A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study

2025-05-29

AI Summary

Traditional methods such as Gaussian processes struggle to capture non-Gaussian spatial dependence and extreme co-occurrence patterns. To address this, we propose A2-SBNN—a Bayesian neural network whose weight priors directly incorporate a bivariate Archimedean (A2) copula, enabling end-to-end mapping from spatial coordinates to continuous fields while preserving tail dependence. Methodologically, we introduce a joint calibration framework integrating Wasserstein distance loss, moment-matching constraints, and correlation regularization. Experiments demonstrate that A2-SBNN significantly outperforms Gaussian process baselines across multiple spatial dependence intensities, particularly in modeling extreme event co-occurrence and quantifying predictive uncertainty. The model achieves superior reliability and accuracy in both tail-dependent spatial inference and probabilistic forecasting.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

In this paper, we introduce the A2 Copula Spatial Bayesian Neural Network (A2-SBNN), a predictive spatial model designed to map coordinates to continuous fields while capturing both typical spatial patterns and extreme dependencies. By embedding the dual-tail novel Archimedean copula viz. A2 directly into the network's weight initialization, A2-SBNN naturally models complex spatial relationships, including rare co-movements in the data. The model is trained through a calibration-driven process combining Wasserstein loss, moment matching, and correlation penalties to refine predictions and manage uncertainty. Simulation results show that A2-SBNN consistently delivers high accuracy across a wide range of dependency strengths, offering a new, effective solution for spatial data modeling beyond traditional Gaussian-based approaches.

Problem

• Model non-Gaussian spatial dependencies in data
• Capture extreme dependencies and rare co-movements
• Improve accuracy beyond Gaussian-based spatial models

Innovation

• A2 Copula embedded in network initialization
• Wasserstein loss and moment matching training
• Models non-Gaussian spatial dependencies effectively