Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cerea-daml/co2-images-inv-dl

Official repository for the paper "Deep learning applied to CO2 power plant emissions quantification using simulated satellite images"

https://github.com/cerea-daml/co2-images-inv-dl

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 7 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.3%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Official repository for the paper "Deep learning applied to CO2 power plant emissions quantification using simulated satellite images"

Basic Info
  • Host: GitHub
  • Owner: cerea-daml
  • Language: Jupyter Notebook
  • Default Branch: inv_pp
  • Homepage:
  • Size: 6.86 MB
Statistics
  • Stars: 4
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 4
Created almost 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme

README.md

co2-images-inv-pp

Welcome to the official repository for the paper "Deep learning applied to CO2 power plant emissions quantification using simulated satellite images," submitted to the "Geoscientific Model Development" journal (COPERNICUS).

DOI

Project Overview

This project demonstrates a novel concept that deep learning can be employed to identify anthropogenic XCO2 emissions from hotspots in XCO2 images, assisted by NO2 and wind data.

Our scripts and modules are written in Python, using Tensorflow as the deep learning framework.

To employ these scripts, download the datasets of fields and plumes from inv-zenodo. Alternatively, you can create the netcdf datasets directly from the SMARTCARB dataset. Note that the data generation scripts are not part of this repository, but can be provided upon request.

Weights for pre-trained models can be obtained from inv-zenodo-weights.

Within the 'examples' directory, you will find two Jupyter notebooks, train.ipynb and test.ipynb: - train.ipynb guides on how to train a model using a configuration (cfg) file, configured with Hydra. - test.ipynb outlines how to evaluate a pre-trained model. For both files, specific items in the configuration file that need adjustments for your set up are highlighted.

Post data collection/generation, use our main.py Python script (refer examples/train.ipynb) to train the Convolutional Neural Network as elaborated in the manuscript.

For any further queries, do not hesitate to reach out or create a GitHub issue.

Acknowledgements and Authors

This project is funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement 958927 (Prototype system for a Copernicus CO2 service). CEREA is a proud member of Institut Pierre Simon Laplace (IPSL).

Support

Feel free to contact: joffrey.dumont@enpc.fr

Owner

  • Name: CEREA DA-ML team
  • Login: cerea-daml
  • Kind: organization
  • Location: Paris, France

GitHub Events

Total
  • Fork event: 1
Last Year
  • Fork event: 1

Dependencies

models/ext_segmentation_models/requirements.txt pypi
  • efficientnet ==1.0.0
  • image-classifiers ==1.0.0
  • keras_applications >=1.0.7,<=1.0.8
models/ext_segmentation_models/setup.py pypi