Coupled Heterogeneous Association Rule Mining (CHARM): Application Toward Inference of Modulatory Climate Relationships

Abstract

The complex dynamic climate system often exhibits hierarchical modularity of its organization and function. Scientists have spent decades trying to discover and understand the driving mechanisms behind western African Sahel summer rainfall variability, mostly via hypothesis-driven and/or firstprinciples based research. Their work has furthered theory regarding the connections between various climate patterns, but the key relationships are still not fully understood. We present Coupled Heterogeneous Association Rule Mining (CHARM), a computationally efficient methodology that mines higher-order relationships between these subsystems' anomalous temporal phases with respect to their effect on the system's response. We apply this to climate science data, aiming to infer putative pathways/cascades of modulating events and the modulating signs that collectively define the network of pathways for the rainfall anomaly in the Sahel. Experimental results are consistent with fundamental theories of phenomena in climate science, especially physical processes that best describe sub-regional climate.

Multi-scale quantitative precipitation forecasting using nonlinear and nonstationary teleconnection signals and artificial neural network models

“…Climate is generally deemed the best example of nonlinear dynamics driven by interactions of its subsystems with multiple scales (e.g., the ocean, the terrestrial systems, and the atmosphere) (Gonzalez et al, 2013). Hence, the main challenge in studying the climate system is to detect the key linkages and their interactions/feedbacks that modulate the dynamic behaviour of the system (Gonzalez et al, 2013).…”

“…Climate is generally deemed the best example of nonlinear dynamics driven by interactions of its subsystems with multiple scales (e.g., the ocean, the terrestrial systems, and the atmosphere) (Gonzalez et al, 2013). Hence, the main challenge in studying the climate system is to detect the key linkages and their interactions/feedbacks that modulate the dynamic behaviour of the system (Gonzalez et al, 2013). As an example of the climate systems' functional response, we focused on the precipitation in the northeastern United States, a region with well documented, strong correlations with known climate indices or teleconnection patterns regarded as a set of index regions in the oceans, such as the Pacific North American (PNA), El-Nino Southern Oscillation (ENSO), and the North Atlantic Oscillation (NAO) Patterns.…”