Data

Tools

Indexes

Applications

Experiments

Open Source Science

grit-lab-public-soil-moisture-retrieval-repo

GRIT Lab Soil Moisture Retrieval Algorithms and Data for JGR Biogeosciences Publication 2023

https://github.com/grit-lab/grit-lab-public-soil-moisture-retrieval-repo

Science Score: 67.0%

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

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 5 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 (15.4%) to scientific vocabulary

Scientific Fields

Mathematics Computer Science - 84% confidence
Artificial Intelligence and Machine Learning Computer Science - 69% confidence
Last synced: 4 months ago · JSON representation ·

Repository

GRIT Lab Soil Moisture Retrieval Algorithms and Data for JGR Biogeosciences Publication 2023

Basic Info
  • Host: GitHub
  • Owner: grit-lab
  • License: mit
  • Language: HTML
  • Default Branch: main
  • Size: 31 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 3
Created over 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

grit-lab-public-soil-moisture-retrieval-repo

Public Release v1.0.3

Welcome to our repository. Here, you will find the Python scripts and the lab and UAS dataset that were used in the research article "Comparison of Soil Moisture Content Retrieval Models Utilizing Hyperspectral Goniometer Data and Hyperspectral Imagery from an Unmanned Aerial System" by Nayma Binte Nur and Charles M. Bachmann, which has been published in Journal of Geophysical Research - Biogeosciences and is accessible via this link: https://doi.org/10.1029/2023JG007381.

For the most recent updates, kindly visit our GitHub repository at grit-lab-public-soil-moisture-retrieval-repo.

Repository Structure

The repository comprises Python implementations of three soil moisture content retrieval models:

  1. MARMIT
  2. Original (SWAP)-Hapke
  3. Modified (SWAP)-Hapke

These models are implemented for two types of datasets: Lab data and UAS data. Each model directory contains its API documentation in the docs folder to help you understand the Python modules better. The input folder holds the datasets used in this study. Please note that in our Python scripts, K, psi, and alpha correspond to A, B, and ψ of the article respectively. This code has been developed with Python version 3.8. For a list of required packages, please refer to requirements.txt.

Usage Instructions

Working with Lab Data

To use the Lab data, execute the following program:

python3 run_project.py

On launching the program, you will be prompted with the following message:

Choose the lab dataset to process (alg/nev/hogp/hogb):

Here, you should select the lab dataset to be processed (e.g., 'alg') and hit Enter. This will kick-start the program to retrieve SMC using the corresponding model for the selected dataset. All outputs from the program will be stored in the outputs folder.

After processing all four lab datasets, you can execute the following program to plot the retrieved SMC vs. estimated SMC for all four lab datasets:

python3 plot_smc_mes_est.py

Working with UAS Data

To use the UAS data, execute the following program:

python3 run_project.py

This will start the program to retrieve SMC using the corresponding model for the UAS dataset.

Please note that the retrieval of SMC from the UAS dataset is performed through a bootstrapping process. The data is randomly split 80/20 into training and testing datasets. This random splitting is repeated 1000 times, so due to the random nature of assigning the testing & training data, the final output may slightly vary each time you run the program. All outputs from the program will be stored in theoutputs folder.

Citing this Repository

If you find the data set or Python scripts in this repository useful for your work, we kindly request that you cite it. The DOI badge below corresponds to the latest version of our software available on Zenodo. DOI

Click on the badge to access the citation details. Thank you for supporting open science!

Owner

  • Login: grit-lab
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.0.3
message: "If the provided data or code is incorporated into your work, please cite as suggested and also reference the original article published in the Journal of Geophysical Research - Biogeosciences:
'Comparison of Soil Moisture Content Retrieval Models Utilizing Hyperspectral Goniometer Data and Hyperspectral Imagery from an Unmanned Aerial System' by Nayma Binte Nur and Charles M. Bachmann, which is accessible via this link: https://doi.org/10.1029/2023JG007381."
authors:
  - family-names: Nur
    given-names: Nayma Binte
    orcid: https://orcid.org/0000-0002-0039-9598
  - family-names: Bachmann
    given-names: Charles M.
    orcid: https://orcid.org/0000-0002-3466-0483
title: "Associated Data and Code for 'Comparison of Soil Moisture Content Retrieval Models Utilizing Hyperspectral Goniometer Data and Hyperspectral Imagery from an Unmanned Aerial System' "
version: 1.0.3
doi: 10.5281/zenodo.8021935
date-released: 2022-06-09
related_identifiers:
- type: "isSupplementTo"
  identifier: "https://doi.org/10.1029/2023JG007381"

GitHub Events

Total
  • Push event: 1
Last Year
  • Push event: 1

Dependencies

requirements.txt pypi
  • lmfit ==1.0.2
  • matplotlib ==3.5.1
  • multiprocess ==0.70.12.2
  • numpy ==1.22.3
  • pandas ==1.4.0
  • prettytable ==2.4.0
  • scikit-learn ==1.0.2
  • scipy ==1.7.3
  • spectral ==0.22.4