A Deep Gravity model for mobility flows generation.
A Deep Gravity model for mobility flows generation.
复制标题
DOI：
10.1038/s41467-021-26752-4
复制
发表时间：
2021-11-12
影响因子：
16.6
通讯作者：
Pappalardo L
中科院分区：
文献类型：
--
作者：
Simini F;Barlacchi G;Luca M;Pappalardo L
个人在城市内部和城市之间的流动影响着我们社会的关键方面，例如福祉、流行病的传播和环境质量。当无法获得特定感兴趣区域的流动信息时，我们必须依靠数学模型来生成它们。在这项工作中，我们提出了Deep Gravity，这是一种有效的模型，可以生成利用许多特征（例如，土地使用、道路网络、交通、食品、卫生设施），并使用深度神经网络来发现这些特征与流动性之间的非线性关系。我们在英格兰、意大利和纽约州的流动性上进行的实验表明，相对于经典重力模型和不使用深度神经网络或地理数据的模型，Deep Gravity实现了性能的显著提高，特别是在人口密集的感兴趣区域。Deep Gravity具有良好的泛化能力，可以为没有数据可供训练的地理区域生成逼真的流。最后，我们展示了如何根据地理特征解释Deep Gravity产生的流量，并强调了三个考虑的国家之间的关键差异，这些国家用可解释的人工智能技术解释了模型的预测。个人在城市内部和城市之间的流动影响着我们社会的关键方面，例如福祉、流行病的传播和环境质量。在这里，作者使用深度神经网络来发现地理变量和流动性之间的非线性关系。
The movements of individuals within and among cities influence critical aspects of our society, such as well-being, the spreading of epidemics, and the quality of the environment. When information about mobility flows is not available for a particular region of interest, we must rely on mathematical models to generate them. In this work, we propose Deep Gravity, an effective model to generate flow probabilities that exploits many features (e.g., land use, road network, transport, food, health facilities) extracted from voluntary geographic data, and uses deep neural networks to discover non-linear relationships between those features and mobility flows. Our experiments, conducted on mobility flows in England, Italy, and New York State, show that Deep Gravity achieves a significant increase in performance, especially in densely populated regions of interest, with respect to the classic gravity model and models that do not use deep neural networks or geographic data. Deep Gravity has good generalization capability, generating realistic flows also for geographic areas for which there is no data availability for training. Finally, we show how flows generated by Deep Gravity may be explained in terms of the geographic features and highlight crucial differences among the three considered countries interpreting the model’s prediction with explainable AI techniques. The movements of individuals within and among cities influence critical aspects of our society, such as well-being, the spreading of epidemics, and the quality of the environment. Here, the authors use deep neural networks to discover non-linear relationships between geographical variables and mobility flows.
登录
查看更多内容
影响因子：
3.7
作者：
Bettencourt LM;Lobo J;Strumsky D;West GB
通讯作者：
West GB
DOI：
10.1068/a300703
发表时间：
1998-04-01
期刊：
ENVIRONMENT AND PLANNING A
影响因子：
--
作者：
Byrne, D
通讯作者：
Byrne, D
DOI：
10.1007/s41060-020-00207-3
发表时间：
2021-05-01
影响因子：
2.4
作者：
Andrienko, Gennady;Andrienko, Natalia;Trasarti, Roberto
通讯作者：
Trasarti, Roberto
城乡迁移对企业创新的影响：来自中国自然实验的证据
影响因子：
2.8
作者：
Chen, Deqiu;Gao, Huasheng;Ma, Yujing
通讯作者：
Ma, Yujing
影响因子：
3.3
作者：
Balcan, Duygu;Goncalves, Bruno;Hu, Hao;Ramasco, Jose J.;Colizza, Vittoria;Vespignani, Alessandro
通讯作者：
Vespignani, Alessandro