Intelligent data fusion techniques are being developed and optimized for use in chemical detection. In this effort, a data fusion framework will be created to provide a cohesive data management and decision making utility that will capture all available data and more efficiently direct the expenditure of time, labor, and resources. Pattern recognition techniques with expert information about the strengths and weaknesses associated with the data acquisition techniques and expert knowledge are being used. Outputs from a variety of sensors are utilized in an overall decision-making algorithm that is more accurate than any individual sensor is on its own. Data fusion algorithms utilized must be tailored to the characteristics of the input data types to extract the maximum information available from sensing technologies. Data fusion algorithms are being developed by applying empirical and theoretically guided heuristics to choose appropriate decision and data combination rules that incorporate selected data features, sensor outputs, and other processed data along with available expert knowledge. Finally, the output of the data fusion algorithms will be assessed with a Bayesian decision tree to provide resilience to missing or corrupted data, and a statistically rigorous method for accommodating imperfect classifications and detections in the earlier steps. Thus, the information accumulated will be utilized to implement an optimized data fusion network that begins with the chosen signal processing algorithms and ends with a Bayesian decision tree based on the data fusion algorithms.