Abstract Informal subdivisions and manufactured home communities make up a substantial share of the United States’ housing stock but receive relatively little attention in the scholarly literature. The time-intensive nature of identifying these often-invisible communities through the analysis of satellite imagery and property records limits their systematic study. What research does exist on these communities suggests that they are often exposed to concentrated forms of economic, social, and environmental vulnerability. This paper uses big data to develop building footprint-derived landscape metrics capable of identifying and distinguishing between informal subdivisions and manufactured home communities based on their morphology. We use a data set of building footprints developed by Microsoft and released publicly in 2018 to measure the size, type, orientation, placement, and uniformity of housing in more than 2000 residential neighborhoods Hidalgo County, Texas, where more than 1000 informal subdivisions have been documented by prior research. Support vector machines (SVMs) and cross-validation are used to test the ability of these metrics to distinguish between three neighborhood types: informal subdivisions, manufactured housing communities, and formal subdivisions (or traditionally planned neighborhoods). Our models can accurately classify these three types of community approximately 91 % of the time. We then examine whether there is evidence to support the further disaggregation of these types of neighborhood, as is the case in both policy and scholarship. Our analysis of the morphology of these communities points to little evidence for the current distinction in state and federal law between pre- and post-1990 informal subdivisions; we do, however, find evidence for the need to distinguish between manufactured home communities with distinct tenure arrangements: namely, land-lease communities that we call manufactured home parks and land-owner communities that we call manufactured home subdivisions. We conclude by offering new research directions made possible by this novel identification method.

中文翻译：

---

建筑足迹衍生的景观指标，用于识别非正式细分和制造的家庭社区：德克萨斯州伊达尔戈县的试点应用

摘要 非正式住宅区和人造住宅社区占美国住房存量的很大一部分，但在学术文献中很少受到关注。通过分析卫星图像和财产记录来识别这些通常不可见的社区的时间密集性限制了他们的系统研究。对这些社区的研究表明，他们经常面临经济、社会和环境脆弱性的集中形式。本文使用大数据来开发基于建筑足迹的景观指标，能够根据形态识别和区分非正式细分和制造的家庭社区。我们使用由微软开发并于 2018 年公开发布的建筑足迹数据集来衡量大小、类型、德克萨斯州伊达尔戈县 2000 多个居民区的住房方向、位置和统一性，先前的研究已记录了 1000 多个非正式分区。支持向量机 (SVM) 和交叉验证用于测试这些指标区分三种社区类型的能力：非正式细分、制造的住房社区和正式细分（或传统规划的社区）。我们的模型可以在大约 91% 的时间内准确地对这三种类型的社区进行分类。然后，我们检查是否有证据支持将这些类型的社区进一步分解，就像政策和学术中的情况一样。我们对这些社区形态的分析表明，目前州和联邦法律在 1990 年前和1990 年之后的非正式分区之间的区别几乎没有证据。然而，我们确实找到了需要区分具有不同使用权安排的预制房屋社区的证据：即我们称之为预制房屋公园的土地租赁社区和我们称之为预制房屋细分的土地所有者社区。最后，我们提供了通过这种新颖的识别方法实现的新研究方向。土地租赁社区，我们称之为预制住宅公园和土地所有者社区，我们称之为预制房屋细分。最后，我们提供了通过这种新颖的识别方法实现的新研究方向。土地租赁社区，我们称之为预制住宅公园和土地所有者社区，我们称之为预制房屋细分。最后，我们提供了通过这种新颖的识别方法实现的新研究方向。