Finding the root causes for risks regarding warfighting systems for the U.S. Marine Corps is critical for designing policies and taking actions in strategic, operational, and tactical levels to prevent future risks. These risks may be attributed to multiple factors and the data sources might reside in distributed environment and often are difficult to share. In this paper, we show collaborative learning agents (CLAs) to analyze data sources separately and then fuse the patterns and models using shared vocabularies in the patterns instead of fusing raw data. We also show causal learning, counterfactuals reasoning, and knowledge graphs to discover root causes from structured data. These counterfactuals knowledge graphs from unstructured data serve as context inputs to a large language model, which can generate more relevant and meaningful descriptive root cause analysis. We demonstrate the methodologies using the use case from the mishap and incident reports of a marine transportation equipment and related data resources from the I Marine Expeditionary Force (IMEF).