BATHYMETRIX-AI: ADVANCED SDB TOOLKIT & COASTAL DYNAMICS
================================================================================

Bathymetrix-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.


--------------------------------------------------------------------------------
🔬 SCIENTIFIC METHODOLOGY — CORE 5-PHASE SYSTEM (SDB SINGLE MASTERFLOW)
--------------------------------------------------------------------------------

The SDB Single Masterflow provides a complete end-to-end processing pipeline for a single satellite scene:

Phase 01 → Phase 02 → Phase 03 → Phase 04 → Phase 05


PHASE 01: ADVANCED PRE-PROCESSING

Prepares satellite imagery for bathymetric modeling by isolating the aquatic domain, reducing radiometric interference, and generating depth-sensitive spectral features.

- Sun-Glint Removal:
Removes surface reflections using the Hedley model, with robust handling of NaN and Inf values.

- Water Segmentation:
Uses NDWI, MNDWI, and NWI with adaptive thresholding to isolate the aquatic domain.

- Deep Water OSW Filtering:
Identifies and removes deep-water areas unsuitable for optical bathymetry using:

(1) Automated Knee-Point Extinction [Recommended].
(2) Turbidity-Invariant Log-Ratio Extinction using NDTI.
(3) Multi-Otsu / GMM 3D Spectral Clustering.
(4) Connected-Component Topological Cleaning.
(5) Manual Polygon ROI & Custom OSW Polygon.

- OSW Boundary Extraction:
Exports Optically Shallow Water boundaries as GeoPackage vectors while preserving the source CRS.

- Log-Ratio Features & Spectral Indices:
Generates depth-sensitive features, including Blue/Green Log-Ratio and additional spectral indices.


PHASE 02: ROBUST FILTERING

Improves training data quality by identifying and removing noisy observations, outliers, and environmental artifacts.

- Noise Removal:
Supports Linear RANSAC, Least-Squares (LS) Variance Fit, and Huber Variance Fit, with optional bypass.

- Dynamic Diagnostic Plotting:
Uses robust percentile-based visualization for variance and trend analysis.


PHASE 03: GLOBAL AUTO-ML & FEATURE ANALYSIS

Automatically evaluates multiple machine-learning approaches instead of relying on one predefined algorithm.

- Feature Analysis:
Pearson/Spearman correlation, Auto-RANSAC, and Auto-Random Forest.

- Algorithm Benchmarking:
Evaluates 15+ regressors, including Random Forest, Gradient Boosting, XGBoost, LightGBM, CatBoost, SVR, and MLP.

- Model Selection & Winner Stability:
Supports seven selection strategies:

(1) Winner Stability via Monte Carlo Sensitivity Simulation.
(2) SDB Composite Score.
(3) Maximum R².
(4) Minimum RMSE.
(5) Minimum wMAPE.
(6) Minimum Absolute Bias.
(7) Minimum MAE.

- Hyperparameter Optimization:
Bayesian Optimization, Grid Search, and Random Search.

- Spatial Cross-Validation:
Independent spatial block cross-validation.

- Ensemble Blending:
Standard Average, Median, Stacking, and Uncertainty-Weighted Pixel Fusion.

- Memory-Efficient Prediction:
Chunk-based raster prediction for large satellite images.

- Customization:
Advanced controls for model parameters and optimization settings.


PHASE 04: ADAPTIVE REFINEMENT

Corrects local errors remaining after global machine-learning prediction.

- Decoupled Refinement Architecture:
Independent Depth Variance Correction and Spatial Residual Error Modeling.

- Spatial Residual Correction:
Models spatial differences between predicted and observed depths.

- Zero-Mean Centered Spatial Residuals:
Applies robust residual processing and spatial weighting to reduce local bias.

- Spatial Residual Modeling:
Robust KNN, Standard KNN, and Gaussian Process / Kriging.

- Spatial Cross-Validation:
Independent spatial validation of residual models.

- Adaptive Re-training & Pixel Fusion:
Integrates model predictions with spatial error information.

- IHO Standards Assessment:
Evaluates results against IHO S-44 Order 1a/2 Total Vertical Uncertainty criteria.


PHASE 05: VALIDATION & REPORTING

Provides independent scientific assessment of the final bathymetric result.

- Independent Accuracy Assessment:
Evaluates model performance using unseen validation points.

- Performance Metrics:
R², RMSE, and wMAPE.

- IHO S-44 Assessment:
Evaluates compliance with applicable Order 1a/2 TVU criteria.

- Interactive Validation Dashboard:
Generates HTML dashboards containing model leaderboards, validation metrics, diagnostic plots, and summary information.


--------------------------------------------------------------------------------
🚀 MASTERFLOWS & STANDALONE MODULES
--------------------------------------------------------------------------------

1. SDB Single Masterflow:
One Scene → Pre-processing → Filtering → AI Modeling → Adaptive Refinement → Validation → One Final SDB Map.

2. SDB SpatioSpectral Masterflow:
Multiple Scenes → Independent SDB Modeling → Scene Evaluation → Best Scene Selection / Weighted Median / Weighted Mean / Median / Mean → One Consolidated SDB Map.

3. SDB SpatioTemporal Masterflow:
Multiple Years → Global Spatiotemporal AI Modeling → Year-Specific Adaptive Refinement → Temporal Series of SDB Maps.

4. Coastal Dynamics Analysis (Module 06):
Analyzes Net Bathymetric Change, Morphological Stability Index (MSI), Statistical Level of Detection (StatCD), Erosion and Accretion, Shoreline Movement, Volumetric Sediment Tracking, and Target ROI Analytics.

5. ICESat-2 Downloader:
Queries, filters, and downloads ICESat-2 ATL24 bathymetric observations directly from NSIDC.

6. Tidal Datum Converter:
Converts and vertically aligns bathymetric observations between tidal reference datums using NASA GSFC GOT4.10c tidal modeling.


--------------------------------------------------------------------------------
📊 PERFORMANCE METRICS
--------------------------------------------------------------------------------

- R² (Coefficient of Determination):
Measures goodness of fit between predicted and observed depths.

- RMSE (Root Mean Square Error):
Measures average vertical prediction error in meters.

- wMAPE (Weighted Mean Absolute Percentage Error):
Measures relative error across depth intervals.

- IHO S-44 Standards:
Evaluates results against Order 1a and Order 2 TVU criteria.


--------------------------------------------------------------------------------
🎯 MASTERFLOW SELECTION GUIDE
--------------------------------------------------------------------------------

- SDB Single Masterflow:
One Scene → One SDB.

- SDB SpatioSpectral Masterflow:
Multiple Scenes → Evaluate / Select / Aggregate → One SDB.

- SDB SpatioTemporal Masterflow:
Multiple Years → Global Temporal AI → SDB for Each Year.

- Coastal Dynamics Analysis:
Yearly SDB → Bathymetric Change & Morphological Analysis.


--------------------------------------------------------------------------------
📚 SCIENTIFIC REFERENCES
--------------------------------------------------------------------------------

- Stumpf et al. (2003):
Determination of shallow water depth with high-resolution satellite imagery.

- Hedley et al. (2005):
Simple and robust removal of sun glint for high-resolution imagery.

- Fischler & Bolles (1981):
Random Sample Consensus (RANSAC) for model fitting.

- Zhang et al. (2021):
Adaptive variance fitting for satellite bathymetry noise reduction.

- Alevizos (2020):
Spatial residual refinement and error compensation in shallow coastal waters.

- Wheaton et al. (2010):
Accounting for uncertainty in DEMs from repeat topographic surveys.


--------------------------------------------------------------------------------
📖 SOFTWARE CITATION
--------------------------------------------------------------------------------

Nasef M. Aly. (2026).
Nasef2017/Bathymetrix-AI: Bathymetrix_AI V7.9 (Version v7.9).
[Computer software]. Zenodo.
https://doi.org/10.5281/zenodo.22539469


================================================================================
DEVELOPMENT & ACKNOWLEDGMENT
================================================================================

Developed by Mohamed Aly Nasef for scientific research, coastal mapping, bathymetric analysis, and hydrographic applications.

Code architecture, algorithms, and technical documentation significantly enhanced and optimized using Google Gemini AI.

================================================================================