Entropy-Guided Multivariate Groundwater Network Design for Multi-Source Data Assimilation under Observational Uncertainty

README Supporting Data and Code: 📁 Contents This repository contains data and source code associated with the parameterization of non-Gaussian permeability fields and multi-source data assimilation for subsurface inverse modeling. It includes two major folders: 1. DCGAN model/ Purpose: Dimensionality reduction and parameterization of non-Gaussian permeability fields using a Deep Convolutional Generative Adversarial Network (DCGAN). 2. Multi-source data assimilation/ Purpose: Integrating surrogate modeling, optimal monitoring network data, and parameters inversion procedure using noise multi-source observations. 🧪 Software Requirements Python 3.8+ PyTorch (for DCGAN and DCRN)