Dataset for "Machine Learning Driven Sensitivity Analysis of E3SM Land Model Parameters for Wetland Methane Emissions"

This dataset is a part of the paper "Machine Learning Driven Sensitivity Analysis of E3SM Land Model Parameters for Wetland Methane Emissions", accepted for publication in the Journal of Advances in Modeling Earth Systems (JAMES).

Contents

This dataset includes:

lhs-gen-190.csv: Training input LHS samples generated by lhsgen.py.

lhs-gen-50-test.csv: Test input LHS samples generated by lhsgen.py.

190-elm-samples.csv: Training input perturbed parameter samples for performing ELM simulations.

50-elm-test-samples.csv: Test input perturbed parameter samples for performing ELM simulations.

train_CH-CHA.csv: Contains the five ELM simulation output flux values for 240 samples (190 train + 50 test).

lhsgen.py: Script for generating Latin Hypercube Samples.

gpr-fit-new.py: Script for fitting Gaussian Process Regression (GPR) models.

sobol-new.py: Script for performing Sobol sensitivity analysis.

Usage

lhsgen.py:

Use this script to generate the Latin Hypercube Samples for parameter sampling.

gpr-fit-new.py:

This script fits GPR models using the training samples provided in lhs-gen-190.csv.

It tests the models using the input testing samples in lhs-gen-50-test.csv.

The fitted GPR models are stored as .joblib files in the gpr_models directory.

Corresponding cross-validation and R-squared values are stored in .xlsx files.

sobol-new.py:

This script performs Sobol sensitivity analysis using the fitted GPR models by reading the .joblib files.

The Sobol indices are written to .xlsx files in the results directory.