Nerve interfaces and infrared fossil finding

The advent of machine learning and AI is reaching back 400 million years to re-evaluate our fossil record. In the past, we were resigned to cracking open a fossil and looking at it under a microscope. But since then, scientists have realised that also present in the fossil are some of the original chemicals that were in the entity when it was alive millions of years ago.A technique called ‘infrared spectroscopy’ can use infrared light to see and quantify these substances. So researchers have now gone a step further and developed a system that can use the relative compositions of these chemicals to confirm what the biological sample might have been. The machine learning algorithm had a test run on the Rhynie Chert, an almost perfectly preserved set of fossils from Scotland, and identified them with remarkable accuracy.So what are the advantages of using machine learning , and where next for the project? Will Tingle spoke to the University of Edinburgh’s Corentin Loron…

Corentin - Using machine learning, computer algorithm statistics, all those kind of tools, you are able to go behind what you can see with your own eyes and access very tiny details that you would've missed if you were just qualitatively analyzing your data. I mean, infrared spectroscopy is not new. What is new is to use machine learning with the data from a infrared spectroscopy. But what is very interesting with this particular technique compared to all the other types that could be used is we have only a bare minimum of preparation for the sample. We're going to slice the rock into sections and those are usually made to look at the fossils under the microscope and there are thousands of those in museums. So now we can take those out of museums and just apply the technique directly on those. We're not going to do any new destruction. So in that way, and this is exactly what we've done in this study, we were able to go in to this precious collection from the National Museum Scotland and look at them without destroying all the rocks. And this is a precious collection. You don't want to destroy those to do studies.

Will - Now that you've had a test run with these well preserved, well-documented fossils and you've seen that it works, is the plan to go out and find some more ambiguous samples?

Corentin - Obviously, the idea behind looking at this very famous site was that we can recognise with our eyes what the fossils are. And so when we look at the signature, we can do a positive matching. You have a positive control over your data. So now we know machine learning approaches worked on fossils because we can actually see that it was a match between what the fossil is and what the signature was. So now we can go back in time in fossil assemblages that are 1 billion - 1 and a half billion years old, which contain a lot of fossils, but with very, very simple shapes, very, very simple forms for which we have no idea what they might have been. They might have been algae, they might have been fungi, they might have been protists, some sort of microorganism. And now we have a new type of approach to look at what their affinities, biological affinities, would be.

Will - So this might give us an idea of the biological makeup of billion year old organisms?

Corentin - Exactly, exactly, yes.

Will - What does this method reveal about the molecular preservation of samples? Because with a 400 million year old sample, I'd personally assume there's not much left?

Corentin - So this site is known for its incredible preservation. It didn't undergo a lot of geological transformations. That's why we can see so many fossils with our eyes on a microscope. But what it revealed on the molecular level is that not only the preservation, the morphological preservation, is amazing, but the molecular preservation is also amazing. And for instance, we were able to see very tiny details of what those fossils were composed of, what type of sugars were composed, what types of fossils, for example.

Will - Does this allow us to look at harder to reach samples? If we find a perfectly preserved 500 million year old sample, that's great, but that's also very rare. Could this machine learning help us identify more partial fossil remains?

Corentin - I would say, theoretically, yes. Now it will depend of course on what kind of condition your fossils were preserved. Because if they were preserved in a very, very harsh environment, if you undergo very high temperatures, then maybe you will see that a fossil was there. But the molecular signature will be not very good. But we're lucky because we have a lot of very ancient fossil sites where the fossil are very well preserved. Some of them in the UK, the billion years old Torridon group in the North of Scotland, for instance. So definitely they're a good target for this kind of technique.

Will - Is there potential to shake up what we already know? You might go back to something that everyone has assumed is one thing and your method says otherwise.

Corentin - Exactly. I think this is the whole point of this whole approach, and we do it in a certain way in this paper when we looked at those curious organisms that were assessed to be part of plants, maybe they were part of a fungi, maybe they were bacteria. And with our study, we were able to show that actually they have a molecular composition that is closer to plants than to fungi. So we definitely could go to those cryptic fossils that we have and try to know where they could fit in the tree of life.

In the battle to preserve biodiversity, humans almost inevitably have a hand to play in habitat loss and environmental destruction. And a study this week has found that 80% of the world’s most important sites for biodiversity on land currently already contain human developments. Here with us to explain the implications is Ash Simkins from the University of Cambridge.

Ash - Yeah, I think it's a good question. Biodiversity seems quite a complicated topic. What does it mean. Does it mean the number of species? Does it mean functions or services? Do they provide pollination? So what we did was we looked at KBAs, which are key biodiversity areas, which are aiming to capture different elements of biodiversity, whether it be things like threatened biodiversity, so is a species threatened with extinction in the wild, or are species found only in small parts of the world? Or it could be similar for ecosystems or key ecological processes or biological processes. So things you would call wilderness areas or key life stages, or migratory sites for birds as they're passing over, for example. So this is an approach to try and combine a lot of different measures of biodiversity to create a systematic network and it's the most comprehensive network we have to date.

James - And you were looking particularly at the impacts of human infrastructure on these particularly important areas, is that right?

灰——所以我们re using data from WWF sites, which is a geospatial tool that they compile to look at near real time changes in conservation, things of conservation values. It could be species, habitats or ranges. It could be these protected areas or these key biodiversity areas. So they have a lot of data compiled from various places on things like road networks across the world, oil and gas, extraction sites, pipelines and then plans for future development, particularly around oil and gas and mining. So we obviously leveraged this stuff for the first time because, in most sites, unfortunately, because a lot of them are hard to reach and there's over 15,000 sites on land across the world. So it's hard to monitor all of them regularly. But this satellite world we're in now enables us to get information in much more real time.

James - And what were the main conclusions you drew about how human infrastructure is having an impact on these biodiverse, important areas?

Ash - I think it's important to say what we looked at was where infrastructure is in relation to these areas of biodiversity. So we can't necessarily get at impact. We were finding that around 80% of these 15,000 sites or so have at least some sort of human development in them, and given what we know from the literature around things like how roads impact biodiversity, or how things like wind turbines, things like that, how they might impact biodiversity, it's likely that them being there is an indicator that there might be a threat happening. So it's the first step in that. But we are calling on people to do more research to fully understand the impacts.

James - Could you speculate as to whether human infrastructure is always going to have a negative impact on the wildlife in these areas? Or could there be examples where some species will benefit?

Ash - Yeah, I think it depends how it's done. Most species are not likely to benefit overall. So there might be some species that are more generalist, which means that they can exploit a greater variety of habitats or environments. So things you might see typically in gardens or urban areas may be more adapted to living alongside humans, for example. So things like pigeons or grey squirrels you tend to see much more around in urban areas. Whereas a lot of species tend to be more sensitive, especially ones that are more threatened. So it depends what species you're concerned with as to how vulnerable it would be. And it depends on the type of infrastructure that you're impacting. If it's a road, maybe if something's flying at high enough altitude, it won't be in the line of traffic. Likewise, if birds are flying at a lower level or if something can't fly, it will be at risk of being hit by cars. So it sort of depends on the context about how much it'll impact it, but there are things we can do to try and minimise that impact.

詹姆斯-确定。我们会到,but a lot of the things you mentioned earlier, the infrastructure projects, strike me as ones that, as we transition to a more green economy, more sustainable modes of getting our energy, are only going to become more prevalent. Are you worried therefore about how this is going to impact on the biodiversity of these areas?

Ash - Yeah, I think it is a cause for concern. As I say, I think there are things we can do in terms of more smart planning. There's this thing called the mitigation hierarchy, which suggests you want to avoid these areas. So these things like key biodiversity areas, using things like species that we know are particularly vulnerable to things like roads for example. You might say, okay, we should avoid roads going through those networks and try and maybe route the roads around them. Whatever kind of infrastructure it is, whether it's wind turbines, maybe put them in area of high wind where there's a low chance of birds flying through that area. So there's things you can do in terms of placement of these infrastructures to try and minimise their impact by ideally avoiding or putting them as much out of harm's way as you can get them, or even putting mitigation measures in to adapt the environment such that species are less likely to encounter direct impacts from this infrastructure.

James - And are there any more ways we can reconcile this need for more infrastructure against their effects on biodiversity?

Ash - You can look at restoring an area after impacts that you've had or restoring completely different areas to compensate called offsetting, which is an approach and sometimes is necessary because the infrastructure has to go in a certain area and it's unavoidable. But I think ideally we need to be first looking at the planning stage and looking at how we can ideally avoid those areas most at risk.