Protecting nature can safeguard cities from floods
image:
Recent photo showing Montreal's tiny islands almost flooded by the Saint-Lawrence (or the Prairies river, its side-arm) because of heavy rainfall
view moreCredit: Ágnes Vári
A new UBC-led study shows that safeguarding key natural ecosystems across Canada can help reduce flood risks for more than half of the country’s urban areas at high risk for flooding.
The research reveals that preserving the most important five per cent of watersheds—about 201,000 square kilometres or two per cent of Canada’s land—can significantly reduce rainwater runoff, protect homes and livelihoods, and safeguard croplands.
“This is the first national study to assess the role of Canadian ecosystems in flood prevention and to identify where conservation could have the greatest impact,” said Dr. Matthew Mitchell, an assistant professor in the faculty of forestry and the faculty of land and food systems.
Nature: the flood shield
Upstream watersheds near cities such as Vancouver and Toronto play an important role in protecting 3.7 million people living in floodplains and another 20.1 million nearby—more than half of Canada’s population.
Using global data, Dr. Mitchell and his colleagues analyzed how land types like forests, wetlands and riparian zones absorb water and reduce runoff.
These natural systems prevent downstream flooding, improve water quality and support wildlife, while reducing reliance on costly infrastructure like dams.
“Nature-based solutions are highly effective for managing flood risks, and this study shows exactly where conservation can make the biggest impact,” said Dr. Mitchell.
Conservation priorities across Canada
The study identified key ecosystems in B.C. that are critical for flood prevention:
- Alpine and subalpine ecosystems in the Coast and Columbia Mountains, which help regulate water flow and prevent downstream flooding.
- Wetlands in the Fraser River Delta, including Burns Bog and other peatlands, which are crucial for flood protection in the Lower Mainland.
- Forests and wetlands in the Okanagan and Similkameen valleys, which protect key agricultural areas and growing population centres.
Beyond B.C., the researchers recommend the following conservation priorities:
- Prairie Provinces (Alberta, Saskatchewan, Manitoba): Protect grasslands and wetlands in key river watersheds, such as the Red and Saskatchewan Rivers.
- Northern Regions: Prioritize conservation in northern wetlands and other ecosystems, including those in the Yukon and Northwest Territories.
- Southern Ontario: Safeguard wetlands around the Great Lakes and major rivers to reduce flood risks in cities like Toronto, Ottawa, and Hamilton.
Canada has committed to protect 30 per cent of its lands by 2030, yet only eight per cent of the most flood-critical ecosystems are currently protected. The researchers call for stronger conservation policies and funding to prioritize these high-impact areas.
“This research makes it clear that conserving nature isn’t just about biodiversity—it’s also about protecting communities and making cities more resilient to climate change,” said Dr. Mitchell.
The study, published recently in Ecosystem Services, offers a global roadmap for integrating nature-based solutions into urban planning and flood management.
Journal
Ecosystem Services
Method of Research
Data/statistical analysis
Subject of Research
Not applicable
Article Title
Flood prevention benefits provided by Canadian natural ecosystems
Article Publication Date
1-Dec-2024
New AI tool generates realistic satellite images of future flooding
The method could help communities visualize and prepare for approaching storms
Visualizing the potential impacts of a hurricane on people’s homes before it hits can help residents prepare and decide whether to evacuate.
MIT scientists have developed a method that generates satellite imagery from the future to depict how a region would look after a potential flooding event. The method combines a generative artificial intelligence model with a physics-based flood model to create realistic, birds-eye-view images of a region, showing where flooding is likely to occur given the strength of an oncoming storm.
As a test case, the team applied the method to Houston and generated satellite images depicting what certain locations around the city would look like after a storm comparable to Hurricane Harvey, which hit the region in 2017. The team compared these generated images with actual satellite images taken of the same regions after Harvey hit. They also compared AI-generated images that did not include a physics-based flood model.
The team’s physics-reinforced method generated satellite images of future flooding that were more realistic and accurate. The AI-only method, in contrast, generated images of flooding in places where flooding is not physically possible.
The team’s method is a proof-of-concept, meant to demonstrate a case in which generative AI models can generate realistic, trustworthy content when paired with a physics-based model. In order to apply the method to other regions to depict flooding from future storms, it will need to be trained on many more satellite images to learn how flooding would look in other regions.
“The idea is: One day, we could use this before a hurricane, where it provides an additional visualization layer for the public,” says Björn Lütjens, a postdoc in MIT’s Department of Earth, Atmospheric and Planetary Sciences, who led the research while he was a doctoral student in MIT’s Department of Aeronautics and Astronautics (AeroAstro). “One of the biggest challenges is encouraging people to evacuate when they are at risk. Maybe this could be another visualization to help increase that readiness.”
To illustrate the potential of the new method, which they have dubbed the “Earth Intelligence Engine,” the team has made it available as an online resource for others to try.
The researchers report their results today in the journal IEEE Transactions on Geoscience and Remote Sensing. The study’s MIT co-authors include Brandon Leschchinskiy; Aruna Sankaranarayanan; and Dava Newman, professor of AeroAstro and director of the MIT Media Lab; along with collaborators from multiple institutions.
Generative adversarial images
The new study is an extension of the team’s efforts to apply generative AI tools to visualize future climate scenarios.
“Providing a hyper-local perspective of climate seems to be the most effective way to communicate our scientific results,” says Newman, the study’s senior author. “People relate to their own zip code, their local environment where their family and friends live. Providing local climate simulations becomes intuitive, personal, and relatable.”
For this study, the authors use a conditional generative adversarial network, or GAN, a type of machine learning method that can generate realistic images using two competing, or “adversarial,” neural networks. The first “generator” network is trained on pairs of real data, such as satellite images before and after a hurricane. The second “discriminator” network is then trained to distinguish between the real satellite imagery and the one synthesized by the first network.
Each network automatically improves its performance based on feedback from the other network. The idea, then, is that such an adversarial push and pull should ultimately produce synthetic images that are indistinguishable from the real thing. Nevertheless, GANs can still produce “hallucinations,” or factually incorrect features in an otherwise realistic image that shouldn’t be there.
“Hallucinations can mislead viewers,” says Lütjens, who began to wonder whether such hallucinations could be avoided, such that generative AI tools can be trusted to help inform people, particularly in risk-sensitive scenarios. “We were thinking: How can we use these generative AI models in a climate-impact setting, where having trusted data sources is so important?”
Flood hallucinations
In their new work, the researchers considered a risk-sensitive scenario in which generative AI is tasked with creating satellite images of future flooding that could be trustworthy enough to inform decisions of how to prepare and potentially evacuate people out of harm’s way.
Typically, policymakers can get an idea of where flooding might occur based on visualizations in the form of color-coded maps. These maps are the final product of a pipeline of physical models that usually begins with a hurricane track model, which then feeds into a wind model that simulates the pattern and strength of winds over a local region. This is combined with a flood or storm surge model that forecasts how wind might push any nearby body of water onto land. A hydraulic model then maps out where flooding will occur based on the local flood infrastructure and generates a visual, color-coded map of flood elevations over a particular region.
“The question is: Can visualizations of satellite imagery add another level to this, that is a bit more tangible and emotionally engaging than a color-coded map of reds, yellows, and blues, while still being trustworthy?” Lütjens says.
The team first tested how generative AI alone would produce satellite images of future flooding. They trained a GAN on actual satellite images taken by satellites as they passed over Houston before and after Hurricane Harvey. When they tasked the generator to produce new flood images of the same regions, they found that the images resembled typical satellite imagery, but a closer look revealed hallucinations in some images, in the form of floods where flooding should not be possible (for instance, in locations at higher elevation).
To reduce hallucinations and increase the trustworthiness of the AI-generated images, the team paired the GAN with a physics-based flood model that incorporates real, physical parameters and phenomena, such as an approaching hurricane’s trajectory, storm surge, and flood patterns. With this physics-reinforced method, the team generated satellite images around Houston that depict the same flood extent, pixel by pixel, as forecasted by the flood model.
“We show a tangible way to combine machine learning with physics for a use case that’s risk-sensitive, which requires us to analyze the complexity of Earth’s systems and project future actions and possible scenarios to keep people out of harm’s way,” Newman says. “We can’t wait to get our generative AI tools into the hands of decision-makers at the local community level, which could make a significant difference and perhaps save lives.”
The research was supported, in part, by the MIT Portugal Program, the DAF-MIT Artificial Intelligence Accelerator, NASA, and Google Cloud.
###
Written by Jennifer Chu, MIT News
Journal
IEEE Transactions on Geoscience and Remote Sensing
Article Title
“Generating Physically-Consistent Satellite Imagery for Climate Visualizations”
New model combines data to improve typhoon forecasting
image:
HAIYAN-I, about to take off for an observation mission
view moreCredit: Liu Zhenyu
Over the past few decades, because of the frequent number of typhoons making landfall in South China, the Guangzhou Institute of Tropical and Marine Meteorology has developed a model, called CMA-TRAMS, to provide operational forecasting products for typhoons.
Years of research carried out by scientists has led to the point where we know that assimilating unmanned aerial vehicle (UAV) and atmospheric sounding data can enhance the typhoon forecasting capabilities of numerical models. However, in practical operations, the scarcity of such data over ocean regions restricts further improvement in operational typhoon forecasting.
Based on these considerations, China’s National Meteorological Observation Centre has promoted a new generation of operational sounding systems called “Beidou”. Compared to traditional sounding balloons, the Beidou system provides more segments of high-level observation data. Combined with the data from the new-generation HAIYAN-I UAV, the data sources over the ocean during landfalling typhoons have been greatly enriched.
On this basis, the CMA-TRAMS team conducted an assimilation forecast experiment with observations that targeted Typhoon Haikui, which occurred in 2023. The results showed that, with the new assimilated data, the forecast landing point of Haiku was significantly closer to reality, which is published in Atmospheric and Oceanic Science Letters recently.
"This experiment marks the first attempt to assimilate both Beidou sounding data and UAV data into an operational forecast system for South China, and the results suggest it represents a good start," says Dr. Sheng Hu, one of the corresponding authors of the study.
The other corresponding author, Dr Xuefen Zhang, adds "Promoting the integration of new observation data into operational forecasting models is crucial. We hope to continue conducting such operational assimilation experiments to ultimately serve frontline operational forecasts."
In the future, the CMA-TRAMS team plan to conduct further targeted observations of typhoons in the South China Sea and increase the application of observational data in the assimilation process. Ultimately, they hope to provide higher-quality typhoon forecasts for the South China region.
Journal
Atmospheric and Oceanic Science Letters
No comments:
Post a Comment