【】

Google is expanding its flood forecasting capabilities to the United States and Canada, providing a potentially lifesaving resource as the climate crisis continues to exacerbate environmental events and threaten communities worldwide.

The company's global Flood Hubprediction tool provides real-time flood forecasts and visualizations integrated with Google Search and Maps, alerting communities and humanitarian organizations to imminent disaster. Now, users can count on improved public alerts, with the ability to enter nearly any global location on the Google Flood Hub platform — and in many places, Google Search and Maps — to proactively monitor flood risk and prepare for emergency response.

"Floods are the most common natural disaster, causing thousands of fatalities and disrupting the lives of millions every year," wrote vice president of engineering and research Yossi Matias in a Google Sustainabilityannouncement. "As cities and individuals work to address the effects of climate change, we believe AI can play a transformative role. We're working to build more solutions — like our AI-based predictions and forecasting — that provide actionable information to help individuals stay safe and communities plan ahead." 

In May, Google turned ongoing flood forecasting researchinto the publicly accessible Flood Hub, providing flood indicatorsto more than 80 countries across Africa, the Asia-Pacific region, Europe, South America, and Central America. In its first iteration, the resource focused on "territories with the highest percentages of population exposed to flood risk and experiencing more extreme weather, covering 460 million people globally."

FloodHub will now provide information on potential riverine floods across 800 locations in the United States and Canada, covering the homesteads of more than 12 million people. 

The company's flood forecasting tools use a combination of two AI models fed with publicly available data sources. Google's Hydrologic Model forecasts the amount of water flowing in a river, while its Inundation Model predicts what areas will be affected and how high the water level will be, the company explains. The models allow the company and partnering agencies, like the United Nations, local government, and other NGOs, to issue emergency alerts up to seven days before the event.

Early warning systems are becoming more essential to the general public. Continuous warming of our planet has led to worsening periods of rain, and with intense rain has come devastating flooding in regions unaccustomed to dealing with dangerous water levels. It's expected to get worse. 

Last year, Pakistan faced a deluge of rain that overpowered expected monsoon forecasts, leading to extreme flooding that many scientists called a deadly climate emergency. Just last month, New York City residents faced massive citywide flooding that shut down local transit and threatened lives and homes. New York Gov. Kathy Hochul declared a state of emergency, calling the situation a "life-threatening rainfall event."

According to FEMA and the National Flood Insurance Program, more and more Americans outside of high-risk areas are experiencing unexpected flooding. "It's critical people understand their flood risk regardless of where they live, because storms are worsening, and they're here to stay," the organizations warn. A 2022 analysisof the National Oceanic and Atmospheric Administration's Storm Events Database by Pew Charitable Trusts found that flooding is a near-daily occurrence across the United States, with flooding reported almost as often inland as it was along the coast during the June-November hurricane season.

• Google Maps Platform adds air quality and pollen information to capture changing climate realities
• Youth advocates make their groundbreaking case in court for climate action
• How to advocate for climate change action
• Websites can choose to opt out of Google Bard and future AI models

Google's response is to leverage AI toolsto address the global climate crisis. 

Along with new Flood Hub regions, the company announced ongoing updates to a host of other AI-powered environmental resources, including Project Greenlight — a collaboration to optimize more fuel- and emissions-efficient traffic lights. Google also is adding on to its Search and Maps wildfire alerts and boundary tracking, intended to mitigate fire spread through machine learning-optimized firefighter training, fuel treatment planning, and wildfire suppression efforts. 

Google's Tree Canopy tool, part of the Environmental Insights Explorer platform, is expanding its data coverage to more than 2,000 cities around the world. Tree Canopy combines AI and aerial imagery to show where shaded areas are in the city, helping cities better understand where to plant more trees to reduce heat, the company explains. 

"AI is already playing an important role in addressing the climate crisis. As we advance our AI research, we'll do so boldly and responsibly to help further address the effects of climate change and help more people around the world."

最新评论