{"name": "Bathymetrix-AI", "package_name": "Bathymetrix_AI", "description": "A professional QGIS research toolkit for Satellite-Derived Bathymetry (SDB), integrating multispectral imagery with ICESat-2 LiDAR via Auto-ML, SpatioSpectral aggregation, SpatioTemporal modeling, Adaptive Refinement, and Coastal Dynamics.", "about": "================================================================================\r\nBATHYMETRIX-AI: ADVANCED SDB TOOLKIT & COASTAL DYNAMICS\r\n================================================================================\r\n\r\nBathymetrix-AI is a professional QGIS research toolkit for high-precision Satellite-Derived Bathymetry (SDB). The toolkit integrates multispectral satellite imagery with ICESat-2 (ATL24) LiDAR bathymetry through a modular and adaptive Machine Learning framework. It automates the end-to-end SDB processing pipeline while maintaining full control over data quality, model selection, spatial refinement, uncertainty estimation, and scientific validation.\r\n\r\n\r\n--------------------------------------------------------------------------------\r\nSCIENTIFIC METHODOLOGY \u2014 CORE 5-PHASE SYSTEM (SDB SINGLE MASTERFLOW)\r\n--------------------------------------------------------------------------------\r\nThe SDB Single Masterflow is the core SDB workflow of Bathymetrix-AI, providing a complete end-to-end processing pipeline for a single satellite scene: Phase 01 -> Phase 02 -> Phase 03 -> Phase 04 -> Phase 05\r\n\r\nPhase 01: Advanced Pre-processing\r\nPrepares the satellite imagery for bathymetric modeling by isolating the aquatic domain, reducing radiometric interference, and generating depth-sensitive spectral features:\r\n- Sun-Glint Removal: Removes surface reflections using the Hedley model, with robust handling of NaN and Inf values for processing stability.\r\n- Water Segmentation: Uses NDWI, MNDWI, and NWI together with adaptive thresholding to isolate the aquatic domain.\r\n- Deep Water OSW Filtering: Identifies and removes deep-water areas unsuitable for optically derived bathymetry using an advanced multi-method engine:\r\n(1) Automated Knee-Point Extinction [Recommended] detecting the physical optical extinction cutoff on NIR absorption.\r\n(2) Turbidity-Invariant Log-Ratio Extinction utilizing NDTI to protect coastal waters from sediment/mud plumes.\r\n(3) Multi-Otsu / GMM 3D Spectral Clustering for complex reefs and heterogeneous benthos.\r\n(4) Connected-Component Topological Cleaning removing open ocean speckles.\r\n(5) Manual Polygon ROI & Custom OSW Polygon.\r\n- OSW Boundary Extraction: Exports the Optically Shallow Water boundary as a GeoPackage vector while preserving the source imagery CRS.\r\n- Log-Ratio Features & Spectral Indices: Generates physics-based depth-sensitive features such as Blue/Green Log-Ratio together with additional spectral indices.\r\n\r\nPhase 02: Robust Filtering\r\nImproves the quality of the training data by identifying and removing noisy observations, outliers, and environmental artifacts:\r\n- Noise Removal: Supports Linear RANSAC, Least-Squares (LS) Variance Fit, and Huber Variance Fit with seamless user bypass.\r\n- Dynamic Diagnostic Plotting: Uses robust percentile-based visualization to produce clearer variance and trend plots while reducing the effect of extreme noise.\r\n\r\nPhase 03: Global Auto-ML & Feature Analysis\r\nAutomatically evaluates multiple machine-learning approaches instead of relying on a single predefined algorithm:\r\n- Feature Analysis: Evaluates feature correlation, redundancy, and importance using Pearson/Spearman correlation, Auto-RANSAC, and Auto-Random Forest.\r\n- Algorithm Benchmarking: Evaluates 15+ machine-learning regressors (Random Forest, Gradient Boosting, XGBoost, LightGBM, CatBoost, SVR, MLP, etc.).\r\n- Model Selection & Winner Stability: Evaluates models using 7 distinct selection strategies (Winner Stability via Monte Carlo Sensitivity Simulation, SDB Composite Score, Max R\u00b2, Min RMSE, Min wMAPE, Min |Bias|, Min MAE) with auto-balanced metric weighting and custom syntax parsing.\r\n- Hyperparameter Optimization: Supports Bayesian Optimization, Grid Search, and Random Search.\r\n- Spatial Cross-Validation: Provides independent spatial block cross-validation for model evaluation.\r\n- Ensemble Blending: Supports Standard Average, Median, Stacking, and Uncertainty-Weighted Pixel Fusion.\r\n- Memory-Efficient Prediction: Uses chunk-based raster prediction to reduce memory usage when processing large images.\r\n- Customization: Provides advanced control over model and optimization parameters for research and fine-tuning.\r\n\r\nPhase 04: Adaptive Refinement\r\nCorrects local errors that may remain after global machine-learning prediction:\r\n- Decoupled Refinement Architecture: Independent controls for Depth Variance Correction (Datum Mean Shift) and Spatial Residual Error Modeling (KNN / Kriging Grid).\r\n- Spatial Residual Correction: Analyzes the differences between predicted and observed depths and models their spatial behavior.\r\n- Zero-Mean Centered Spatial Residuals: Uses robust residual processing and spatial weighting to reduce local depth bias.\r\n- Spatial Residual Modeling: Supports robust KNN, Standard KNN, and Gaussian Process / Kriging.\r\n- Spatial Cross-Validation: Provides independent spatial validation for residual modeling.\r\n- Adaptive Re-training & Pixel Fusion: Combines model information with spatial error information to generate a refined bathymetric surface.\r\n- IHO Standards Assessment: Evaluates results against IHO S-44 Order 1a/2 Total Vertical Uncertainty (TVU) standards.\r\n\r\nPhase 05: Validation & Reporting\r\nProvides independent scientific assessment of the final bathymetric result:\r\n- Independent Accuracy Assessment: Evaluates the final model using unseen validation points.\r\n- Performance Metrics: R\u00b2 (Coefficient of Determination), RMSE (Root Mean Square Error), wMAPE (Weighted Mean Absolute Percentage Error).\r\n- IHO S-44 Assessment: Evaluates compliance with applicable Order 1a/2 TVU criteria.\r\n- Interactive Validation Dashboard: Generates HTML dashboards containing model leaderboards, validation metrics, diagnostic plots, and summary information.\r\n\r\n\r\n--------------------------------------------------------------------------------\r\nMASTERFLOWS & STANDALONE MODULES\r\n--------------------------------------------------------------------------------\r\n1. SDB Single Masterflow:\r\nThe standard end-to-end SDB workflow for a single satellite scene (One Scene -> Pre-processing -> Data Filtering -> AI Modeling -> Adaptive Refinement -> Scientific Validation -> One Final SDB Map).\r\n\r\n2. SDB SpatioSpectral Masterflow:\r\nDesigned for multiple satellite scenes covering the same area. Evaluates independent SDB results per scene and applies multi-scene consensus strategies (Best Scene Selection, Weighted Median, Weighted Mean, or Median/Mean) to produce one final consolidated SDB map.\r\n\r\n3. SDB SpatioTemporal Masterflow:\r\nMulti-year SDB modeling integrating Year/Time directly into a Global Spatiotemporal AI model, followed by year-specific adaptive refinement to produce a consistent temporal series of SDB maps.\r\n\r\n4. Coastal Dynamics Analysis (Module 06):\r\nUses yearly SDB maps to analyze long-term bathymetric trends, Net Bathymetric Change, Morphological Stability Index (MSI), Statistical Level of Detection (StatCD), Erosion and Accretion, Shoreline Movement, Volumetric Sediment Tracking, and Target ROI Analytics.\r\n\r\n5. ICESat-2 Downloader:\r\nSpecialized tool for querying, filtering, and downloading ICESat-2 ATL24 bathymetry data directly from NSIDC.\r\n\r\n6. Tidal Datum Converter:\r\nDedicated tool for converting and vertically aligning bathymetric observations between different tidal reference datums (e.g., MSL to Chart Datum) integrating NASA GSFC GOT4.10c automated global tidal modeling.\r\n\r\n\r\n--------------------------------------------------------------------------------\r\nPERFORMANCE METRICS\r\n--------------------------------------------------------------------------------\r\n- R\u00b2 (Coefficient of Determination): Measures goodness of fit between predicted and observed depths.\r\n- RMSE (Root Mean Square Error): Measures average vertical error in meters.\r\n- wMAPE (Weighted Mean Absolute Percentage Error): Measures relative error across depth intervals.\r\n- IHO S-44 Standards: Evaluates compliance with Order 1a and Order 2 TVU criteria.\r\n\r\n\r\n--------------------------------------------------------------------------------\r\nMASTERFLOW SELECTION GUIDE\r\n--------------------------------------------------------------------------------\r\n- SDB Single Masterflow: One Scene -> One SDB.\r\n- SDB SpatioSpectral Masterflow: Multiple Scenes -> Evaluate / Select / Aggregate -> One SDB.\r\n- SDB SpatioTemporal Masterflow: Multiple Years -> Global Temporal AI -> SDB for Each Year.\r\n- Coastal Dynamics Analysis: Yearly SDB -> Change & Morphological Analysis.\r\n\r\n\r\n--------------------------------------------------------------------------------\r\nSCIENTIFIC REFERENCES\r\n--------------------------------------------------------------------------------\r\n- Stumpf et al. (2003): Determination of shallow water depth with high-resolution satellite imagery.\r\n- Hedley et al. (2005): Simple and robust removal of sun glint for high-resolution imagery.\r\n- Fischler & Bolles (1981): Random Sample Consensus (RANSAC) for model fitting.\r\n- Zhang et al. (2021): Adaptive variance fitting for satellite bathymetry noise reduction.\r\n- Alevizos (2020): Spatial residual refinement and error compensation in shallow coastal waters.\r\n- Wheaton et al. (2010): Accounting for uncertainty in DEMs from repeat topographic surveys.\r\n\r\n\r\n================================================================================\r\nDeveloped by Mohamed Aly Nasef for scientific research, coastal mapping, bathymetric analysis, and hydrographic applications.\r\nCode architecture, algorithms, and technical documentation significantly enhanced and optimized using Google Gemini AI.\r\n================================================================================", "homepage": "https://github.com/Nasef2017/Bathymetrix-AI", "repository": "https://github.com/Nasef2017/Bathymetrix-AI", "tracker": "https://github.com/Nasef2017/Bathymetrix-AI/issues", "author": "Mohamed Aly Nasef", "tags": ["icesat-2", "remote sensing", "machine learning", "spatial correction", "ransac", "bathymetry", "sdb", "hydrography", "python", "satellite imagery", "coastal dynamics", "volumetric change", "quantile regression", "spatiospectral", "iho-s44", "spatiotemporal"], "downloads": 6356, "latest_version": "7.9", "versions": [{"version": "7.9", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 163, "uploaded_by": "nasefmaly", "upload_datetime": "2026-09-07T01:20:02.661942"}, {"version": "7.7", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 129, "uploaded_by": "nasefmaly", "upload_datetime": "2026-09-01T11:25:10.845578"}, {"version": "7.5", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 119, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-30T07:10:30.810237"}, {"version": "7.2", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 238, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-19T22:25:35.391308"}, {"version": "7.1", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 101, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-18T06:57:49.328943"}, {"version": "7.0", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 113, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-14T04:35:26.071826"}, {"version": "6.5", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 270, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-06T14:14:17.227002"}, {"version": "6.4", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 168, "uploaded_by": "nasefmaly", "upload_datetime": "2026-08-02T12:24:23.951318"}, {"version": "6.3", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 402, "uploaded_by": "nasefmaly", "upload_datetime": "2026-07-16T06:33:37.071600"}, {"version": "6.1", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 368, "uploaded_by": "nasefmaly", "upload_datetime": "2026-07-10T10:12:44.772453"}, {"version": "6.0", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 148, "uploaded_by": "nasefmaly", "upload_datetime": "2026-07-07T10:38:19.664382"}, {"version": "5.2", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 159, "uploaded_by": "nasefmaly", "upload_datetime": "2026-07-02T03:43:33.163448"}, {"version": "5.1", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 248, "uploaded_by": "nasefmaly", "upload_datetime": "2026-06-23T13:21:19.150571"}, {"version": "5.0", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 180, "uploaded_by": "nasefmaly", "upload_datetime": "2026-06-21T03:44:36.916673"}, {"version": "4.8", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 433, "uploaded_by": "nasefmaly", "upload_datetime": "2026-05-25T17:49:03.248788"}, {"version": "4.7", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "4.99.0", "downloads": 339, "uploaded_by": "nasefmaly", "upload_datetime": "2026-05-09T06:24:06.990974"}, {"version": "4.6", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 290, "uploaded_by": "nasefmaly", "upload_datetime": "2026-04-23T07:20:30.150107"}, {"version": "4.5", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 133, "uploaded_by": "nasefmaly", "upload_datetime": "2026-04-22T04:58:17.735258"}, {"version": "4.4", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 112, "uploaded_by": "nasefmaly", "upload_datetime": "2026-04-22T03:00:50.708322"}, {"version": "4.3", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 288, "uploaded_by": "nasefmaly", "upload_datetime": "2026-04-07T00:01:56.962288"}, {"version": "4.2", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 117, "uploaded_by": "nasefmaly", "upload_datetime": "2026-04-02T13:40:52.819255"}, {"version": "4.1", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 587, "uploaded_by": "nasefmaly", "upload_datetime": "2026-02-22T01:51:22.218820"}, {"version": "4.0", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 449, "uploaded_by": "nasefmaly", "upload_datetime": "2026-01-29T12:50:52.978416"}, {"version": "3.3", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 208, "uploaded_by": "nasefmaly", "upload_datetime": "2026-01-25T13:22:28.905958"}, {"version": "3.2", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 232, "uploaded_by": "nasefmaly", "upload_datetime": "2026-01-11T23:41:05.860406"}, {"version": "3.1", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 128, "uploaded_by": "nasefmaly", "upload_datetime": "2026-01-10T23:43:49.931487"}, {"version": "3.0", "experimental": false, "qgis_min": "3.22.0", "qgis_max": "3.99.0", "downloads": 233, "uploaded_by": "nasefmaly", "upload_datetime": "2025-12-30T09:52:02.168442"}]}