AI 中文总结
本研究基于多层网络，用10种模型探究跨行业人类运动可预测性，明确关键特征，发现非线性模型表现最优、周度运动更易预测，为人类运动建模提供实用进展。
AI 中文摘要
理解人类运动的时空模式在城市设计、疾病防控、社会与认知科学、应急响应规划等诸多应用中至关重要。近期，多层移动网络被用于研究按不同行业部门分层时，空间单元（如人口普查区）间的运动差异——例如前往杂货店、学校或医院的运动。本研究利用人口统计、社会经济及基础设施信息训练统计与机器学习模型，探究跨行业运动的可预测性。我们对比了10种预测模型，发现非线性模型（随机森林回归始终表现最优）具有优势；明确了预测的关键特征：区域向外运动的关键特征是人口规模，区域向内运动的关键特征是行业相关基础设施。两类特征中，向内运动（入度）的预测通常更困难，但食品服务相关运动的差异较小。我们还对比了周度运动与时间平均运动的预测，发现加入时间编码输入特征后，周度运动比时间平均值更易预测（至少对非线性预测模型而言）。这些发现为将机器学习应用于人类运动建模及众多下游应用提供了实用进展。
英文摘要
Understanding the spatiotemporal patterns of human movement is important across diverse applications including urban design, disease control, social and cognitive science, and emergency response planning. Recently, multilayer mobility networks were used to study how movements between spatial units (e.g., census tracts) can significantly vary when they are stratified according to different industry sectors-e.g., movements to grocery stores, to schools, or to hospitals. Here, we study the predictability of movements across different industry sectors using statistical and machine learning models trained on demographic, socioeconomic, and infrastructure information. We compare ten predictive models and identify advantages for nonlinear models (with random forest regression being a consistent top performer). We identify the most important features enabling prediction (population size for outward movements from regions and industry-related infrastructure for movements into regions). Of the two, prediction for inward movements (i.e., in-degrees) is generally more difficult; however, the difference is small for movements associated with food services. We also compare the prediction of weekly and time-averaged movements, finding that with the addition of time-encoding input features, weekly movements are easier to predict than time-averaged values (at least for the nonlinear predictive models). These findings provide a practical step toward using machine learning for human movement modeling and the many downstream applications.
Comments16 pages, 9 figures
