Calibration of Manning’s roughness coefficients for shallow-water flows on complex bathymetries using optimization algorithms and surrogate neural network models
Bibliographic record
Abstract
• The main features of a newly developed high-performance multi-GPU solver for the shallow-water equations are presented. This solver is used to build a database of highfidelity solutions. • A surrogate model based on an ensemble of neural networks is trained on the database. • Optimization algorithms are analyzed to identify the optimal Manning friction coefficients using the surrogate model. Notably, no convergence issue is observed and accurate solutions are obtained. • Hybrid Particle Swarm Optimization (HPSO) algorithm revealed robust and fast convergence. • The versatility of this approach makes it applicable to various domains. This paper presents an effective methodology for the automatic calibration of Manning’s roughness coefficients, which are crucial parameters for modeling shallow free-surface flows. Traditionally determined through empirical methods, these coefficients are subject to significant variability, making their determination challenging, especially in flow areas with complex bathymetry. The conventional trial-and-error approach, widely used to select these coefficients, is often tedious and time-consuming, particularly in applications constrained by time and data availability. The proposed methodology aims to determine the optimal values of Manning’s coefficients distributed over the flow domain while minimizing global discrepancies between simulations and field measurements. The calibration approach is formulated as an inverse optimization problem and addressed using metaheuristic optimization algorithms such as the Genetic Algorithm or Particle Swarm Optimization, combined with an ensemble model of deep neural networks. The database for training the neural networks is obtained using a newly developed finite volume-based shallow-water equations solver, parallelized on multiple GPUs, to generate large datasets of solutions for machine learning purposes. The performance of this approach is evaluated through various flow scenarios. Compared to conventional techniques, this methodology stands out for its simplicity, computational efficiency, and robustness. Additionally, Hybrid Particle Swarm Optimization (HPSO) proves to be particularly effective, notably for its speed. The developed codes are available at: https://github.com/ETS-GRANIT/CuteFlow .
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".