3. Split survey data into lines

We will try and automatically split a survey into flight lines using various techniques and compare there results to the hand-split lines from the published survey data.

%load_ext autoreload
%autoreload 2


import geopandas as gpd
import pandas as pd
import plotly.io as pio

import airbornegeo

pio.renderers.default = "notebook"

The autoreload extension is already loaded. To reload it, use:
  %reload_ext autoreload

3.1. Load data

This is a subset of the BAS AGAP survey over Antarctica’s Gamburtsev Subglacial Mountains. The file is downloaded and subset in the notebook AGAP_magnetic_survey.

data_df = pd.read_csv("data/AGAP_magnetic_survey_processed_blocked.csv")

# only keep relevant columns
data_df = data_df[
    [
        "easting",
        "northing",
        "latitude",
        "longitude",
        "unixtime",
        "line",
    ]
]

# retain only a subset of lines
data_df = data_df[(data_df.line.between(168, 176)) | (data_df.line.between(90, 127))]

# rename lines starting from 1
data_df["original_line"] = airbornegeo.unique_line_id(data_df, "line")
data_df = data_df.drop(columns="line")

# sort by time and line
# data_df = data_df.sort_values(by=["original_line", "unixtime"])
data_df = data_df.sort_values(by=["unixtime"])

# turn to geopandas geodataframe
data_df = gpd.GeoDataFrame(
    data_df,
    geometry=gpd.points_from_xy(x=data_df.easting, y=data_df.northing),
    crs="EPSG:3031",
)

data_df.head()

	easting	northing	latitude	longitude	unixtime	original_line	geometry
592564	1307565.129	550917.135	-76.995	67.153	1229692438.500	39	POINT (1307565.129 550917.135)
592565	1307617.217	550827.922	-76.995	67.157	1229692440.500	39	POINT (1307617.217 550827.922)
592566	1307664.827	550736.002	-76.995	67.161	1229692442.500	39	POINT (1307664.827 550736.002)
592567	1307707.061	550641.238	-76.995	67.165	1229692444.500	39	POINT (1307707.061 550641.238)
592568	1307743.369	550543.805	-76.995	67.170	1229692446.500	39	POINT (1307743.369 550543.805)

print(f"Originally {len(data_df.original_line.unique())} lines")

Originally 47 lines

airbornegeo.plotly_points(
    data_df,
    color_col="original_line",
    hover_cols=[
        "unixtime",
    ],
    robust=False,
    size=3,
)

3.2. Split lines on time gaps

Here we assume any time gap greater than 2 minutes between successive points marks the end of one line and the start of another.

data_df["segments_by_time"] = airbornegeo.split_into_segments(
    data_df,
    threshold=60 * 2,  # 2 minutes
    column_name="unixtime",
)
print(f"{len(data_df.segments_by_time.unique())} segments")

46 segments

airbornegeo.plotly_points(
    data_df,
    color_col="segments_by_time",
    hover_cols=[
        "original_line",
        "unixtime",
    ],
    robust=False,
    size=3,
)

3.3. Split lines on distance gaps

Here we assume any distance gap greater than 5 km between successive points marks the end of one line and the start of another.

data_df["relative_distance"] = airbornegeo.relative_distance(
    data_df,
    easting_column="easting",
    northing_column="northing",
)

data_df["segments_by_distance"] = airbornegeo.split_into_segments(
    data_df,
    threshold=5e3,  # 5 km
    column_name="relative_distance",
)
print(f"{len(data_df.segments_by_distance.unique())} segments")

46 segments

airbornegeo.plotly_points(
    data_df,
    color_col="segments_by_distance",
    hover_cols=["original_line", "relative_distance"],
    robust=False,
    size=3,
)

3.4. Split lines on track / heading changes

Here we assume any change of track (heading) more than 45 degrees between successive points marks the end of one line and the start of another. First we need to calculate the track from the latitude and longitude of the data.

data_df["track"] = airbornegeo.track(
    data_df,
    latitude_column="latitude",
    longitude_column="longitude",
    ellipsoid=False,
)

airbornegeo.plotly_points(
    data_df,
    color_col="track",
    hover_cols=["original_line"],
    size=3,
)

data_df = data_df.sort_values("unixtime")
data_df["segments_by_track"] = airbornegeo.split_into_segments(
    data_df,
    threshold=40,  # 20 degree track change
    column_name="track",
    angular_difference=True,  # the difference between two values on either side of (0/360) should be small
)
print(f"{len(data_df.segments_by_track.unique())} segments")

66 segments

airbornegeo.plotly_points(
    data_df,
    color_col="segments_by_track",
    hover_cols=["original_line", "track"],
    robust=False,
    size=3,
)