Agent Based Models (ABMs) have emerged as a powerful tool for investigating
complex social interactions, particularly in the context of public health and
infectious disease investigation. In an effort to enhance the conventional ABM,
enabling automated model calibration and reducing the computational resources
needed for scaling up the model, we have developed a tensorized and
differentiable agent-based model by coupling Graph Neural Network (GNN) and
Long Short-Term Memory (LSTM) network. The model was employed to investigate
the 2019 measles outbreak occurred in New Zealand, demonstrating a promising
ability to accurately simulate the outbreak dynamics, particularly during the
peak period of repeated cases. This paper shows that by leveraging the latest
Artificial Intelligence (AI) technology and the capabilities of traditional
ABMs, we gain deeper insights into the dynamics of infectious disease
outbreaks. This, in turn, helps us make more informed decision when developing
effective strategies that strike a balance between managing outbreaks and
minimizing disruptions to everyday life.

利用最新的人工智能技术和传统的基于代理的模型，该研究通过耦合图神经网络（GNN）和长短期记忆（LSTM）网络，开发了一种张量化且可微分的基于代理的模型，用于研究 2019 年发生在新西兰的麻疹爆发，展示了在重复发病期间准确模拟爆发动态的有希望的能力，从而帮助我们在制定应对爆发和最大限度减少对日常生活干扰的有效策略时做出更明智的决策。