PreDisM: Pre-Disaster Modelling With CNN Ensembles for At-Risk Communities
PreDisM: Pre-Disaster Modelling With CNN Ensembles for At-Risk Communities
复制标题
PreDisM：使用 CNN 集成为高危社区进行灾前建模
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Y. Miura
中科院分区：
文献类型：
--
作者：
Vishal Anand;Y. Miura
机器学习社区最近对气候和灾害损害领域的兴趣增加，这是由于自然灾害的发生率显著增加（例如，飓风、森林火灾、洪水、地震）。然而，对减轻即将发生的自然灾害可能造成的破坏没有给予足够的重视。我们通过在事前预测建筑物级别的损害来探索这一关键领域，这将使国家行为者和非政府组织能够最好地配备资源分配，以最大限度地减少或先发制人地减少损失。我们引入了PreDisM，它采用ResNets和决策树上的全连接层的集合来捕获图像级和元级信息，以准确估计人造结构对灾害发生的弱点。我们的模型表现良好，是响应调整跨类型的灾害，并突出了先发制人的灾害损害建模的空间。
The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that employs an ensemble of ResNets and fully connected layers over decision trees to capture image-level and meta-level information to accurately estimate weakness of man-made structures to disaster-occurrences. Our model performs well and is responsive to tuning across types of disasters and highlights the space of preemptive hazard damage modelling.
确定针对风暴潮和海平面上升的最佳海岸保护策略的方法框架
影响因子：
3.7
作者：
Miura, Yuki;Qureshi, Huda;Ryoo, Chanyang;Dinenis, Philip C.;Li, Jiao;Mandli, Kyle T.;Deodatis, George;Bienstock, Daniel;Lazrus, Heather;Morss, Rebecca
通讯作者：
Morss, Rebecca
影响因子：
--
作者：
Miura, Yuki;Dinenis, Philip C.;Mandli, Kyle T.;Deodatis, George;Bienstock, Daniel
通讯作者：
Bienstock, Daniel
基于 GIS 的风暴潮高速模拟 - 导致海平面上升的洪水核算
影响因子：
2.7
作者：
Miura, Yuki;Mandli, Kyle T.;Deodatis, George
通讯作者：
Deodatis, George