Update docs, instructions and format code

ARCHITECTURE.md

@@ -27,12 +27,20 @@ The pipeline follows a sequential processing approach where each stage produces
 
 ### System Components
 
-The codebase is organized into four main packages:
+The project in general is organized into four directories:
+
+- **`src/entropice/`**: The main processing codebase
+- **`scripts/`**: Bash scripts and wrapper for data processing pipeline scripts
+- **`notebooks/`**: Exploratory analysis and validation notebooks (not commited to git)
+- **`tests/`**: Unit tests and manual validation scripts
+
+The processing codebase is organized into five main packages:
 
 - **`entropice.ingest`**: Data ingestion from external sources (DARTS, ERA5, ArcticDEM, AlphaEarth)
 - **`entropice.spatial`**: Spatial operations and grid management
 - **`entropice.ml`**: Machine learning workflows (dataset, training, inference)
 - **`entropice.utils`**: Common utilities (paths, codecs)
+- **`entropice.dashboard`**: Streamlit Dashboard for interactive visualization
 
 #### 1. Spatial Grid System (`spatial/grids.py`)
 
@@ -179,6 +187,14 @@ scripts/05train.sh      # Model training
 - TOML files for training hyperparameters
 - Environment-based path management (`utils/paths.py`)
 
+### 6. Geospatial Best Practices
+
+- Use **xarray** with XDGGS for gridded data storage
+- Store intermediate results as **Parquet** (tabular) or **Zarr** (arrays)
+- Leverage **Dask** for lazy evaluation of large datasets
+- Use **GeoPandas** for vector operations
+- Use EPSG:3413 (Arctic Stereographic) coordinate reference system (CRS) for any computation on the data and EPSG:4326 (WGS84) for data visualization and compatability with some libraries
+
 ## Data Storage Hierarchy
 
 ```sh