Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | |
| Publié: |
Zenodo
2026
|
| Sujets: | |
| Accès en ligne: | https://doi.org/10.5281/zenodo.20023567 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Table des matières:
- <p><strong>Description:</strong></p> <p>This dataset contains the numerical simulation results and corresponding topographic data used in the study published in the paper: <em>"Multi-task super-resolution deep learning overcomes computational bottlenecks in high-fidelity debris flow modeling"</em>.</p> <p>The data is stored in GeoTIFF format and organized into a hierarchical folder structure based on the location and resolution of the debris flow simulation results. The repository includes data for the primary study area (Lantau) at multiple resolutions and a separate, independent test area (C210) for model inference validation.</p> <h3>1. Study Area: Lantau (<code class="hyc-common-markdown__code__inline">lantau_*/</code>)</h3> <p>Data for the Lantau Island, used primarily for model training and validation. It includes simulations at a fine resolution (5m) and two coarser resolutions (15m, 30m). Each subfolder contains the following raster files:</p> <ul class="ybc-ul-component"> <li class="ybc-li-component ybc-li-component_ul"> <p><strong><code class="hyc-common-markdown__code__inline">lantau_5m/</code>(Fine-Grid Simulation Outputs):</strong></p> <p>This directory stores the core simulation outputs at <strong>5-meter resolution</strong>.</p> <ul class="ybc-ul-component"> <li class="ybc-li-component ybc-li-component_ul"> <p><strong>File Naming Convention:</strong> <code class="hyc-common-markdown__code__inline">c_{catchment_id}_d_{time}.tif</code>(Debris Flow Depth) and <code class="hyc-common-markdown__code__inline">c_{catchment_id}_v_{time}.tif</code>(Debris Flow Velocity).</p> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><strong>Examples:</strong> <code class="hyc-common-markdown__code__inline">c_25_d_0.0.tif</code>(Depth at catchment 25, t=0.0s), <code class="hyc-common-markdown__code__inline">c_43_v_1320.0.tif</code>(Velocity at catchment 43, t=1320.0s).</p> </li> </ul> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><strong><code class="hyc-common-markdown__code__inline">lantau_5m_mask/</code>(Inundation Extent):</strong></p> <p>Binary masks indicating the final inundation extent derived from the 5m simulations (values typically 0 for non-inundated and 1 for inundated cells).</p> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><strong><code class="hyc-common-markdown__code__inline">lantau_5m_topo/</code>(Topographic Derivatives):</strong></p> <p>Input features for the deep learning model derived from the 5m DEM.</p> <ul class="ybc-ul-component"> <li class="ybc-li-component ybc-li-component_ul"> <p><strong>Files:</strong> <code class="hyc-common-markdown__code__inline">c_{catchment_id}_acc.tif</code>(Flow Accumulation), <code class="hyc-common-markdown__code__inline">c_{catchment_id}_ele.tif</code>(Elevation), <code class="hyc-common-markdown__code__inline">c_{catchment_id}_slp.tif</code>(Slope), <code class="hyc-common-markdown__code__inline">c_{catchment_id}_profile.tif</code>(Profile Curvature), <code class="hyc-common-markdown__code__inline">c_{catchment_id}_plan.tif</code>(Plan Curvature).</p> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><em>Note:</em>The curvature files were generated to support the input parameter sensitivity analysis performed during the manuscript revision phase.</p> </li> </ul> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><strong><code class="hyc-common-markdown__code__inline">lantau_15m/</code>& <code class="hyc-common-markdown__code__inline">lantau_30m/</code>(Coarse-Grid Simulation Outputs):</strong></p> <p>These folders contain the corresponding depth and velocity simulation results at <strong>15-meter</strong> and <strong>30-meter resolutions</strong>, respectively. They serve as the "low-fidelity" data used to demonstrate the super-resolution capabilities of the proposed model.</p> </li> </ul> <h3>2. Independent Test Area: C210 (<code class="hyc-common-markdown__code__inline">c210_*/</code>)</h3> <p>This directory contains data for catchment ID <strong>210</strong>, which was held out during the training process and used exclusively for the final model inference and application testing.</p> <ul class="ybc-ul-component"> <li class="ybc-li-component ybc-li-component_ul"> <p><strong>Structure:</strong> The structure mirrors the Lantau dataset, containing <code class="hyc-common-markdown__code__inline">c210_5m</code>, <code class="hyc-common-markdown__code__inline">c210_15m</code>, and <code class="hyc-common-markdown__code__inline">c210_30m</code>folders.</p> </li> <li class="ybc-li-component ybc-li-component_ul"> <p><strong>Purpose:</strong> These files allow users to validate the model's generalization capabilities on unseen geographical terrain.</p> </li> </ul>