This paper motivates the concept of urban monitoring in a decision-making framework for emergency responses to technical systems that support various types of urban performance, and discussed its conceptual and technical requirements. The conceptual requirements are: it should be (a) real-time for grasping time-dependent disaster situations; (b) multi-scale and (c) multi-performance for cross-sectionally evaluating a variety of component systems at different scales and with various types of performance. The technical requirements derived from the conceptual ones are: (i) rapidity, (ii) versatility, (iii) integrity, (iv) efficiency, (v) easiness, and (vi) extensibility. The fulfillment of these requirements is effectively tackled by data-driven methodologies such as machine learning and artificial intelligence.