[general]
icon=icon.png
name=Bathymetrix-AI
qgisMinimumVersion=3.22
qgisMaximumVersion=4.99
version=6.4
author=Mohamed Aly Nasef
email=Eng.m.nasef2017@gmail.com
description=An advanced Machine Learning pipeline for Satellite-Derived Bathymetry (SDB). Features ICESat-2 integration, In-Situ Data filtering, Spatial Residual Stacking, and Multi-Year Coastal Dynamics.

about=<h3>Bathymetrix-AI: Advanced SDB Modeling & Coastal Dynamics</h3>
    <p><b>Bathymetrix-AI</b> is a specialized QGIS research toolkit designed to derive high-precision bathymetry from corrected multispectral satellite imagery. It systematically integrates physics-based corrections with data-driven Machine Learning to overcome traditional SDB limitations, and features a state-of-the-art Temporal Intelligence engine for coastal monitoring.</p>
    
    <p><b>Core Workflow (The 5-Phase System):</b></p>
    <ul>
        <li><b>Phase 01: Advanced Pre-processing:</b> Sun-glint correction (Hedley), <b>Advanced Water Masking</b> using 3-Indices (NDWI, MNDWI, NWI), physics-based Log-Ratio features computation (including NDWI, Log(Green)/Log(NIR), Log(Red)/Log(NIR)), and a <b>Deep Water Filter</b> customized for ML algorithms (featuring dynamic Elbow Point Detection and Polygon masking).</li>
        <li><b>Phase 02: Robust Filtering:</b> Noise removal using Linear RANSAC, LS Variance Fit, or Huber Variance Fit (Zhang et al., 2021).</li>
        <li><b>Phase 03: Global Auto-ML & Feature Analysis:</b> Optional feature correlation analysis (<b>Automatic-RANSAC, Automatic-Random Forest</b>), competitive benchmarking of <b>15+ ML algorithms</b> (including XGBoost, LightGBM, CatBoost), independent <b>Spatial Cross-Validation</b>, and hyperparameter optimization via Random Search, Grid Search, or Bayesian. Features automated chunk-based processing to prevent memory errors with large datasets.</li>
        <li><b>Phase 04: Adaptive Refinement:</b> Spatially localized corrections, independent <b>Spatial Cross-Validation</b>, and residual analysis (Alevizos, 2020) to fix local biases.</li>
        <li><b>Phase 05: Validation & Reporting:</b> Independent accuracy assessment on unseen test data.</li>
    </ul>

    <p><b>Standalone Modules:</b></p>
    <ul>
        <li><b>Coastal Dynamics (Temporal Intelligence):</b> Multi-year <b>Volumetric Erosion/Accretion Trend</b> using Linear Regression, <b>Morphological Stability Index (MSI)</b>, and <b>Shoreline Migration Polygons</b>. Features auto-detection of depth/elevation formats and automated HTML reporting.</li>
        <li><b>ICESat-2 Downloader:</b> Specialized tool for querying and downloading ICESat-2 (ATL24) LiDAR data directly from NSIDC.</li>
    </ul>

    <p><b>Key References:</b><br>
    - <b>Stumpf et al. (2003):</b> Log-Ratio Algorithm for SDB inversion.<br>
    - <b>Hedley et al. (2005):</b> Physics-based sun-glint correction.<br>
    - <b>Fischler & Bolles (1981):</b> RANSAC algorithm for ICESat-2 data filtering.<br>
    - <b>Zhang et al., (2021):</b> LS Variance Fit, or Huber Variance Fit for ICESat-2 data filtering.<br>
    - <b>Alevizos (2020):</b> Residual analysis and spatial refinement in shallow waters.<br>
    - <b>Bergstra & Bengio (2012):</b> Randomized search for hyperparameter optimization.<br>
    - <b>Parrish et al. (2025):</b> Analysis and assessment of global ICESat-2 bathymetry.<br>
    - <b>Wheaton et al. (2010):</b> Accounting for uncertainty in DEMs from repeat topographic surveys (StatCD / Volumetric significance).<br>
    - <b>Lane & Chandler (2003):</b> The application of topographic surveying to fluvial studies (MMU spatial coherence filters).</p>

    <p><i>Developed for scientific research and hydrographic applications. Creating the Codes and documentation optimized using <b>Google Gemini AI</b>.</i></p>

homepage=https://github.com/Nasef2017/Bathymetrix-AI
repository=https://github.com/Nasef2017/Bathymetrix-AI
tracker=https://github.com/Nasef2017/Bathymetrix-AI/issues

tags=sdb,bathymetry,machine learning,icesat-2,ransac,spatial correction,remote sensing,hydrography,satellite imagery,python,coastal dynamics,volumetric change
category=Raster
changelog=v6.4: Added Coastal Dynamics Analysis (Linear Regression Volumetric Trends, MSI, Shoreline Change), New Band Indices (NDWI, Log(G/NIR), Log(R/NIR)), Dynamic Elbow Point OSW Filtering, Memory-efficient chunk-based ML prediction, Dynamic Outlier-Robust Plotting, and safe CRS reprojection.