Forecasting precipitation in the Arctic using probabilistic machine learning informed by causal climate drivers

2025-10-28

AI Summary

This study addresses the low reliability and poor interpretability of precipitation forecasting in vulnerable Arctic regions, such as Bear Island and Ny-Ålesund. To tackle this, we propose a time-frequency-aware predictive framework that integrates causal inference with probabilistic machine learning. Methodologically, we innovatively incorporate wavelet coherence analysis and synergistic–unique–redundant decomposition (SURD) to quantify causal interactions among multiple climate drivers across distinct temporal scales. Furthermore, we combine probabilistic modeling with conformal prediction to generate well-calibrated, nonparametric prediction intervals. Our framework significantly improves probabilistic accuracy in forecasting both precipitation dynamics and intensity—particularly enhancing early warning capability for extreme events. Validation at both sites demonstrates high reliability and interpretable uncertainty quantification. The approach establishes a novel paradigm for Arctic marine climate risk assessment and the development of operational early-warning systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Understanding and forecasting precipitation events in the Arctic maritime environments, such as Bear Island and Ny-Ålesund, is crucial for assessing climate risk and developing early warning systems in vulnerable marine regions. This study proposes a probabilistic machine learning framework for modeling and predicting the dynamics and severity of precipitation. We begin by analyzing the scale-dependent relationships between precipitation and key atmospheric drivers (e.g., temperature, relative humidity, cloud cover, and air pressure) using wavelet coherence, which captures localized dependencies across time and frequency domains. To assess joint causal influences, we employ Synergistic-Unique-Redundant Decomposition, which quantifies the impact of interaction effects among each variable on future precipitation dynamics. These insights inform the development of data-driven forecasting models that incorporate both historical precipitation and causal climate drivers. To account for uncertainty, we employ the conformal prediction method, which enables the generation of calibrated non-parametric prediction intervals. Our results underscore the importance of utilizing a comprehensive framework that combines causal analysis with probabilistic forecasting to enhance the reliability and interpretability of precipitation predictions in Arctic marine environments.

Problem

• Forecasting Arctic precipitation using probabilistic machine learning with causal drivers
• Analyzing scale-dependent relationships between precipitation and atmospheric variables
• Generating calibrated prediction intervals for reliable Arctic precipitation forecasts

Innovation

• Probabilistic machine learning framework for precipitation forecasting
• Wavelet coherence analysis of scale-dependent climate relationships
• Conformal prediction method generating calibrated uncertainty intervals