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", submitted to 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. lhsgen.py: Script for generating Latin Hypercube Samples. gpr-fit.py: Script for fitting Gaussian Process Regression (GPR) models. sobol.py: Script for performing Sobol sensitivity analysis. Usage lhsgen.py: Use this script to generate the Latin Hypercube Samples for parameter sampling. gpr-fit.py: This script fits GPR models using the training samples provided in lhs-gen-190.csv and tests using the input testing samples in lhs-gen-50-test.csv. The GPR models are stored as .joblib files. The corresponding cross-validation and R-square values are stored in .xlsx files. sobol.py: This script performs Sobol sensitivity analysis using the fitted GPR models by reading the .joblib files and writes the Sobol indices to .xlsx files.本数据集为已提交至《地球系统建模进展期刊》（Journal of Advances in Modeling Earth Systems, JAMES）的论文《面向湿地甲烷排放的E3SM陆面模型参数机器学习驱动敏感性分析》的组成部分。 数据集内容 本数据集包含以下文件与脚本： 1. lhs-gen-190.csv：由lhsgen.py生成的训练输入拉丁超立方采样（Latin Hypercube Samples, LHS）样本集 2. lhs-gen-50-test.csv：由lhsgen.py生成的测试输入拉丁超立方采样样本集 3. 190-elm-samples.csv：用于开展ELM模拟的训练输入扰动参数样本集 4. 50-elm-test-samples.csv：用于开展ELM模拟的测试输入扰动参数样本集 5. lhsgen.py：用于生成拉丁超立方采样样本的脚本 6. gpr-fit.py：用于拟合高斯过程回归（Gaussian Process Regression, GPR）模型的脚本 7. sobol.py：用于开展Sobol敏感性分析（Sobol sensitivity analysis）的脚本 使用说明 1. lhsgen.py：通过该脚本可生成用于参数采样的拉丁超立方采样样本 2. gpr-fit.py：本脚本依托lhs-gen-190.csv提供的训练样本拟合高斯过程回归模型，并以lhs-gen-50-test.csv中的测试样本开展模型测试。拟合得到的高斯过程回归模型将以.joblib格式文件存储，对应的交叉验证结果与决定系数（R-square）将存储于.xlsx格式文件中 3. sobol.py：本脚本通过读取.joblib格式存储的已拟合高斯过程回归模型，开展Sobol敏感性分析，并将计算得到的Sobol敏感性指数写入.xlsx格式文件中