New aI Tool Generates Realistic Satellite Pictures Of Future Flooding

Visualizing the prospective impacts of a cyclone on people’s homes before it hits can help citizens prepare and choose whether to leave.

MIT scientists have established an approach that produces satellite images from the future to illustrate how an area would look after a possible flooding event. The method combines a generative expert system design with a physics-based flood design to produce sensible, birds-eye-view images of an area, revealing where flooding is most likely to occur provided the strength of an approaching storm.

As a test case, the team used the approach to Houston and generated satellite images depicting what specific places around the city would look like after a storm similar to Hurricane Harvey, which hit the region in 2017. The team compared these produced images with actual satellite images taken of the very same regions after Harvey struck. They also compared AI-generated images that did not consist of a physics-based flood model.

The team’s physics-reinforced approach produced satellite pictures of future flooding that were more sensible and precise. The AI-only approach, in contrast, produced images of flooding in locations where flooding is not physically possible.

The team’s method is a proof-of-concept, meant to demonstrate a case in which generative AI designs can produce sensible, trustworthy content when coupled with a physics-based design. In order to use the approach to other regions to portray flooding from future storms, it will require to be trained on much more satellite images to learn how flooding would search in other areas.

“The idea is: One day, we could utilize this before a typhoon, where it supplies an extra visualization layer for the general public,” says Björn Lütjens, a postdoc in MIT’s Department of Earth, Atmospheric and Planetary Sciences, who led the research study while he was a doctoral trainee in MIT’s Department of Aeronautics and Astronautics (AeroAstro). “Among the most significant obstacles is motivating people to leave when they are at danger. Maybe this might be another visualization to help increase that readiness.”

To highlight the capacity of the brand-new approach, which they have dubbed the “Earth Intelligence Engine,” the team has made it offered as an online resource for others to try.

The scientists report their results today in the journal IEEE Transactions on Geoscience and Remote Sensing. The study’s MIT co-authors include Brandon Leshchinskiy; Aruna Sankaranarayanan; and Dava Newman, professor of AeroAstro and director of the MIT Media Lab; along with collaborators from numerous institutions.

Generative adversarial images

The brand-new study is an extension of the team’s efforts to apply generative AI tools to visualize future climate situations.

“Providing a hyper-local point of view of climate seems to be the most efficient method to interact our clinical outcomes,” says Newman, the research study’s senior author. “People connect to their own zip code, their local environment where their friends and family live. Providing local climate simulations ends up being intuitive, individual, and relatable.”

For this research study, the authors use a conditional generative adversarial network, or GAN, a type of artificial intelligence method that can generate sensible images using 2 completing, or “adversarial,” neural networks. The very first “generator” network is trained on sets of real information, such as satellite images before and after a hurricane. The 2nd “discriminator” network is then trained to differentiate in between the real satellite images and the one synthesized by the first network.

Each network immediately enhances its efficiency based upon feedback from the other network. The concept, then, is that such an adversarial push and pull need to ultimately produce artificial images that are equivalent from the genuine thing. Nevertheless, GANs can still produce “hallucinations,” or factually inaccurate features in an otherwise reasonable image that should not exist.

“Hallucinations can misguide viewers,” states Lütjens, who began to wonder whether such hallucinations could be avoided, such that generative AI tools can be relied on to help inform people, particularly in risk-sensitive scenarios. “We were believing: How can we utilize these generative AI models in a climate-impact setting, where having relied on information sources is so essential?”

Flood hallucinations

In their brand-new work, the researchers considered a risk-sensitive circumstance in which generative AI is charged with creating satellite pictures of future flooding that might be credible enough to inform choices of how to prepare and potentially leave individuals out of harm’s way.

Typically, policymakers can get an idea of where flooding might happen based on visualizations in the type of color-coded maps. These maps are the end product of a pipeline of physical designs that typically starts with a typhoon track model, which then feeds into a wind design that simulates the pattern and strength of winds over a local region. This is combined with a flood or storm rise design that anticipates how wind might push any close-by body of water onto land. A hydraulic model then draws up where flooding will take place based upon the regional flood facilities and produces a visual, color-coded map of flood elevations over a particular area.

“The question is: Can visualizations of satellite images include another level to this, that is a bit more concrete and mentally engaging than a color-coded map of reds, yellows, and blues, while still being trustworthy?” Lütjens states.

The group first tested how generative AI alone would produce satellite pictures of future flooding. They trained a GAN on real 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 exact same regions, they found that the normal satellite images, however a closer look revealed hallucinations in some images, in the kind of floods where flooding must not be possible (for example, in locations at higher elevation).

To minimize hallucinations and increase the trustworthiness of the AI-generated images, the group paired the GAN with a physics-based flood model that integrates real, physical specifications and phenomena, such as an approaching hurricane’s trajectory, storm surge, and flood patterns. With this physics-reinforced method, the group generated satellite images around Houston that portray the exact same flood level, pixel by pixel, as anticipated by the flood model.