Tyler O'Neal, Staff Editor GOVERNMENT

Pivotal technique harnesses cutting-edge AI capabilities to model, map the natural environment

UK scientists have developed a pioneering new technique that harnesses the cutting-edge capabilities of AI to model and map the natural environment in intricate detail. 

A team of experts, including Charlie Kirkwood from the University of Exeter, has created a sophisticated new approach to modeling the Earth’s natural features in greater detail and accuracy. 

The new technique can recognize intricate features and aspects of the terrain far beyond the capabilities of more traditional methods and use these to generate enhanced-quality environmental maps. 

Crucially, the new system could also pave the way to unlocking discoveries of the relationships within the natural environment, that may help tackle some of the greater climate and environment issues of the 21st century. 

The study is published in the academic journal Mathematical Geosciences, as part of a special issue on geostatistics and machine learning. 

Modeling and mapping the environment is a lengthy, time-consuming, and expensive process. Cost limits the number of observations that can be obtained, which means that creating comprehensive spatially-continuous maps depends upon filling in the gaps between these observations.  

Scientists can use a range of information sources to help fill in these observation gaps, such as terrain elevation data and satellite imagery. However, conventional modeling methods rely on users to manually engineer predictive features from these datasets – for example generating slope angles and curvatures from terrain elevation data in the hope that these can help explain the spatial distribution of the variable being mapped. 

However, scientists believe there are likely to be many more nuanced relationships at play within the natural environment that models based on traditional manual feature-engineering approaches may simply miss. 

The pioneering new AI approach, developed in the study, poses environmental information extraction as an optimization problem. Doing so allows it to automatically recognize and make use of relationships that may otherwise go unnoticed and unutilized by humans using more traditional modeling methods.  

In addition to improving map quality, this also unlocks the potential for the discovery of new relationships in the natural environment by AI, while simultaneously eliminating huge amounts of trial-and-error experimentation in the modeling process. 

Charlie Kirkwood, a postgraduate student at the University of Exeter said: “To be useful for decision making, we need our models to provide answers that are as specific as possible while also being trustworthy – and that means creating accurate measures of the uncertainty associated with our estimates, which in this case are predictions at unmeasured locations.” 

“Our AI approach is set within a Bayesian statistical framework which allows us to quantify these uncertainties and provide a range of uncertainty measures, including credible intervals, exceedance probabilities, and other more bespoke products that will feed directly into decision-making processes. Crucially, all this is provided whilst harnessing any available information more effectively than traditional approaches allow – which you can see coming through in the detail of the map“ 

The new approach was demonstrated using stream sediment calcium concentration observations from the British Geological Survey’s Geochemical Baseline Survey of the Environment (G-BASE) project.  

The distribution of calcium in the environment, which has standalone importance for its impact on soil fertility, is controlled primarily by geology – with different rock types containing different proportions of calcium – but also by hydrological processes at the surface.  

Calcium, therefore, provides a challenging use case for the AI approach, which must learn to recognize and utilize features relating to both bedrock geology (e.g. differing terrain textures, breaks of slope) and surface hydrology (e.g. drainage, river channels). 

The method, the scientists say, has produced a spectacularly detailed and accurate map which, despite depicting just one element – calcium, reveals the geology of Britain in arguably a new level of detail thanks to the information-extracting power of the new AI approach. The team believes that by combining the research skills, expertise, and data resources of its partners - the University of Exeter, Met Office, and British Geological Survey - this work presents a new dawn for environmental mapping practices in the age of AI.

 Professor Gavin Shaddick, from the University of Exeter, added “This is a fantastic example of Environmental Intelligence, the use of AI to help solve challenges in environmental science. This work is an exemplar in integrating technical knowledge of AI and machine learning with expertise in geosciences to produce a new methodology that directly addresses crucial questions in mapping environmental information. The resulting methodological advances could be used to produce detailed maps of a wide variety of environmental hazards and have the potential to provide a rich source of information for both scientists and decision-makers.” 

Garry Baker, Interim Chief Digital Officer, British Geological Survey added: “This paper is an excellent demonstration of how environmental information such as the BGS geochemical database can be re-assessed via new approaches (AI spatial interpolation). It exemplifies the benefits of ongoing environmental research and how this can draw upon the extensive datasets available to everyone through the National Geoscience Data Centre and wider NERC, and UKRI data repositories.” 

Dr. Kirstine Dale, the Met Office’s Principal Fellow for Data Science and Co-Director for Joint Centre for Excellence in Environmental Intelligence commented on the value of this work: “This is an important example of how data science has the potential to transform our understanding of the natural world. Critically, it highlights what can be achieved by working across disciplines, in this case bringing together mathematicians, weather specialists and computer scientists enrich our knowledge of the natural world in a way that no single discipline can.” 

Duke, Birmingham’s research into sugar-based plastics shows the shape of things to come

Tyler O'Neal, Staff Editor GOVERNMENT

Researchers at the University of Birmingham, U.K., and Duke University, U.S., have described the exceptional strength and toughness of novel polymers made from sugars, and the chemistry underpinning their characteristics, in a study published in Angew Chemie.

The study examined two polymers based on isosorbide and isomannide that were produced by a recently disclosed method that uses sugars as a starting point for synthesis. Both polymers have superior properties to conventional thermoplastic elastomers, and in addition, are degradable and mechanically recyclable.

In a key finding, the researchers discovered that the polymer made from isosorbide displayed superior elastic recovery and toughness which was shown to be a result of the stereochemistry of the sugar groups in the materials.

Using supercomputer simulations and other experimental techniques, the researchers showed that the difference in elastic recovery results from the way that the sugar stereochemistry directs the network of hydrogen bonds between and within the long-chain molecules.

The researchers concluded that both polymers have high optical clarity, exceptional mechanical strength, and extensibility, but the isosorbide-based polymer has superior toughness, due to its higher elasticity.

Professor Andrew Dove, from Birmingham’s School of Chemistry, commented, who led the research team, commented: “The long-term impacts of modern polymers on the environment are a significant concern. Isosorbide is a renewable feedstock alternative to petroleum derivatives for commercial polymer production. It is derived from plants, and, as one of the top 20 biomass sourced molecules, is available at a scale that is consistent with commercial production of bioplastics.”

Duke University professor Dr. Matthew Becker said: “Most bio-sourced plastics have lacked the mechanical properties needed to compete in commercial applications and lose nearly all of their mechanical properties when reprocessed. The materials outlined in this paper change that paradigm”.

A joint patent application has been filed by the University of Birmingham Enterprise and Duke University, covering both the polymers and the method of making them. The researchers are now looking for industrial partners who are interested in licensing the technology.

Ebrahimi simulates the dispersal strategies that drive marine microbial diversity

Tyler O'Neal, Staff Editor GOVERNMENT

The study suggests ecological trade-offs between growth and death allow marine microbes with different dispersal strategies to coexist on small particles in the ocean Image credit: Anastasia Taioglou (CC0)

Trade-offs between the benefit of colonizing new particles and the risk of being wiped out by predators allow diverse populations of marine microbes to exist together shows a study published today in eLife.

The findings help explain how a vast array of diverse bacteria and microbes coexist on floating particle rafts in oceans.

Microbial foraging in patchy environments, where resources are fragmented into particles, plays a key role in natural environments. In oceans and freshwater systems, bacteria and microbes can interact with particle surfaces in different ways: some only colonize them for short periods, while others form long-lived, stable colonies.

Scientists have long puzzled over the greater-than-expected diversity of microscopic creatures in oceans, a phenomenon called the 'plankton paradox'. While researchers have begun to understand the factors that support so many different types of plankton, many questions remain about the more plentiful ocean microbes that live on floating particles. 

"We wanted to study the role that dispersal strategies play in the successful coexistence of different microbes living on the same set of particles," says co-first author Ali Ebrahimi, who completed the study while he was a postdoctoral fellow at the Ralph M. Parsons Laboratory for Environmental Science and Engineering, Massachusetts Institute of Technology (MIT), Cambridge, US.

Ebrahimi and the team used mathematical modeling and computer simulations to test how different dispersal strategies may help marine microbes exist together in this way. They found that differently navigating the trade-offs between growth and survival can allow microbes to thrive together.

Their model showed that organisms that stay put on a single particle for longer have more opportunities to multiply. However, they face a higher risk of being wiped out by a virus or other predator capable of engulfing whole particles. On the other hand, microbes that more frequently hop between particles have less opportunity to multiply, but also have a lower risk of facing a mass mortality event. The success of one strategy over another may depend on differing environmental conditions.

"When the particle supply is high, microbes that hop rapidly between them will have a greater chance of survival," explains co-first author Akshit Goyal, Physics of Living Systems Fellow at the MIT Department of Physics. "But when particles are harder to come by, the bacteria that stay put will have an advantage."

Additionally, the team found that coexistence can remain stable in the face of changing environmental conditions, such as algal blooms of particles, favoring growth, and changing numbers of predators, favoring mortality. Together, these differing factors significantly increase the likelihood that populations with diverse dispersal strategies can live together.

"Our work focused on the link between dispersal and mortality in the ocean, but there’s plenty more going on in these environments," Goyal concludes. "Future research could provide important new insights on how environmental changes might impact these minuscule communities and, in turn, their wider marine ecosystem."

Co-first authors Ebrahimi and Goyal worked on this study alongside senior author Otto Cordero, Associate Professor at the MIT Department of Civil and Environmental Engineering.