probabilistic_prediction_sgl
A probabilistic prediction of supraglacial lakes on the southwest Greenland Ice Sheet
https://github.com/diarmuidcorr/probabilistic_prediction_sgl
Science Score: 44.0%
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
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.7%) to scientific vocabulary
Repository
A probabilistic prediction of supraglacial lakes on the southwest Greenland Ice Sheet
Basic Info
- Host: GitHub
- Owner: diarmuidcorr
- License: cc0-1.0
- Language: R
- Default Branch: main
- Size: 35.2 KB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 1
Metadata Files
README.md
ProbabilisticPredictionSGL
A probabilistic prediction of supraglacial lakes on the southwest Greenland Ice Sheet.
This code is written in R and allows spatial data processing and modeling using the INLA package in R. \ The script process geospatial data for three different lake boundary conditions: "Defined," "Blurred," and "NoClear." \ Creates a consistent mesh determined for input image data 192*192 pixels.\ It defines an SPDE model by constructinf a Matrn covariance model on the SPDE mesh.\ Then INLA is used to create a separate model for each condition, with different spatial parameters for each.\ A multinomial logistic regression is used to discern one of three lake border conditions (well defined, blurred, and without a clear border) within the images.\ The border condition predicted by the multinomial regression on the new data is used to identify the most appropriate model. \ The selected model is then used to predict over the new data. \ This code was compiled by Diarmuid Corr, Lancaster University. Contact dcorr103@gmail.com for any further information.
The main script, inla.spde.apt.model.R, calls on the multinomial.regression.boundary.model.R script to make a lake border type prediction based on the outcome of multinomial regression, and the est.REG.INLA.R script to create the stacks for the INLA-SPDE model.
Owner
- Name: Diarmuid Corr
- Login: diarmuidcorr
- Kind: user
- Location: Lancaster/London
- Company: Lancaster University
- Repositories: 1
- Profile: https://github.com/diarmuidcorr
PhD student using machine learning and satellite imagery to map Supraglacial Hydrology on the ice sheets of Antarctica and Greenland.
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: Probabilistic_Prediction_SGL
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Diarmuid
family-names: Corr
email: dcorr103@gmail.com
affiliation: Lancaster University
orcid: 'https://orcid.org/0000-0002-7026-2052'
identifiers:
- type: doi
value: 10.5281/zenodo.8434657
repository-code: >-
https://github.com/diarmuidcorr/Probabilistic_Prediction_SGL
abstract: >-
A probabilistic prediction of supraglacial lakes on the
southwest Greenland Ice Sheet using INLA-SPDE.
license: CC0-1.0