K-Nearest neighbors (KNN)

K-Nearest Neighbors (KNN) is an estimation algorithm where every point is given the average value of the 'k' closest data points.

Parameters

• source (geoscience object reference)
  • A geoscience object reference that points to a one-dimensional continuous attribute inside a pointset or downhole-intervals object. This is your input data.
• target (geoscience object reference)
  • A geoscience object reference that tells the task where to save the result. It must point to an attribute inside a pointset, downhole-intervals, regular-3d-grid, or regular-masked-3d-grid object.
• search_neighborhood (object)
  • A search ellipse that the task will use to find each point's nearest neighbors.

  •   {
          "max_samples": 40, // The neighborhood can find up to this many other points.
          "anisotropy": {
              "ellipsoid_ranges": {
                  "major": 70, // The ellipsoid's major axis length.
                  "semi_major": 70, // The ellipsoid's semi-major axis length.
                  "minor": 5, // The ellipsoid's minor axis length.
              },
              "rotation": {
                  "dip_azimuth": 0, // The azimuth of the ellipsoid's dip direction, in degrees.
                  "dip": 0, // The dip of the ellipsoid, in degrees.
                  "pitch": 0, // The pitch of the ellipsoid, in degrees.
              },
          },
      }

Example

For more information, see the k-nearest-neighbor API reference.

Request

requests.post(
    "https://{hub}.api.seequent.com/compute/orgs/{org_id}/geostat/knn",
    headers={"Authorization": "Bearer {token}"},
    json={
        "parameters": {
            "composites": {
                "type": "geoscience-object-reference",
                "object_reference": "https://{hub}.api.seequent.com/geoscience-object/orgs/{org_id}/workspaces/{workspace_id}/objects/path/my-pointset.json",
                "object_element": [
                    {
                        "type": "element",
                        "path": "/locations/attributes/@name=my-data",
                    },
                ],
            },
            "target": {
                "type": "geoscience-object-reference",
                "object_reference": "https://{hub}.api.seequent.com/geoscience-object/orgs/{org_id}/workspaces/{workspace_id}/objects/path/my-pointset.json",
                "object_element": [
                    {
                        "type": "element",
                        "path": "/locations/attributes/@name=my-knn",
                    },
                ],
            },
            "neighborhood": {
                "max_samples": 40,
                "anisotropy": {
                    "ellipsoid_ranges": {
                        "major": 25,
                        "semi_major": 25,
                        "minor": 25,
                    },
                    "rotation": {
                        "dip_azimuth": 0,
                        "dip": 0,
                        "pitch": 0,
                    },
                },
            },
        },
    },
)

Result

{
    "message": "KNN estimate completed.",
    "object_modified": {
        "type": "geoscience-object-reference",
        "object_reference": "https://{hub}.api.seequent.com/geoscience-object/orgs/{org_id}/workspaces/{workspace_id}/objects/path/my-pointset.json",
        "object_element": [
            {
                "type": "element",
                "path": "/locations/attributes/@name=my-knn",
            },
        ],
    },
}

Tips

• The source and target can use the same object, but they don't have to.