Urban spatio-temporal prediction is crucial for informed decision-making, such as transportation management, resource optimization, and urban planning. Although pretrained foundation models for natural languages have experienced remarkable breakthroughs, wherein one general-purpose model can tackle multiple tasks across various domains, urban spatio-temporal modeling lags behind. Existing approaches for urban prediction are usually tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive in-domain training data. In this work, we propose a universal model, UniST, for urban spatio-temporal prediction. Drawing inspiration from large language models, UniST achieves success through: (i) flexibility towards diverse spatio-temporal data characteristics, (ii) effective generative pre-training with elaborated masking strategies to capture complex spatio-temporal relationships, (iii) spatio-temporal knowledge-guided prompts that align and leverage intrinsic and shared knowledge across scenarios. These designs together unlock the potential of a one-for-all model for spatio-temporal prediction with powerful generalization capability. Extensive experiments on 15 cities and 6 domains demonstrate the universality of UniST in advancing state-of-the-art prediction performance, especially in few-shot and zero-shot scenarios.

翻译：城市时空预测对于交通管理、资源优化和城市规划等关键决策至关重要。尽管自然语言预训练基础模型取得了显著突破，使单一通用模型能够处理跨领域的多种任务，但城市时空建模仍相对滞后。现有城市预测方法通常针对特定时空场景设计，需要任务特定的模型架构和大量领域内训练数据。本文提出一种城市时空预测通用模型UniST。受大语言模型启发，UniST通过以下机制实现成功：（i）对多样时空数据特征的灵活性，（ii）采用精心设计的掩码策略进行有效的生成式预训练，以捕捉复杂时空关系，（iii）基于时空知识引导的提示，对齐并利用跨场景的内在共享知识。这些设计共同释放了用于时空预测的"一统所有"模型的潜力，并赋予其强大的泛化能力。在15个城市和6个领域的广泛实验结果表明，UniST在推进最先进预测性能方面具有通用性，尤其在少样本和零样本场景中表现突出。