Stanford University, Department of Medicine, Stanford, California.
Harvard Medical School, Center for Primary Care, Cambridge, Massachusetts.
Disaster Med Public Health Prep. 2020 Jun;14(3):302-307. doi: 10.1017/dmp.2019.73. Epub 2019 Aug 27.
Armed conflict has contributed to an unprecedented number of internally displaced persons (IDPs), individuals who are forced out of their homes but remain within their country. IDPs often urgently require shelter, food, and healthcare, yet prediction of when IDPs will migrate to an area remains a major challenge for aid delivery organizations. We sought to develop an IDP migration forecasting framework that could empower humanitarian aid groups to more effectively allocate resources during conflicts.
We modeled monthly IDP migration between provinces within Syria and within Yemen using data on food prices, fuel prices, wages, location, time, and conflict reports. We compared machine learning methods with baseline persistence methods of forecasting.
We found a machine learning approach that more accurately forecast migration trends than baseline persistence methods. A random forest model outperformed the best persistence model in terms of root mean square error of log migration by 26% and 17% for the Syria and Yemen datasets, respectively.
Integrating diverse data sources into a machine learning model appears to improve IDP migration prediction. Further work should examine whether implementation of such models can enable proactive aid allocation for IDPs in anticipation of forecast arrivals.
武装冲突导致国内流离失所者（IDP）数量达到前所未有的水平，这些人被迫离开家园，但仍留在国内。IDP 通常迫切需要住所、食物和医疗保健，但预测 IDP 将何时迁移到一个地区仍然是援助提供组织面临的主要挑战。我们试图开发一种 IDP 迁移预测框架，使人道主义援助组织能够在冲突期间更有效地分配资源。
我们使用有关食品价格、燃料价格、工资、位置、时间和冲突报告的数据，对叙利亚和也门境内各省之间以及也门境内各省之间的每月 IDP 迁移进行建模。我们将机器学习方法与基线持续预测方法进行了比较。
我们发现，与基线持续预测方法相比，机器学习方法更能准确地预测迁移趋势。对于叙利亚和也门数据集，随机森林模型在对数迁移的均方根误差方面分别比最佳持续模型高出 26%和 17%。
将多种数据源整合到机器学习模型中似乎可以提高 IDP 迁移预测的准确性。进一步的研究应探讨实施此类模型是否能够使 IDP 提前获得援助分配。
