply with emission standards. The developed DL tailpipe emission models in this study have diverse applications based on the amount and type of available input data, including engine and aftertreatment system control, diagnostics, and vehicle system-level simulations. These applications collectively contribute to minimizing NOx emissions of vehicles to meet stringent transportation emission standards.
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 | 0.000 |
| 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 | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".