内容来源：https://research.google/blog/protecting-cities-with-ai-driven-flash-flood-forecasting/

内容总结：

谷歌推出AI城市内涝预警系统 助力全球防灾减灾

2026年3月12日，谷歌研究团队宣布，其洪水预警平台（Flood Hub）正式推出城市突发性洪水（俗称“城市内涝”）预报功能。该系统利用人工智能技术，可提前最多24小时对全球城市区域的内涝风险进行预测，旨在弥补全球防灾预警能力的不平衡，提升社区应对气候灾害的韧性。

据世界气象组织数据，突发性洪水造成的死亡人数约占全球洪灾死亡总数的85%，每年导致超过5000人丧生，是威胁最大的自然灾害之一。这类灾害通常在强降雨后6小时内发生，迅速将城市街道变为湍急河流。提前12小时的预警即可将损失降低约60%，然而预警能力在全球分布不均：多数发达国家已建立健全预警体系，而全球南方大量地区仍缺乏有效预警基础设施，超过半数发展中国家未能覆盖多灾种预警系统，数十亿人口面临预警缺口。

与传统河流洪水不同，城市内涝突发性强、形成机制复杂，且往往缺乏历史观测数据（如水文监测站记录），这使得传统水文模型和机器学习方法难以进行有效预测。为突破这一瓶颈，谷歌团队研发了名为“Groudsource”的新型AI方法，通过分析公开新闻报道，精准提取历史内涝事件的时间、地点等信息，构建训练数据集。基于此，团队开发了专门针对城市环境的突发性洪水预测模型。

该模型采用循环神经网络架构，综合处理气象预报时间序列数据以及城市密度、地形、土壤渗透率等静态地理与人为因素。目前模型空间分辨率为20公里×20公里，覆盖全球人口密度超过每平方公里100人的主要城市区域。

评估显示，该模型在南美、东南亚等地区的预测准确率与召回率，已接近美国等拥有先进监测网络国家的预警系统水平。例如，经对比调整，美国国家气象局现行突发洪水预警在相同标准下的召回率约为22%，精确率约为44%。谷歌模型在全球多洪灾地区实现了可比性能。团队也指出，由于部分真实洪水事件未被媒体报道，模型性能的实际值可能高于当前评估数据。

此次发布是谷歌地球AI地理空间模型系列的重要进展，也是其危机韧性计划的关键一步。未来，团队将继续优化模型，拓展至农村地区，提升空间分辨率以实现更精准的本地化预报，并集成更多实时气象数据源。

谷歌表示，在气候变化加剧的背景下，开发可规模化应用的AI防灾工具至关重要。通过将预警覆盖范围扩展至危害城市最甚的突发性内涝，该系统有望为各国政府、民众及国际组织提供关键决策信息，助力构建更具韧性的安全社区。

中文翻译：

利用人工智能驱动的山洪预报守护城市
2026年3月12日
Oleg Zlydenko（软件工程师）与Deborah Cohen（研究科学家），Google研究院

我们正通过在城市地区推出山洪预测功能，扩展全球洪水预报的覆盖范围。借助基于新闻数据的新型人工智能训练方法，我们可为这类突发性灾害提供最长24小时的提前预警。此次扩展是提升全球气候适应能力、保障社区安全的关键一步。

根据世界气象组织（WMO）的数据，山洪约占全球洪水相关死亡人数的85%。它们通常在大暴雨后六小时内发生，使城市街道变为湍急河流，每年导致超过5000人死亡，成为全球最致命的灾害之一。早期预警系统对于保障社区安全、及时传递信息至关重要。事实证明，预警系统能够挽救生命并减轻损失：即使仅提前12小时预警，也可将山洪造成的损害减少60%。然而，各国之间存在显著的“预警差距”。最发达国家受益于完善的预报系统，而全球南方广大地区却普遍缺乏能拯救生命的基础设施——在发展中国家，仅有不到一半的国家拥有多灾种早期预警系统。这导致数十亿人无法获得至关重要的预警信息。

为此，我们今天宣布在Flood Hub平台上推出城市山洪预报功能。通过运用全新的人工智能技术方法，我们现在可以提前24小时预测城市地区的山洪风险。这些预测基于多年的研究成果，标志着我们在洪水预报能力上的重大突破，也拓展了洪水预警的覆盖范围。

迄今为止，我们的洪水预报计划主要关注河流洪水（即河水在相对缓慢的过程中漫过堤岸）。虽然我们的预报已覆盖150个国家、超过20亿人口，针对最严重的河流洪水事件提供预警，但城市山洪带来了独特的挑战。与河流洪水不同，山洪具有突发性，需要完全不同的预报方法。

挑战：“看不见”的洪水
预报山洪的挑战之一在于缺乏“真实地面”数据。河流洪水机器学习模型的训练依赖于测量水位或流量的物理水文监测站。通过历史水文站数据训练模型，我们可以准确预测局部水位上升，并预判河流何时可能漫堤。我们还成功将这些预测扩展到无监测站的区域，以提供更广泛的全球河流洪水覆盖。

然而，山洪可能发生在任何地方，且常远离任何水文监测站。在城市环境中，强降雨、不透水地表和排水系统之间复杂的相互作用，使得传统的物理模型在全球范围内进行计算变得极为困难。此外，若缺乏山洪发生具体位置和时间的历史记录，传统的监督式机器学习模型就无法学习预测所需的关键规律。

为解决历史数据缺失的问题，我们采用了Groundsource这一新的人工智能方法，从非结构化数据中高精度提取真实地面信息。借此，我们创建了包含历史山洪事件的Groundsource数据集。我们使用Gemini分析公开的洪水相关新闻报道，以确认洪水事件细节（如明确的地点与时间）。这些记录经汇总后形成历史洪水事件数据集，用于训练和评估我们针对城市地区的新山洪模型。

规模化挑战：本地精度与全球覆盖
针对特定城市环境中的降雨型山洪，已有专门的高精度本地预警系统被开发出来，例如美国佛罗里达州、哥伦比亚巴兰基亚、菲律宾马尼拉、泰国那空是贪玛叻、波多黎各马亚圭斯以及西班牙巴塞罗那等地部署的系统。这些系统通常依赖物理传感器网络，监测直接和雷达反演的降水、水位及流速等变量。虽然在其特定地点精度很高，但由于硬件部署成本高昂、需要针对具体地点进行算法校准和工程专业知识，难以大规模推广。

在更广层面，诸如世界气象组织的山洪指导系统（FFGS）、基于气候学的欧洲径流指数（ERIC）山洪指标以及美国国家气象局（NWS）山洪预警系统等倡议，通过遥感和数值天气模型提供了更广泛的覆盖。然而，这些系统在全球实施中面临重大障碍。主要问题在于它们依赖高分辨率水文地图和基于雷达的天气预报，而这些资源在全球南方地区大多难以获取。此外，依赖专业水文学家解读复杂模型数据并发布可操作的预警，构成了第二大挑战。

为实现近全球覆盖，我们的模型仅使用全球天气产品（NASA IMERG、NOAA CPC）以及来自欧洲中期天气预报中心（ECMWF）集成预报系统（IFS）高分辨率（HRES）大气模型和Google DeepMind基于人工智能的中期全球天气预报模型的实时全球天气预报。该系统目前以20x20公里的空间分辨率运行，这一限制主要受全球可用数据源的分辨率影响。

模型：聚焦城市
基于Groundsource数据训练的新山洪模型旨在回答一个具体问题：根据预报的天气和当地条件，该区域未来24小时内是否可能发生山洪？

该模型采用由长短期记忆（LSTM）单元构建的循环神经网络（RNN）架构，特别适合处理时间序列数据。除了气象时间序列输入外，它还整合了静态的地理、地球物理和人为属性，如城市化密度、地形和土壤吸收率。

我们初期发布重点针对城市地区，为世界大部分人口提供预报。选择此重点是因为训练数据——新闻报道——在这些地点自然更为密集。目前模型预测的是人口密度大于每平方公里100人区域的灾害影响。

评估结果
我们对照Groundsource数据集评估了模型，并注意到报告的精确度指标可能被低估。由于部分现实中的洪水未获媒体报道，有效的警报可能被误判为误报。对数据集随机子集（每大洲100条警报）的人工审核证实了这一差异，显示许多误报实际上是经过验证的洪水事件，并确认实际精确度高于原始指标所示。我们还通过全球灾害感知与协调系统（GDACS）的洪水数据计算了召回率，以评估模型对最具影响力洪水事件的捕捉能力。

详细性能指标如下图所示。关键发现是，我们的模型在全球南方大部分地区（南美洲、东南亚）的精确度和召回率，与通常受益于现代仪器和本地预报专家的最富裕国家性能相当。作为对比，我们尝试使用相同指标估算美国国家气象局（NWS）山洪预警系统的性能。为确保一致性，我们将NWS数据调整至匹配我们的分辨率（20x20公里网格，24小时窗口）。NWS预报的召回率为22%，精确度为44%（如前所述，此值被低估）。这反映了该问题的难度，并表明我们的模型在许多最常受洪水影响的国家取得了类似成果。

然而，仍存在一些差距。在下图（b）中，我们仅显示在GDACS中至少有10次事件的国家以估算召回率。非洲许多国家仍缺乏Groundsource之外的真实地面数据，这使得准确评估模型性能变得困难。

构建全球气候适应能力
此次发布是我们Google地球人工智能地理空间模型与数据集系列的一部分，也是支持谷歌危机应对工作的重要一步，但这仅仅是个开始。我们正积极改进模型以推广至农村地区，降低空间分辨率以实现更高精度的本地预报，并整合更多实时天气数据源。

当我们聚焦于社区和地球的未来时，可扩展、人工智能驱动的适应工具的重要性从未如此清晰。通过将覆盖范围扩展至影响城市最甚的突发性威胁，我们希望为政府、个人和国际组织提供所需信息，助其在不断变化的气候中保持安全。

致谢
许多人为此项工作的开发做出了贡献。我们要特别感谢谷歌研究院的以下同事：Aviel Niego、Avinatan Hassidim、Benny Mosheyev、Dan Korenfeld、Deborah Cohen、Dem Gerolemou、Gila Loike、Grey Nearing、Hadas Fester、Ido Zemach、Juliet Rothenberg、Martin Gauch、Oleg Zlydenko、Oren Gilon、Reuven Sayag、Rotem Mayo、Shmuel Fronman、Shruti Verma、Tzvika Stein、Yossi Matias和Yuval Shildan。

英文来源：

Protecting cities with AI-driven flash flood forecasting
March 12, 2026
Oleg Zlydenko, Software Engineer, and Deborah Cohen, Research Scientist, Google Research
We’re expanding our global flood forecasting coverage with the roll-out of flash flood predictions in urban areas. Using a novel AI training method based on news data, we provide up to 24 hours advance notice for these rapid-onset events. This expansion is a critical step to enhancing global climate resilience and keeping communities safe.
According to the World Meteorological Organization (WMO), flash floods account for approximately 85% of flood related fatalities worldwide. They typically occur within six hours of heavy rain, turn city streets into gushing rivers, and take more than 5,000 lives annually, making them one of the world’s deadliest disasters. Early warning systems (EWS) are essential for keeping communities safe and informed. They have been proven to save lives and mitigate damage: even a 12-hour lead time can provide a 60% reduction in flash flood damage. However, a stark “warning gap" exists between countries. While the most developed nations benefit from robust forecasting, life-saving infrastructure is largely absent across vast regions of the Global South, where less than half of developing countries have access to multi-hazard EWS. This leaves billions of people without the advance notice that makes a critical difference.
To address this, today we’re announcing the roll-out of Urban Flash Flood forecasts on Flood Hub. By leveraging a new AI-powered methodology, we can now predict the risk of flash floods in urban areas up to 24 hours in advance. These predictions build on years of research and mark a significant breakthrough in our flood forecasting capabilities and an expansion of our flood coverage.
To date, our Flood Forecasting Initiative has focused on riverine floods, where rivers overflow their banks over a relatively slow period. While our forecasts cover over 2 billion people in 150 countries for the most significant riverine floods events, urban flash floods present a unique challenge. Unlike riverine floods, flash floods are characterized by their rapid onset, requiring a fundamentally different forecasting approach.
The challenge: The "invisible" flood
One challenge in forecasting flash floods is a lack of "ground truth" data. Riverine machine learning models are trained on physical stream gauges that measure water levels or streamflow. By training models on historical river gauge measurements, we can accurately predict localized water rises and anticipate when a river is likely to exceed its flood banks. We have also successfully extended these predictions to ungauged locations to provide more global coverage of riverine floods.
Flash floods, however, can happen anywhere and often far from any stream gauge. In urban environments, the complex interaction between intense rainfall, impermeable surfaces, and drainage systems makes traditional physical modeling computationally prohibitive at a global scale. Furthermore, without a historical record of exactly where and when flash floods have occurred in the past, traditional supervised ML models cannot learn the patterns necessary to predict them.
To address the lack of historical data, we used Groundsource, a new AI-powered methodology to extract ground truth from unstructured data with high precision. This enabled us to create the Groundsource dataset of past flash flood events. We used Gemini to analyze publicly available news reports that mention floods to confirm flood event details (e.g., clear locations and times). These entries were then aggregated to create a dataset of historical flooding events, which we used to train and evaluate our new flash flood model in urban areas.
The scaling challenge: Local precision vs. global reach
Specialized, hyper-local early warning systems have been engineered to address flash floods from rainfall in specific urban settings, with examples in Florida (US), Barranquilla (Colombia), Manila (Philippines), Nakhon Si Thammarat (Thailand), Mayaguez (Puerto Rico), and Barcelona (Spain). These systems typically rely on a network of physical sensors monitoring variables like direct and radar-inferred precipitation, water levels and flow velocities. While highly accurate for their specific locations, they are difficult to scale because of the high costs of hardware deployment, the need for site-specific calibration algorithms and engineering expertise.
At a broader level, initiatives such as the WMO’s Flash Flood Guidance System (FFGS), the European Runoff Index based on Climatology (ERIC) flash flood indicator, and the US National Weather Service (NWS) Flash Flood Warnings system provide wider coverage through remote sensing and numerical weather models. These systems, however, encounter significant hurdles regarding global implementation. A primary issue is their dependency on high-resolution hydrological maps and radar-based weather forecasts, resources that are largely unavailable within the Global South. Furthermore, the reliance on professional hydrologists to interpret complex model data and distribute actionable warnings presents a second major challenge.
To achieve near-global reach, our model uses only global weather products (NASA IMERG, NOAA CPC) as well as real-time global weather forecasts from the ECMWF Integrated Forecast System (IFS) High Resolution (HRES) atmospheric model and the AI-based medium-range global weather forecasting model by Google DeepMind. The system currently operates at a 20x20 kilometer spatial resolution, a constraint primarily driven by the resolution of globally available data sources.
The model: Focusing on the city
Trained on Groundsource, the new flash flood model is designed to answer a specific question: Given the forecasted weather and local conditions, is a flash flood likely to occur in this area in the next 24 hours?
The model utilizes a recurrent neural network (RNN) architecture constructed with a long short-term memory (LSTM) unit that is specifically suited for processing time-series data. In addition to the meteorological time-series inputs, it also incorporates static geographic, geophysical, and anthropogenic attributes, such as urbanization density, topography, and soil absorption rates.
We focused our initial launch on urban areas, providing forecasts for the majority of the world’s population. The reason for this choice is that the training data — news reports — is naturally more dense in these locations. Currently the model predicts impact in areas with population densities greater than 100 people per square kilometer.
Evaluation results
We evaluated our model against the Groundsource dataset, noting that reported precision metrics are likely underestimates. Because some real-world floods go unreported in the media, valid alerts can be misclassified as false positives. A manual audit of a random subset of the dataset (100 alerts per continent) substantiated this discrepancy, revealing that many false positives were in fact verified flood events, and confirmed that the actual precision is higher than raw metrics show. We calculated recall on floods from the Global Disaster Awareness and Coordination System (GDACS), in order to estimate how well our model captures the most impactful flood events.
Detailed performance metrics are shown in the plots below. The key insight is that the precision and recall of our model in much of the global south — South America, South East Asia — is equivalent to the performance in the richest countries that typically benefit from modern instrumentation and local forecasting experts. For comparison, we tried to estimate the performance of the NWS Flash Flood Warnings in the U.S., using the same metrics. To ensure consistency, we adjusted NWS data to match our resolution (20x20 kilometer grids over 24-hour windows). The recall of the NWS forecasts is 22% and the precision is 44% (which is underestimated, as above). This provides context for the difficulty of the problem, and shows that our model achieves similar results in many of the countries that are most frequently affected by floods.
Some gaps still remain however. In map (b) below we only show countries where we had at least 10 events in GDACS in order to estimate our recall. Many countries in Africa are still lacking in ground truth beyond Groundsource, making it difficult to accurately estimate the accuracy of our model.
Building global climate resilience
This launch is part of our Google Earth AI family of geospatial models and datasets and is a critical step supporting Google’s Crisis Resilience effort, but it is just the beginning. We are actively working to improve the model's generalization to rural areas, reduce the spatial resolution for more hyper-local forecasts, and integrate even more real-time weather data sources.
As we focus on the future of our communities and our planet, the importance of scalable, AI-driven adaptation tools has never been clearer. By expanding our coverage to include the rapid-onset threats that affect cities most, we hope to provide governments, individuals, and international organizations with the information they need to stay safe in a changing climate.
Acknowledgements
Many people were involved in the development of this effort. We would like to especially thank those from Google Research: Aviel Niego, Avinatan Hassidim, Benny Mosheyev, Dan Korenfeld, Deborah Cohen, Dem Gerolemou, Gila Loike, Grey Nearing, Hadas Fester, Ido Zemach, Juliet Rothenberg, Martin Gauch, Oleg Zlydenko, Oren Gilon, Reuven Sayag, Rotem Mayo, Shmuel Fronman, Shruti Verma, Tzvika Stein, Yossi Matias, and Yuval Shildan.