Skip to main content
Donate to the Python Software Foundation or Purchase a PyCharm License to Benefit the PSF! Donate Now

A Python library for n-dimensional Earth observation data processing

Project description

Build Status codecov

nd

This package contains a selection of tools to handle and analyze satellite data.

nd is making heavy use of the xarray library. dask is used for parallelization.

The GDAL library is only used as a compatibility layer in nd.io to enable reading supported file formats. Internally, all data is passed around as xarray Datasets and all provided functions expect this format as inputs. nd.io.from_gdal_dataset may be used to convert any gdal.Dataset object or GDAL-readable file into an xarray Dataset.


Submodules

nd.io

Several functions to read and write satellite data.

  • to/from NetCDF
  • read data from open GDAL datasets and any GDAL-readable file
  • deal with complex-valued data (not supported by NetCDF) by disassembling into two reals when writing to NetCDF, and vice versa when reading.

nd.change

A module implementing change detection algorithms.

  • convert dual polarization data into the complex covariance matrix representation
  • OmnibusTest (change detection algorithm by Conradsen et al. (2015))

nd.classify

A collection of classification and clustering methods.

... work in progress ...

nd.filter

Implements several filters, currently:

  • kernel convolutions
  • non-local means

nd.utils

Several utility functions.

  • split/merge numpy arrays, xarray datasets, ...
  • parallelize operations acting on xarray datasets

nd.warp

Given a dataset with Ground Control Points (GCPs), usually in the form of a tie point grid, warp the dataset onto an equirectangular projection (WGS84), such that lat/lon directly correspond to the y and x coordinates, respectively.

This makes concatenating datasets easier and reduces storage size, because lat/lon coordinates do not need to be stored for each pixel.

nd.visualize

Several functions to quickly visualize data.

  • create RGB images from data
  • create video from a spatiotemporal dataset

nd.tiling

  • Split a dataset into tiles.
  • Read a tiled dataset.
  • Map a function across a tiled dataset.
  • Create and merge tiles with buffer to avoid edge affects.

Project details


Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
nd-0.0.0.tar.gz (539.5 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page