arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.12696cs.LGstat.ML
收藏

莫桑比克实现可持续的独立人口普查估计

Towards Sustainable Census Independent Population Estimation in Mozambique

University of Edinburgh(爱丁堡大学);UNICEF(联合国儿童基金会)

Isaac Neal, Sohan Seth, Gary Watmough, Mamadou Saliou Diallo

摘要:

可靠和频繁的人口估计是制定疫苗接种政策和规划基础设施交付的关键。由于人口普查缺乏这些任务所需的时空分辨率,使用遥感和微型人口普查数据的独立于人口普查的方法已变得流行。我们估计在莫桑比克的两个试点地区的两次人口普查之间的人口计数。为了鼓励可持续发展,我们评估了使用公开数据集来估计人口的可行性。我们还探索了迁移学习与现有的注释数据集预测建筑物的足迹,并从感兴趣的区域训练额外的“点”注释,以提高这些估计。我们观察到,人口预测改善时,使用这种方法估计的足迹面积与只有公开可用的功能。

英文摘要:

Reliable and frequent population estimation is key for making policies around vaccination and planning infrastructure delivery. Since censuses lack the spatio-temporal resolution required for these tasks, census-independent approaches, using remote sensing and microcensus data, have become popular. We estimate intercensal population count in two pilot districts in Mozambique. To encourage sustainability, we assess the feasibility of using publicly available datasets to estimate population. We also explore transfer learning with existing annotated datasets for predicting building footprints, and training with additional `dot' annotations from regions of interest to enhance these estimations. We observe that population predictions improve when using footprint area estimated with this approach versus only publicly available features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑