Urban Indicator Prediction

What is it about?

Urban indicator prediction has become an important tool for urban planning and decision-making, and promoting the process of urbanization. However, the existing methods often rely on the time-consuming and resource-intensive "pre-training and fine-tuning" paradigm. To address this, we propose UrbanICL, an urban in-context learning framework, as a new paradigm for urban indicator prediction

Featured Image

Photo by Owen Lystrup on Unsplash

Photo by Owen Lystrup on Unsplash

Why is it important?

Compared to directly predicting urban indicators, we obtain predictions for new regions by aggregating the downstream labels of similar regions. Specifically, a retrieval-based urban in-context learning module is proposed to retrieve regions with similar urban semantics and aggregate their corresponding labels to make predictions for new regions. Our framework, with in-context learning, brings a new insight for urban indicator prediction. The experiment results demonstrate the effectiveness of UrbanICL, even in an extremely low-consumption and time-efficient manner.