Urban Information Lab, The School of Architecture, The University of Texas at Austin, Austin, TX, United States of America.
PLoS One. 2024 Jul 24;19(7):e0306782. doi: 10.1371/journal.pone.0306782. eCollection 2024.
Transit deserts refer to regions with a gap in transit services, with the demand for transit exceeding the supply. This study goes beyond merely identifying transit deserts to suggest actionable solutions. Using a multi-class supervised machine learning framework, we analyzed factors leading to transit deserts, distinguishing demand by gender. Our focus was on peak-time periods. After assessing the Support Vector Machine, Decision Tree, Random Forest, and K-nearest Neighbor, we settled on the Random Forest method, supported by Diverse Counterfactual Explanation and SHapley Additive Explanation in our analysis. The ranking of feature importance in the trained Random Forest model revealed that factors such as density, design, distance to transit, diversity in the built environment, and sociodemographic characteristics significantly contribute to the classification of transit deserts. Diverse Counterfactual Explanation suggested that a reduction in population density and an increase in the proportion of green open spaces would likely facilitate the transformation of transit deserts into transit oases. SHapley Additive Explanation highlighted the differential impact of various features on each identified transit desert. Our analysis results indicate that identifying transit deserts can vary depending on whether the data is aggregated or separated by demographics. We found areas that have unique transit needs based on gender. The disparity in transit services was particularly pronounced for women. Our model pinpointed the core elements that define a transit desert. Broadly, to address transit deserts, strategies should prioritize the needs of disadvantaged groups and enhance the design and accessibility of transit in the built environment. Our research extends existing analyses of transit deserts by leveraging machine learning to develop a predictive model. We developed a machine learning-powered interactive dashboard. Integrating participatory planning approaches with the development of an interactive interface could enhance ongoing community engagement. Planning practices can evolve with AI in the loop.
过境荒漠是指过境服务存在缺口的区域，过境需求超过了供给。本研究不仅仅是要识别过境荒漠，还提出了可行的解决方案。我们使用多类监督机器学习框架，分析了导致过境荒漠的因素，并按性别区分了需求。我们的重点是高峰时段。在评估了支持向量机、决策树、随机森林和 K 近邻之后，我们选择了随机森林方法，并在分析中使用了多样化反事实解释和 Shapley 加法解释来支持该方法。在训练后的随机森林模型中，特征重要性的排名显示，密度、设计、到过境的距离、建成环境的多样性以及社会人口特征等因素，对过境荒漠的分类有很大的影响。多样化反事实解释表明，降低人口密度和增加绿色开放空间的比例，可能有助于将过境荒漠转变为过境绿洲。Shapley 加法解释突出了各种特征对每个已识别的过境荒漠的不同影响。我们的分析结果表明，识别过境荒漠可能因数据是按人口统计数据聚合还是分离而有所不同。我们根据性别发现了具有独特过境需求的区域。女性的过境服务差距尤其明显。我们的模型确定了定义过境荒漠的核心要素。总的来说，为了解决过境荒漠问题，策略应优先考虑弱势群体的需求，并加强建成环境中的过境设计和可达性。我们的研究通过利用机器学习来开发预测模型，扩展了对过境荒漠的现有分析。我们开发了一个基于机器学习的交互式仪表板。将参与式规划方法与交互式界面的开发相结合，可以增强正在进行的社区参与。规划实践可以随着人工智能的发展而不断发展。
