Unsupervised machine learning method for analysis of snowfall datarecorded from test vehicle
Bibliographic record
Abstract
Systems that rely on the recognition of surroundings, such as autonomous vehicles (AVs) and unmanned aerial vehicles (UAVs), can be severely affected by weather stressors like rain and snow. Their proper functioning depends on advanced driverassistance systems (ADAS) which consist of sensing devices such as LiDAR, RADAR, and cameras. Low visibility range caused by intense precipitation as well as covering of sensor surfaces due to snow accumulation impede the operation of AVs at their full potential. Developing strategies to mitigate these factors is necessary to improve vehicle performance and ensure driver safety. For this, climatic wind tunnels (CWT), such as the one of the Automotive Centre of Excellence (ACE) team at Ontario Tech University, offer the possibility of simulating adverse conditions in controlled environments. Using this type of facility allows the generation of robust databases that cover different precipitation cases. However, it is necessary to use realistic precipitation parameters for this type of experiment, which remains a gap in literature. This paper proposes a Machine Learning-based method to identify recurring types of precipitation in southern Ontario. First, field measurements are performed on an outdoor test track using an SUV equipped with weather sensors. Then, a custom theoretical model is used to fit probability density functions (PDF) of particle size distributions (DSD) recorded during the experimental campaign. The parameters of the theoretical model form a data matrix which has its dimensionality reduced through Principal Component Analysis (PCA). From this new matrix, a K-means clustering model is used to identify patterns among the sampled cases. Finally, statistical analysis is performed within each cluster to identify its main features, such as average particle size, temperature, and relative humidity at the time of measurement. The results obtained represent a step forward for realistic climate simulations and more reliability for the design of adverse weather mitigation systems.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".