Deriving snow ablation upscaling relationships via machine learning
Bibliographic record
Abstract
<!--!introduction!--> Hydrologic processes are often measured and understood at the point scale. However, there is significant spatial variability in rates of snowmelt, sublimation, and snowfall over larger landscapes. The role of atmospheric and local terrain characteristics in controlling the variations between the small-scale and the bulk response to spatially heterogeneous mass and energy inputs is poorly understood. The application and identification of appropriate upscaling rules are necessary to translate small-scale descriptions of snow processes into constitutive relationships that are applicable at larger scales. As a proof of concept, this study examines the temporal and spatial variability of sublimation and snowmelt fluxes in a drainage basin in the Canadian Rockies using machine learning methods. In the approach, Raven, a fine-resolution hydrologic model, generates high-resolution fluxes and state variables used in training and testing machine learning models. This study involves estimating spatially averaged results from discretized fine-scaled models without explicit knowledge of detailed local response and with and without low-order statistics of state (e.g., the standard deviation of snow water equivalent). A series of experiments progressively increasing in complexity are used to test and validate that the upscaling methodology can successfully represent the impact of heterogeneity within the system. Weights from the machine learning models are then incorporated into a mass balance equation at a coarser resolution to demonstrate the efficacy of this upscaling methodology for practical hydrologic modeling.
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 | 0.003 |
| 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 | 0.000 |
| Research integrity | 0.000 | 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".