Skip to main content

DINCAE (Data-Interpolating Convolutional Auto-Encoder) is a neural network to reconstruct missing data in satellite observations

Project description

documentation latest DOI Build Status codecov.io

DINCAE

DINCAE (Data-Interpolating Convolutional Auto-Encoder) is a neural network to reconstruct missing data in satellite observations. https://www.geosci-model-dev-discuss.net/gmd-2019-128/

Installation

Python 3.6 with the modules:

Tested versions:

  • Python 3.6.8
  • netcdf4 1.4.2
  • numpy 1.15.4
  • Tensorflow version 1.15

You can install those packages either with pip3 or with conda.

Input format

The input data should be in netCDF with the variables:

  • lon: longitude (degrees East)
  • lat: latitude (degrees North)
  • time: time (days since 1900-01-01 00:00:00)
  • mask: boolean mask where true means the data location is valid
  • SST (or any other varbiable name): the data
netcdf avhrr_sub_add_clouds {
dimensions:
	time = UNLIMITED ; // (5266 currently)
	lat = 112 ;
	lon = 112 ;
variables:
	double lon(lon) ;
	double lat(lat) ;
	double time(time) ;
		time:units = "days since 1900-01-01 00:00:00" ;
	int mask(lat, lon) ;
	float SST(time, lat, lon) ;
		SST:_FillValue = -9999.f ;
}

Running DINCAE

Copy the template file run_DINCAE.py and adapt the filename, variable name and the output directory and possibly optional arguments for the reconstruction method as mentioned in the documentation. The code can be run as follows:

export PYTHONPATH=/path/to/module
python3 run_DINCAE.py

/path/to/module should be replaced by the directory name containing the file DINCAE.py.

Project details


Release history Release notifications

This version

1.1.0

Download files

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

Files for DINCAE, version 1.1.0
Filename, size File type Python version Upload date Hashes
Filename, size DINCAE-1.1.0-py3-none-any.whl (22.1 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size DINCAE-1.1.0.tar.gz (12.2 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page