Command and control (C2) maps in military unmanned aerial vehicles (UAVs) are often cluttered beyond the needs of operators. Unfortunately, information overload increases the operators' mental effort and mission performance suffers. To make C2 maps more useful and improve operator performance, this study proposes a triangular approach to highlighting mission-critical information. First, the underlying value of map information and its relevance to mission success are examined. Second, algorithms based on machine learning are developed to facilitate information integration and generate visualization items, via tagging in time and space, where the appropriate area of relevance for each item is defined. Third, the algorithms are improved to dynamically update the visualizations. The proposed approach and developed algorithms are being evaluated based on four experiments with professional operators in simulated UAV and C2 environments. Hopefully, it would be possible to generalize the algorithms developed in this research-in-progress to other spatial and temporal domains where workload must be reduced.