Convolutional neural networks for image-based sediment detection applied to a large terrestrial and airborne dataset
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract. Image-based grain sizing has been used to measure grain size more efficiently compared with traditional methods (e.g., sieving and Wolman pebble count). However, current methods to automatically detect individual grains are largely based on detecting grain interstices from image intensity which not only require a significant level of expertise for parameter tuning but also underperform when they are applied to suboptimal environments (e.g., dense organic debris, various sediment lithology). We proposed a model (GrainID) based on convolutional neural networks to measure grain size in a diverse range of fluvial environments. A dataset of more than 125 000 grains from flume and field measurements were compiled to develop GrainID. Tests were performed to compare the predictive ability of GrainID with sieving, manual labeling, Wolman pebble counts (Wolman, 1954) and BASEGRAIN (Detert and Weitbrecht, 2012). When compared with the sieving results for a sandy-gravel bed, GrainID yielded high predictive accuracy (comparable to the performance of manual labeling) and outperformed BASEGRAIN and Wolman pebble counts (especially for small grains). For the entire evaluation dataset, GrainID once again showed fewer predictive errors and significantly lower variation in results in comparison with BASEGRAIN and Wolman pebble counts and maintained this advantage even in uncalibrated rivers with drone images. Moreover, the existence of vegetation and noise have little influence on the performance of GrainID. Analysis indicated that GrainID performed optimally when the image resolution is higher than 1.8 mm pixel−1, the image tile size is 512×512 pixels and the grain area truncation values (the area of smallest detectable grains) were equal to 18–25 pixels.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 it