Machine Learning Based Surface Velocimetry
Bibliographic record
Abstract
Streamflow measurement is of great importance in hydrological research, water management and water infrastructure design. Traditional measurement methods typically employ intrusive techniques, and under certain conditions, obtaining accurate streamflow data with these techniques can be challenging because of safety concerns, especially in some critical circumstances, such as during flood flows. The advent of new instrumentation and technologies, and in particular advances in digital imagery, has led to the emergence of non-intrusive novel image-based technologies that can be used to estimate surface velocity, which in turn can be used to estimate streamflow. Image based technologies, most of which are based on correlation between consecutive images, have the potential for remote and on demand measurements and can provide data when the application of other traditional methods are not possible, reliable or safe. In this study, we present a novel machine learning based optical flow algorithm for streamflow surface velocimetry estimation. The developed algorithm is tested in different flow conditions and using drone and fixed photogrammetry. This method appears to outperform all the other available image-based surface velocimetry approaches (i.e. correlation based and classical optical flow methods). Moreover, this method requires the least user involvement for velocity estimation and thus reduces the impact or arbitrary choices linked to user expertise.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".