AI world model to simulate the Earth System
The WOW project will develop a new AI approach to take climate modeling to a new level, from simulating global climate change down to better estimates of highly local impacts on ecosystems and societies
Karlsruher Institut für Technologie (KIT)
Climate change is already reshaping global weather patterns and ecosystems around the world. In the long-term, its consequences could range from further substantial increases in the number of extreme weather events to even the collapse of entire ecosystems. “Numerical climate, weather, and environmental models already help us estimate these coupled changes across large spatial and temporal scales. However, modeling the entire Earth system at the required level of complexity has remained a formidable challenge for decades. AI has the potential to be a game-changing technology in modeling complex systems such as the Earth system” says tenure-track Professor Peer Nowack from KIT’s Institute of Theoretical Informatics who coordinates the project. “AI can emulate, i.e. mimic, the behavior of computationally expensive physics-based models. But the truly transformative step is that it can be trained or fine-tuned directly on observational data. In weather forecasting, this has led to AI models surpassing conventional models in key performance scores within just a few years. This technology offers opportunities for environmental modeling that go far beyond weather forecasting alone.”
In the WOW project, Nowack and seven other KIT researchers are now going one step further: They investigate how a number of these AI models for different processes in the Earth system can be coupled through their “latent spaces” – effectively abstractions of data within the AI models. This approach promises to be particularly effective to couple AI sub-models across scales of space and time. To this end, the team wants to pursue an AI approach from computer science, referred to as “world models”, but in this case applied to the actual physical world of the Earth system.
How Can the AI World Model be Shaped?
With WOW, the team will thus develop new methods that can link different AI models, following a modular approach that promises both high task-specific performance but also global consistency and efficiency. For the Earth system, these AI sub-models include emulators of global climate models, AI-based weather forecasting models as well as models that simulate highly local phenomena such as wildfires or flooding events. The aim is to link those initially separately trained and task-oriented AI sub-models to form a consistently coupled end-to-end process chain from global changes to local impacts. In order to enable these improvements, new advances - especially in AI methodology and in the relevant AI sub-models - will be developed as part of the project. Consequently, the team is a multidisciplinary mix of computer scientists, and environmental scientists.
With the world model, the researchers hope to better understand often highly nonlinear interactions between the atmosphere, water cycle, and the land surface. “We want to know how variations in one part of the Earth system affect others – for example, how droughts or changed cloud formation might feedback onto climate and vice versa,” says Professor Almut Arneth from the Institute of Meteorology and Climate Research – Atmospheric Environmental Research, i.e. KIT’s Campus Alpin located in Garmisch-Partenkirchen, who is also involved in the research project. “This could help us to reveal so far hidden connections in the climate system.”
Relevance to Other Fields of Knowledge
Even in the mid-term, the new AI world model might help to better assess risks, and to make well-founded decisions for climate adaptation and mitigation measures. “In the future, our methods might also be applied to other natural sciences where complex systems are modeled,” explains Dr. Markus Götz from KIT’s Scientific Computing Center. “If we learn to couple AI models efficiently, we can understand relations between them faster and more accurately. All told, this offers great opportunities for science.” The Carl Zeiss Foundation is funding the WOW project for five years with six million euros.
More information on the KIT Climate and Environment Center
More details on the KIT Information, Systems, Technologies Center
In close partnership with society, KIT develops solutions for urgent challenges – from climate change, energy transition and sustainable use of natural resources to artificial intelligence, sovereignty and an aging population. As The University in the Helmholtz Association, KIT unites scientific excellence from insight to application-driven research under one roof – and is thus in a unique position to drive this transformation. As a University of Excellence, KIT offers its more than 10,000 employees and 22,800 students outstanding opportunities to shape a sustainable and resilient future. KIT – Science for Impact.
The WOW project will develop a new AI approach to take climate modeling to a new level, from simulating global climate change down to better estimates of highly local impacts on ecosystems and societies
Karlsruher Institut für Technologie (KIT)
Climate change is already reshaping global weather patterns and ecosystems around the world. In the long-term, its consequences could range from further substantial increases in the number of extreme weather events to even the collapse of entire ecosystems. “Numerical climate, weather, and environmental models already help us estimate these coupled changes across large spatial and temporal scales. However, modeling the entire Earth system at the required level of complexity has remained a formidable challenge for decades. AI has the potential to be a game-changing technology in modeling complex systems such as the Earth system” says tenure-track Professor Peer Nowack from KIT’s Institute of Theoretical Informatics who coordinates the project. “AI can emulate, i.e. mimic, the behavior of computationally expensive physics-based models. But the truly transformative step is that it can be trained or fine-tuned directly on observational data. In weather forecasting, this has led to AI models surpassing conventional models in key performance scores within just a few years. This technology offers opportunities for environmental modeling that go far beyond weather forecasting alone.”
In the WOW project, Nowack and seven other KIT researchers are now going one step further: They investigate how a number of these AI models for different processes in the Earth system can be coupled through their “latent spaces” – effectively abstractions of data within the AI models. This approach promises to be particularly effective to couple AI sub-models across scales of space and time. To this end, the team wants to pursue an AI approach from computer science, referred to as “world models”, but in this case applied to the actual physical world of the Earth system.
How Can the AI World Model be Shaped?
With WOW, the team will thus develop new methods that can link different AI models, following a modular approach that promises both high task-specific performance but also global consistency and efficiency. For the Earth system, these AI sub-models include emulators of global climate models, AI-based weather forecasting models as well as models that simulate highly local phenomena such as wildfires or flooding events. The aim is to link those initially separately trained and task-oriented AI sub-models to form a consistently coupled end-to-end process chain from global changes to local impacts. In order to enable these improvements, new advances - especially in AI methodology and in the relevant AI sub-models - will be developed as part of the project. Consequently, the team is a multidisciplinary mix of computer scientists, and environmental scientists.
With the world model, the researchers hope to better understand often highly nonlinear interactions between the atmosphere, water cycle, and the land surface. “We want to know how variations in one part of the Earth system affect others – for example, how droughts or changed cloud formation might feedback onto climate and vice versa,” says Professor Almut Arneth from the Institute of Meteorology and Climate Research – Atmospheric Environmental Research, i.e. KIT’s Campus Alpin located in Garmisch-Partenkirchen, who is also involved in the research project. “This could help us to reveal so far hidden connections in the climate system.”
Relevance to Other Fields of Knowledge
Even in the mid-term, the new AI world model might help to better assess risks, and to make well-founded decisions for climate adaptation and mitigation measures. “In the future, our methods might also be applied to other natural sciences where complex systems are modeled,” explains Dr. Markus Götz from KIT’s Scientific Computing Center. “If we learn to couple AI models efficiently, we can understand relations between them faster and more accurately. All told, this offers great opportunities for science.” The Carl Zeiss Foundation is funding the WOW project for five years with six million euros.
More information on the KIT Climate and Environment Center
More details on the KIT Information, Systems, Technologies Center
In close partnership with society, KIT develops solutions for urgent challenges – from climate change, energy transition and sustainable use of natural resources to artificial intelligence, sovereignty and an aging population. As The University in the Helmholtz Association, KIT unites scientific excellence from insight to application-driven research under one roof – and is thus in a unique position to drive this transformation. As a University of Excellence, KIT offers its more than 10,000 employees and 22,800 students outstanding opportunities to shape a sustainable and resilient future. KIT – Science for Impact.
Texas A&M researchers use AI to identify genetic ‘time capsule’ that distinguishes species
A new study, published in Nature, reveals a conserved genetic region that preserves species history through waves of gene flow and may be crucial to the development of some common X-linked diseases.
Texas A&M University
image:
Texas A&M University researchers Dr. Bill Murphy and Dr. Nicole Foley led an AI-driven genome study that identified a genetic region conserved across mammals — a “time capsule” that helps preserve species identity and may inform human reproductive health.
view moreCredit: Texas A&M University
In a groundbreaking study, scientists from the Texas A&M College of Veterinary Medicine and Biomedical Sciences (VMBS) have utilized cutting-edge artificial intelligence methods to identify a region of the X chromosome that has maintained the distinctiveness of mammal species for millions of years.
Their findings shed new light on how species maintain their genetic identity, even when hybridization acts to homogenize their gene pools.
“We know that species like big cats; wolves, dogs and coyotes; and even whales and dolphins have interbred to create hybrid offspring. What has been less clear has been why, despite all this interbreeding, these animals have remained separate species,” said Dr. Nicole Foley, a research assistant professor in the VMBS’ Department of Veterinary Integrative Biosciences and the study’s lead author.
The mixing of DNA between species is common across the Tree of Life and often helps species survive as they explore new environments and encounter new pathogens or environmental conditions.
A major obstacle has been the lack of detailed genetic recombination maps, which are crucial for understanding how the shuffling of genes during reproduction, together with natural selection, influences the emergence of reproductive barriers in nature. This genetic swapping makes it more challenging for scientists to accurately map out species relationships, which are crucial for understanding the evolutionary history of animals.
Now, using AI-driven genome analysis, researchers can unlock this hidden blueprint of mammalian evolution.
A time capsule in the genome
A major discovery from these studies is the identification of a massive region on the X chromosome that is shared across most mammalian species for more than 100 million years.
Dubbed the X-linked recombination desert (XLRD), this region spans nearly 30% of the X chromosome. It serves as a powerful reproductive barrier and plays a crucial role in preserving the true evolutionary relationships among species, even when widespread genetic exchange clouds the rest of the genome.
“Remarkably, the XLRD appears to be a recurrent and ancient feature in mammals, functioning almost like a genomic ‘time capsule’ that records deep evolutionary history,” Foley said.
“We were unable to see this before because we never had this diversity of recombination maps,” she said. “When we lined up all of the X chromosomes for those 22 species and we looked at the recombination map, it was pretty much the same map — it dipped in the exact same place, so we knew there was something functionally important going on in this part of the chromosome.”
“We had some evidence from previous studies based on a small handful of species that the XLRD exists, but we were very surprised to discover that this region was so conserved and so ancient,” said Dr. Bill Murphy, a distinguished professor in the VMBS and director of the Texas A&M Center for Comparative Genomics.
This discovery was especially exciting because the XLRD appears to play a key role in speciation — the process by which one species evolves into distinct new species through the development of reproductive barriers.
The XLRD’s reproductive role
The researchers also discovered that the XLRD region is notably enriched with genes related to male and female reproduction and sex chromosome silencing; this suggest that genetic switches relevant to X chromosome regulation in both sexes, which are embedded within and around the XLRD, may play a larger role in infertility as well as in human conditions like polycystic ovarian syndrome, an endocrine disorder that has been linked to reproductive and metabolic issues.
“This is one of the more novel findings because it has been thought that reproductive barriers arise rapidly and from unique genetic sources across different groups of species. Our results suggest this is not the case,” Murphy said. “For all the reasons, it looks like the XLRD is a key region associated with reproductive dysfunction in hybrids and reproductive isolation in nature.”
These discoveries open new avenues for understanding problems — and finding solutions — related to human reproduction and fertility.
By Texas A&M University College of Veterinary Medicine and Biomedical Sciences
Journal
Nature
Method of Research
Data/statistical analysis
Subject of Research
Animals
Article Title
An ancient recombination desert is a speciation supergene in placental mammals
Article Publication Date
12-Nov-2025
No comments:
Post a Comment