A survey on long-term traffic prediction from the information fusion perspective: Requirements, methods, applications, and outlooks

Abstract

Long-term traffic prediction (LTP) aims to predict future traffic conditions based on the fusion of multi-dimensional historical data across extended time horizons, emerging as a rapidly advancing research domain with extensive applications in predicting traffic flow, speed, accident likelihood, and congestion patterns, thereby significantly enhancing societal mobility and quality of life. Compared with the general traffic prediction task, the traffic prediction task under long time span is more challenging. It is necessary to summarize the internal requirements of LTP to lead the development of this field. However, there has been no comprehensive review to systematically summarize and synthesize it. To address this gap, we present the first systematic survey of LTP from an information fusion perspective, encompassing interval requirements, targeted methodologies, application scenarios, and performance metrics. Specifically, we first establish the knowledge framework of traffic prediction tasks and formalize the concept of LTP, then categorize and analyze existing approaches through the lens of internal requirements. Furthermore, we meticulously examine application scenarios alongside corresponding performance benchmarks, datasets, and evaluation metrics. Ultimately, we delineate prevailing challenges and potential research directions to inspire future investigations.