城市的 海堤能否抵御特大风暴? 地区的 电网能否抵御破纪录的高温? 城镇的 消防资源能否遏制重大山火?
Can a city的 seawall stand up to a blockbuster storm? Will a region的 power grid hold against record-breaking heat? And can a town的 fire-fighting resources contain a major wildfire?
要回答这些问题, 社区首先需要知道此类极端事件如何发生。野火可能蔓延多远? 风暴可能影响多少地区? 热浪会持续多长时间?
To answer these questions, communities will first need to know how such extreme events could unfold. How far is a wildfire likely to spread? How much of a region might a storm impact? How long could a heat wave last?
但众所周知，极端事件很难预测。就其本质而言, 他们是异常值。在历史记录保存, 极端事件是零星的和罕见的。然而，大多数评估区域的风险的方法都依赖于过去的极端事件来描述未来更极端的,最坏情况。
But extreme events are notoriously difficult to anticipate. By their nature, they are outliers. In the history of record keeping, extreme events are sporadic and rare. Yet most methods that assess a region的 risk depend on extreme events of the past to characterize even more extreme, worst-case scenarios in the future.
现在, 麻省理工学院的工程师开发了一种工具，可以生成可能的极端事件和最坏情况,，并绘制其特征,，例如极端风暴的 可能的持续时间, 强度, 和影响区域。他们的方法的关键在于，它不需要了解以前的极端事件就可以生成可能的未来极端事件。
Now, MIT engineers have developed a tool that generates plausible extreme events and worst-case scenarios, and maps their characteristics, such as an extreme storm的 likely duration, intensity, and area of impact. The key to their method is that it does not need to know about previous extreme events in order to generate plausible future extreme events.
相反,，方法,以机器学习算法,的形式从数据集,学习，例如区域’的每日天气记录和地图。该记录可能包含也可能不包含过去的极端偏差,，例如创纪录的高温或降雨。团队的 算法采用统计方法从可用数据, 中学习，以排除不可信的天气情况。然后，该方法生成可能在给定频率 (（例如每 100 年一次),）的区域发生的极端事件，并预测这些极端事件的规模, 强度, 和持续时间。
Instead, the method, in the form of a machine-learning algorithm, learns from a dataset, such as a region的 daily weather records and maps. This record may or may not contain past extreme deviations, such as record-setting heat or rain. The team的 algorithm takes a statistical approach to learn from the available data, to exclude implausible weather scenarios. The method then generates plausible extreme events that are likely to occur in a region with a given frequency (such as once every 100 years), and projects how those extreme events might look in terms of their size, intensity, and duration.
“我们正在尝试对从未见过的极端,史无前例的事件进行建模,不在数据集中,”，麻省理工学院机械工程研究生、麻省理工学院计算科学与工程中心附属机构的 Kai Chang, 说。
“We are trying to model extreme, unprecedented events that no one has seen before, that are not in the dataset,” says Kai Chang, an MIT graduate student in mechanical engineering and affiliate of the MIT Center for Computational Science and Engineering.
“像卡特里娜飓风这样的事件每 30 到 40 年就会发生一次,” 添加了 Themis Sapsis,，他是麻省理工学院, 机械和海洋工程的 William I. Koch 教授，计算科学与工程中心, 的核心成员，也是麻省理工学院数据, 系统, 和社会研究所的附属机构。 “每 100 年发生一次的卡特里娜飓风会怎样? 会有多糟糕? 那’正是我们’正在尝试量化,以帮助规划者为可能的极端情况做好准备。”
“An event like Hurricane Katrina is something that happens every 30 to 40 years,” adds Themis Sapsis, the William I. Koch Professor of Mechanical and Ocean Engineering at MIT, a core member of the Center for Computational Science and Engineering, and an affiliate of the MIT Institute for Data, Systems, and Society. “What will be the Katrina that happens every 100 years? How bad will it be? That的 exactly what we’re trying to quantify, to help planners prepare for plausible extreme scenarios.”
除了天气事件, 之外，该团队将其称为“极端事件感知,”或“η-学习,” 的方法, 还可以应用于其他领域,，例如机器人导航和金融市场。
Beyond weather events, the approach, which the team has dubbed Extreme Event Aware, or “η-learning,” can be applied to other fields, such as robotic navigation and financial markets.
“金融市场崩盘是极端事件，是多种事件的复杂组合,涉及许多不同部门,” Chang说。 “导致市场崩溃的相互作用是什么?这是该方法可以探索的内容。”
“Financial market crashes are extreme events that are a complicated combination of things, involving many different sectors,” Chang says. “What is the interaction that leads to a market crash? That is something that this method could explore.”
“比一切都危险”
“Riskier than everything”
为了估计某个地区’发生极端天气事件的风险,规划者,政策制定者,和保险公司通常会提出这样的问题：“纽约市百年一遇的风暴是什么样的?”为了得到答案,，他们使用计算机模拟，这些模拟必须接受过包括极端,百年一遇事件的数据训练,以便了解导致这些事件的条件并生成这些事件未来可能发生的情况。
To estimate a region的 risk of an extreme weather event, planners, policymakers, and insurance companies typically ask questions such as “What does a once-every-100-year storm look like for New York City?” For answers, they use computer simulations that must be trained on data that includes extreme, once-in-a-century events, in order to learn the conditions leading up to those events and generate scenarios of how those events might look in the future.
“这些方法假设我们在数据集中看到了非常灾难性的事件,，他们构建了一种方法来估计这些事件的风险,，或者尝试准确预测已发生的事件,” Chang 说。 “我们正在尝试了解: 史无前例的极端事件是什么样的，这些事件比以前发生的所有事件都更具风险，但仍然是合理的?”
“These methods assume there are very disastrous events that we have seen in the dataset, and they build a method to either estimate the risk of those events, or they try to predict exactly the events that have happened,” Chang says. “We are trying to see: What do unprecedented extreme events look like that are riskier than everything that has happened before and yet are still plausible?”
例如, 如果纽约市有史以来记录的最极端降雨量为 200 毫米, 什么样的风暴会产生更极端的测量值, 300 毫米? 这样的事件以前从未被记录过，但仍然可能是合理的。城市规划者想知道这样的风暴将袭击,的何处、覆盖的区域有多大,以及强度有多大。风暴模拟可以帮助他们评估基础设施并计划增援。
For example, if the most extreme rainfall measurement ever recorded in New York City is 200 millimeters, what kind of storm would produce an even more extreme measurement, of 300 millimeters? Such an event has never been recorded before and yet could still be plausible. City planners would want to know where such a storm would hit, how big an area it would cover, and how intense it would be. A simulation of the storm could help them assess infrastructure and plan reinforcements.
“我们想要预测这些最坏情况的地图,” Sapsis 说。 “没有方法可以有效地预测很少发生的事件。”
“We want to predict maps of these worst-case scenarios,” Sapsis says. “There is no method that does this efficiently to predict events that happen rarely.”
团队’的新算法可以生成合理的,前所未有的极端场景,，而无需使用以前的极端事件数据进行训练。为此,，算法结合并学习有关两种类型数据: 点统计数据和空间地图之间关系的统计数据, 或概率,。
The team的 new algorithm generates plausible, unprecedented extreme scenarios, without needing to train on previous extreme event data. To do so, the algorithm combines and learns statistics, or probabilities, about the relationships between two types of data: point statistics and spatial maps.
为了证明,，研究人员应用该方法生成美国大陆未来极端降水事件的地图。研究人员从 25 年的每小时降水量图, 开始，将其汇总到每日地图中。根据完整记录,，他们计算了点统计数据，描述了地图上最大降雨量达到给定水平的频率。然后，他们在记录,的前六个月的成对低分辨率和高分辨率空间地图上训练算法，其中很少或根本没有最极端降雨水平的例子。
To demonstrate, the researchers applied the method to generate maps of future extreme precipitation events over the continental United States. The researchers began with 25 years of hourly precipitation maps, which they pooled into daily maps. From the full record, they computed point statistics describing how often the maximum rainfall across a map reached a given level. They then trained the algorithm on paired low- and high-resolution spatial maps from just the first six months of the record, which contained few or no examples of the most extreme rainfall levels.
从这些数据, 中，算法了解到低分辨率地图中的模式如何与详细的, 高分辨率降水地图相对应。然后，它使用点统计数据来限制这些地图中表示的极端降雨量。这种组合使算法能够为比训练数据—中表示的更极端的事件生成合理的空间模式，例如,，可能的位置,大小,以及百年一遇的最大降雨量事件的强度，最大为300毫米。
From these data, the algorithm learned how patterns in low-resolution maps correspond to detailed, high-resolution precipitation maps. It then used the point statistics to constrain the rainfall extremes represented in those maps. This combination enables the algorithm to generate plausible spatial patterns for events more extreme than those represented in the training data — for instance, the possible locations, sizes, and intensities of a once-in-a-century rainfall event with a maximum of 300 millimeters.
用户可以用诸如, “纽约市的百年一遇的风暴是什么样子?”来提示经过训练的算法，然后该算法会生成统计上可能以该频率,发生的风暴的地图，包括风暴’的大小,覆盖面积,和降雨强度等特征。
A user can prompt the trained algorithm with a question such as, “What could a once-in-a-century storm look like in New York City?” The algorithm then generates maps of statistically plausible storms that are likely to occur with that frequency, including characteristics such as the storm的 size, area of coverage, and intensity of rainfall.
“有人可能会说, ‘I’m有兴趣建造一些东西来承受每100年发生一次的事件的风险,’” Chang说。 “我们能做的就是产生数千种可能的实现，这些实现将以这种罕见的频率发生。”
“Someone can say, ‘I’m interested in building things to withstand the risk of an event that happens every 100 years,’” Chang says. “What we can do then is produce thousands of possible realizations that will happen with this sort of rare frequency.”
只要有相关的点统计数据和空间数据,，该方法就可以用于可视化其他前所未有的事件，例如极端洪水和野火。
As long as relevant point statistics and spatial data are available, the method could be applied to visualize other unprecedented events such as extreme floods and wildfires.
“极端事件已成为战略问题,不仅仅是环境问题—我们’已经优化了全球系统以提高效率,，这种效率的代价是’在任何地方都几乎没有余裕。 Sapsis 表示，单一极端事件会在数周内通过供应链, 能源市场, 和食品系统传播,”。 “能够对尚未发生’t的事件进行概率分析现在是一个国家和经济弹性的问题。”
“Extreme events have become a strategic concern, not just an environmental one — we’ve optimized global systems for efficiency, and the price of that efficiency is that there的 very little slack left anywhere. A single extreme event propagates through supply chains, energy markets, and food systems in weeks,” Sapsis says. “Being able to put a probability on an event that hasn’t happened yet is now a question of national and economic resilience.”
这项研究的,部分,得到了Vannevar Bush教员奖学金和美国空军科学研究办公室的支持。
This research was supported, in part, by a Vannevar Bush Faculty Fellowship and the U.S. Air Force Office of Scientific Research.