diff --git a/aok/core/test_site_utils.py b/aok/core/test_site_utils.py
new file mode 100644
index 0000000..b526c5c
--- /dev/null
+++ b/aok/core/test_site_utils.py
@@ -0,0 +1,157 @@
+"""Utility functions for AOK pipeline."""
+
+from datetime import datetime
+from pathlib import Path
+from typing import Any
+
+from shapely.geometry import Point
+import yaml
+
+
+def load_test_sites(path: str = "./test_sites.yaml") -> dict[str, Any]:
+    """Load test sites from YAML file.
+
+    Parameters
+    ----------
+    path : str, optional
+        Path to the test sites YAML file, by default "./test_sites.yaml"
+
+    Returns
+    -------
+    dict
+        Dictionary containing test site configurations
+    """
+    with Path(path).open("r") as f:
+        return yaml.safe_load(f)
+
+
+def get_region_by_name(
+    name: str, sites: dict[str, Any] | None = None
+) -> dict[str, Any]:
+    """Retrieve a region configuration by name.
+
+    Parameters
+    ----------
+    name : str
+        Name of the region to retrieve
+    sites : dict, optional
+        Loaded sites configuration. If None, loads from default path
+
+    Returns
+    -------
+    dict
+        Region configuration dictionary
+
+    Raises
+    ------
+    KeyError
+        If region name is not found in sites
+    """
+    if sites is None:
+        sites = load_test_sites()
+    for site in sites["locations"]:
+        if site["name"] == name:
+            return site
+    msg = f"Region not found: {name}"
+    raise KeyError(msg)
+
+
+def check_not_null(key: Any) -> bool:
+    """Check if a key or list of keys is not None/empty.
+
+    Parameters
+    ----------
+    key : str or list
+        Single value or list to check
+
+    Returns
+    -------
+    bool
+        True if key is not None and not empty, False otherwise
+    """
+    return not (key is None or all(elem is None for elem in key))
+
+
+def get_bbox_shapely(
+    lat: float, lon: float, buffer_deg: float
+) -> tuple[float, float, float, float]:
+    """Create a bounding box around a point using Shapely.
+
+    Parameters
+    ----------
+    lat : float
+        Latitude coordinate
+    lon : float
+        Longitude coordinate
+    buffer_deg : float
+        Buffer distance in degrees
+
+    Returns
+    -------
+    tuple
+        Bounding box bounds as (min_lon, min_lat, max_lon, max_lat)
+    """
+    point = Point(lon, lat)
+    # Creating a 'square' buffer
+    bbox_poly = point.buffer(buffer_deg, cap_style=3)
+    return bbox_poly.bounds  # Returns (min_lon, min_lat, max_lon, max_lat)
+
+
+def get_spatial_extent(site: dict[str, Any]) -> tuple[float, float, float, float]:
+    """Extract spatial extent from site configuration.
+
+    Checks for bbox first, then falls back to lat/lon with buffer.
+
+    Parameters
+    ----------
+    site : dict
+        Site configuration dictionary containing spatial_extent
+
+    Returns
+    -------
+    tuple
+        Bounding box as (min_lon, min_lat, max_lon, max_lat)
+
+    Raises
+    ------
+    ValueError
+        If no valid spatial extent is found
+    """
+    spatial = site["spatial_extent"]
+    if check_not_null(spatial["bbox"]):
+        return spatial["bbox"]
+    if check_not_null(spatial["latlon"]):
+        return get_bbox_shapely(
+            spatial["latlon"][0], spatial["latlon"][1], spatial["buffer"]
+        )
+    msg = "Missing spatial extent"
+    raise ValueError(msg)
+
+
+def get_temporal_extent(site: dict[str, Any]) -> list[datetime]:
+    """Extract temporal extent from site configuration.
+
+    Parameters
+    ----------
+    site : dict[str, Any]
+        Site configuration dictionary containing dates
+
+    Returns
+    -------
+    list[datetime]
+        List of [start_datetime, end_datetime]
+
+    Raises
+    ------
+    ValueError
+        If no valid temporal inputs are found
+    """
+    if any(
+        [check_not_null(site["dates"]["start"]), check_not_null(site["dates"]["end"])]
+    ):
+        return [
+            datetime.fromisoformat(site["dates"]["start"]),
+            datetime.fromisoformat(site["dates"]["end"]),
+        ]
+    msg = "Missing temporal inputs"
+    raise ValueError(msg)
diff --git a/doc/source/example_notebooks/test_sites.yaml b/doc/source/example_notebooks/test_sites.yaml
new file mode 100644
index 0000000..da668a0
--- /dev/null
+++ b/doc/source/example_notebooks/test_sites.yaml
@@ -0,0 +1,315 @@
+locations:
+- name: chesapeake_bay
+  RGT: null
+  filename: ATL03_20181022081006_03620106_007_01.h5
+  dates:
+    start: '2018-10-22'
+    end: '2018-10-26'
+  spatial_extent:
+    bbox: [-77.54, 36.66, -74.58, 39.63]
+    latlon: null
+    buffer: null
+- name: core_sound_nc
+  RGT: '0484'
+  filename: null
+  dates:
+    start: '2022-04-23'
+    end: '2022-04-23'
+  spatial_extent:
+    bbox:
+    - -76.319707
+    - 34.895786
+    - -76.210123
+    - 34.985618
+    latlon:
+    - 34.940702
+    - -76.264915
+    buffer: 5.0
+- name: great_bay_nj
+  RGT: '0362'
+  filename: null
+  dates:
+    start: '2024-10-10'
+    end: '2024-10-10'
+  spatial_extent:
+    bbox:
+    - -74.410173
+    - 39.469391
+    - -74.293731
+    - 39.559223
+    latlon:
+    - 39.514307
+    - -74.351952
+    buffer: 5.0
+- name: apalachee_bay_fl
+  RGT: '1033'
+  filename: null
+  dates:
+    start: '2025-05-23'
+    end: '2025-05-23'
+  spatial_extent:
+    bbox:
+    - -84.160703
+    - 29.645356
+    - -83.746519
+    - 30.00468
+    latlon:
+    - 29.825018
+    - -83.953611
+    buffer: 20.0
+- name: columbia_river_estuary
+  RGT: '1050'
+  filename: null
+  dates:
+    start: '2025-05-24'
+    end: '2025-05-24'
+  spatial_extent:
+    bbox:
+    - -123.534834
+    - 46.20226
+    - -123.404936
+    - 46.292092
+    latlon:
+    - 46.247176
+    - -123.469885
+    buffer: 5.0
+- name: amazon_river_plume
+  RGT: '0117'
+  filename: null
+  dates:
+    start: '2023-06-27'
+    end: '2023-06-27'
+  spatial_extent:
+    bbox:
+    - null
+    - null
+    - null
+    - null
+    latlon:
+    - null
+    - null
+    buffer: 15.0
+- name: coastal_suriname
+  RGT: '0110'
+  filename: null
+  dates:
+    start: '2023-06-27'
+    end: '2023-06-27'
+  spatial_extent:
+    bbox:
+    - -55.344061
+    - 5.926538
+    - -55.073053
+    - 6.196032
+    latlon:
+    - 6.061285
+    - -55.208557
+    buffer: 15.0
+- name: kodiak_island_waves
+  RGT: '0937'
+  filename: null
+  dates:
+    start: '2023-02-19'
+    end: '2023-02-19'
+  spatial_extent:
+    bbox:
+    - -154.608682
+    - 56.212883
+    - -154.34974
+    - 56.356613
+    latlon:
+    - 56.284748
+    - -154.479211
+    buffer: 8.0
+- name: south_coast_portugal_waves
+  RGT: '0344'
+  filename: null
+  dates:
+    start: '2025-07-08'
+    end: '2025-07-08'
+  spatial_extent:
+    bbox:
+    - -9.430314
+    - 38.246449
+    - -9.086528
+    - 38.515943
+    latlon:
+    - 38.381196
+    - -9.258421
+    buffer: 15.0
+- name: hawaiian_islands_waves
+  RGT: '1158'
+  filename: null
+  dates:
+    start: '2023-12-03'
+    end: '2023-12-03'
+  spatial_extent:
+    bbox:
+    - -157.679862
+    - 20.803931
+    - -157.005772
+    - 21.432749
+    latlon:
+    - 21.11834
+    - -157.342817
+    buffer: 35.0
+- name: gulf_of_lions_night
+  RGT: '1159'
+  filename: null
+  dates:
+    start: '2023-12-03'
+    end: '2023-12-03'
+  spatial_extent:
+    bbox:
+    - 3.795804
+    - 43.139246
+    - 4.21542
+    - 43.444672
+    latlon:
+    - 43.291959
+    - 4.005612
+    buffer: 17.0
+- name: gulf_of_lions_day
+  RGT: '1197'
+  filename: null
+  dates:
+    start: '2023-12-06'
+    end: '2023-12-06'
+  spatial_extent:
+    bbox:
+    - 3.814676
+    - 43.092271
+    - 4.30818
+    - 43.451595
+    latlon:
+    - 43.271933
+    - 4.061428
+    buffer: 20.0
+- name: cook_inlet_tidal_flat
+  RGT: '0975'
+  filename: null
+  dates:
+    start: '2023-08-23'
+    end: '2023-08-23'
+  spatial_extent:
+    bbox:
+    - -149.685473
+    - 60.912944
+    - -149.500427
+    - 61.002776
+    latlon:
+    - 60.95786
+    - -149.59295
+    buffer: 5.0
+- name: baja_california_low_density_night
+  RGT: '1225'
+  filename: null
+  dates:
+    start: '2023-09-08'
+    end: '2023-09-08'
+  spatial_extent:
+    bbox:
+    - -113.62051
+    - 30.458626
+    - -113.098238
+    - 30.907782
+    latlon:
+    - 30.683204
+    - -113.359374
+    buffer: 25.0
+- name: baja_california_low_density_day
+  RGT: '1339'
+  filename: null
+  dates:
+    start: '2023-09-15'
+    end: '2023-09-15'
+  spatial_extent:
+    bbox:
+    - -111.958456
+    - 27.063638
+    - -111.65546
+    - 27.333132
+    latlon:
+    - 27.198385
+    - -111.806958
+    buffer: 15.0
+- name: bora_bora_high_waves
+  RGT: '0868'
+  filename: null
+  dates:
+    start: '2023-02-15'
+    end: '2023-02-15'
+  spatial_extent:
+    bbox:
+    - -151.769291
+    - -17.088578
+    - -151.393731
+    - -16.729254
+    latlon:
+    - -16.908916
+    - -151.581511
+    buffer: 20.0
+- name: cook_inlet_very_turbid_water
+  RGT: '1013'
+  filename: null
+  dates:
+    start: '2025-08-21'
+    end: '2025-08-22'
+  spatial_extent:
+    bbox:
+    - -150.622053
+    - 61.045382
+    - -150.361757
+    - 61.171146
+    latlon:
+    - 61.108264
+    - -150.491905
+    buffer: 7.0
+- name: rio_de_la_plata
+  RGT: '0216'
+  filename: null
+  dates:
+    start: '2023-07-04'
+    end: '2023-07-04'
+  spatial_extent:
+    bbox:
+    - -58.409826
+    - -34.611195
+    - -58.082914
+    - -34.341701
+    latlon:
+    - -34.476448
+    - -58.24637
+    buffer: 15.0
+- name: klamath_lake_algal_bloom
+  RGT: '1332'
+  filename: null
+  dates:
+    start: '2023-09-15'
+    end: '2023-09-15'
+  spatial_extent:
+    bbox:
+    - -122.041563
+    - 42.423257
+    - -121.968517
+    - 42.477155
+    latlon:
+    - 42.450206
+    - -122.00504
+    buffer: 3.0
+- name: chesapeake_bay
+  RGT: null
+  filename: ATL03_20230825074121_10102002_006_02.h5
+  dates:
+    start: '2018-10-22'
+    end: '2018-10-26'
+  spatial_extent:
+    bbox:
+    - -77.54
+    - 36.66
+    - -74.58
+    - 39.63
+    latlon:
+    - null
+    - null
+    buffer: 0.0