00:00.00 archpodnet Welcome back to episode two zero seven of the archeotech podcast and we are talking to Marcus here about this paper that is linked in the show notes. So go check that out I won't read the whole thing out out again. But we're talking about micro debotage machine learning and figuring all this out. So Paul you had a question to bring in on the side. 00:17.79 Paul Yeah I did I was curious so Marcus you're saying that that size is a great filter that you use once things get too small you ah you don't want to count them because they're unreliable and part of that is that they become rounder are there other. Thresholds that you use about the shape of the particles that you that you can use to filter or is basically size and roundness the the main one. 00:43.65 Markus Um, actually I mean for the moment and this is really like the ongoing project I'm still trying to figure out. You know what are good characteristics to identify macroabbotage. So as to repeat 1 aspect this particle analyzer that I'm using Meshes about. 00:50.40 Paul Me. 01:01.43 Markus 39 variables and I say about because you can turn on specific measures and others. But so you have a lot of variables to play with so you can look into angularity different types of length width and so forth and. 01:01.43 Paul Thin. 01:16.92 Markus This is one of the aspects that I'm trying to work through right now to answer seemingly basic Questions. You know how do microabittage look like and how can identify it in statistically useful ways and so currently I'm still Using. Basically all these variables. And ah, we are just like focusing on a few like for example, in this particular paper ah transparent ah transparency came out as the key variable which probably for archaeologists to look at flint's or like like bifaces is pretty. 01:45.79 Paul Whom. 01:55.17 Markus Obvious I guess because normally flakes are relatively thin so light shines through them and the same applies to microabitage. So for our machine learning Algorithms transparency was by far the key variable others came in. 01:59.55 archpodnet Um, yeah. 02:13.43 Markus But this is also when ah where these different algorithms then differed. You know where which type of variable they preferred. But as I said transparency was really the one that stood out among all 4 algorithms that we compared. 02:28.59 archpodnet You know that's really interesting to me because you've got in the article. Ah you used a a handful of different algorithms right to these machine machine learning Algorithms but in order to make a machine learning algorithm smart and and and give you the results that it's that it's going to come out with. You have to teach it. But if we don't really know if you guys don't really know exactly how to characterize one of these micro debotage flakes. What kind of material are you giving the algorithm to say this is right and this is wrong. 02:55.61 Markus So what we do is and this is why the data scientists on the team were so delighted because we have experimentally produced microdabotage. So basically what we gave the machine is okay, this is a sample of experimentally produced microdavitage. 03:04.61 archpodnet Oh right? yeah. 03:07.50 Paul Um. 03:13.88 Markus And this is what you have to as a training material. So this is how microdibotage looks like and then we give it the archaeological soil sample and say okay, where can you find this microdavitage in an actual soil sample and can you figure out. Are there similar. 03:16.26 archpodnet Yeah. 03:28.50 Paul In. 03:31.27 archpodnet Ah. 03:33.45 Markus Particles in this soil sample. So this is the key part that we have an experimental sample that can be used for training and then we can apply it to an actual soil sample. 03:43.64 archpodnet I'm imagining somebody napping in like a radiological suit in a clean room or something like that. So you don't contaminate it with anything else. 03:46.60 Markus But but you know I mean you know we I mean yeah in our archaeological way I bought like 1 of these 20 by thirty feet tarps and we put it up in a small room and the flintnapper was then working diligently in front of the tarp and we just folded it up and put it all into siplock bags. 04:00.38 Paul Um, the. 04:09.50 Paul Yeah, you know you'd mentioned earlier flint and obsidian and and we're talking about the the training group how how much variability you have between different kinds of stone that would be used because I could imagine that might be significant between Churchs and flints and obsidians and whatever else people are. 04:09.36 archpodnet Nice, nice. 04:27.24 Markus Like no you know and this is again, you know like in a short I would have to say we don't know because you know like like people have always assumed as I said before with the manual approach. You know that every micro debotage particle should look like a regular flake. 04:27.71 Paul Quartzite Whatever else, they're ah they're napping. 04:33.88 Paul I. 04:46.30 Markus And nobody has really studied differences for example, in material. You know like and I'm just getting into that you know is obsidian the same from flint are different sources of Obsidian ah do they have do they produce the same type of of Debitage. So this is really what I'm really starting to to to throw these statistics out to to see whether we can see these differences or whether they are really similar. But yeah, it's like it's again, 1 of these simple questions that lead. 05:05.57 archpodnet Um. 05:18.79 Markus On a rabbit hole of well we don't really know we have to jump into that and look into different sources different raw material sources and compare. 05:28.28 Paul Um, I'm also imagining different workshops using slightly different techniques or different tools might also affect that. Ah. 05:32.15 Markus Yeah, you know and and to add that I mean for example I have a credit student who's interested in gender differences I mean you know I don't know whether you ever went to one of these nap-ins I find them fascinating because they are basically 95% male so this is often. 05:33.33 archpodnet Yeah. 05:39.30 Paul Are. 05:48.94 Paul Um. 05:49.36 Markus Also what we think you know when we think about stonenapping. Okay, well what you know these are male stoneappers. But again you know do we really know that and so I have a graduate student who looks for specifically female stoneappers to collect their debris. 06:04.90 archpodnet Um. 06:06.67 Markus To see whether she can find find for example, different differences among the debris of male versus female stone Nappers again an issue that simply hasn't been studied and and I'm looking forward to see that you know like like whether she makes find something. 06:12.78 Paul Who. 06:23.30 archpodnet Yeah, yeah, it might be I mean not to be too on the nose but literally microscopic differences between male and female. But that the algorithm could could suss out. Yeah yeah, it had to be said. 06:33.90 Markus Well, you know mean you know and and what you what we also do we do interviews with modern stoneappppers. And for example, we had several male stoneappers who say you know female colleagues that they have they can put as much pressure on the stone. So so. 06:35.82 Paul But yeah, sorry. 06:52.15 Paul Um. 06:52.62 archpodnet Um. 06:52.96 Markus Again, you know this is not quantifiable but you know anecdotally they say oh there are differences how male and female stonenappers work and you know if we can quantify that I mean that that would be fascinating. 07:03.28 archpodnet Yeah, you know something Paul said earlier made me think about another thing that could be looked for during this process you mentioned different workshops different tools. Obviously. There's different things used to make stone tools right? You've got antler. You've got bone. You've got other rocks. You know things like that. Are you guys close to analyzing because those are going to break up as well and you'll produce micro bits of debris from those. So are you able to find some of that in your samples are you looking for that kind of stuff yet. 07:27.81 Markus The session. 07:34.11 Markus Not yet I mean but made but you bring up a really good point I mean different napping techniques. So another thing that we are working with modernstoneappers is to ask them well or what we do is we record that the specific tools that they're using. 07:37.40 archpodnet Yeah. 07:50.98 Markus And we also ask them. You know could you use an antler instead of like like an isshy stick or whatever they're doing and that's for us Really a critical part again, something that and has not been studied the other aspect. 07:51.61 archpodnet Um. 07:56.73 archpodnet Yeah. 08:02.78 archpodnet Oh. 08:06.39 Markus Really, that's a really good idea I mean I haven't really thought about you know Antler Debris that could end up in a soil sample. Um, yeah I mean it's possible I mean honestly I haven't looked into it so I don't know. Yeah. 08:19.22 archpodnet Yeah, there's so many there's so many directions this could go really, it's it's pretty interesting I've got another direction to go here. Paul you have a follow up sound like you might okay so you know bringing bringing this all together and I know you're really in preliminary stages on figuring out what we can actually. 08:22.73 Paul Yeah. 08:23.15 Markus Yeah. 08:30.40 Paul Not now not I good. 08:38.91 archpodnet Find out from all this stuff but and and we talked about this a little bit in segment one. But really, what have you learned from some of the things you've analyzed by studying microdebotage that you wouldn't have known otherwise about a site or about you know a technique or something like that. What? what is this really telling you that's different from other techniques. 08:56.48 Markus Well I mean 1 aspect is is simply that I see a path forward to analyze hundreds or even thousands of soil samples. So the traditional manual approach has been really limited in the sample population. I mean I think you know I did a review of the literature I think the maximum number that I saw is about 160 samples so people have been really ah dealing with like often just a single room in a building or like a residential group. 09:15.68 archpodnet Um. 09:20.80 Paul A. 09:23.40 archpodnet Um. 09:31.99 Markus But it has been really hard to to use Microabbotage analysis at least the traditional microabbotage analysis on the level of an entire archaeological site or even like a region. 09:40.89 archpodnet Um, yeah. 09:44.20 Markus And that's really what I'm getting very excited about I mean one of my previous credit students. We are still collaborating. She for example, took soil samples from an entire archaeological site in the mayeolands and we are now still I mean these are now 500 and something samples. So we are still in the process of looking through them. But this is for me the first where I can say okay, we can probably talk about how stonenapping looked like in an entire ancient. Ah city you know? do we have different neighborhoods of stonenappers did they work with different stone materials to to not compete with each other and so they are really for me. Fascinating issues about the ancient economy of stone napping that previously could not be answered and so that's what I'm really getting excited about to to scale up this particular. 10:30.80 archpodnet Um, yeah, um. 10:34.77 Markus Approach and hopefully get insights into like larger economic patterns in ancient societies. 10:43.56 archpodnet You know as we're wrapping up here anytime somebody comes up with an efficient way to do something and you bought the equipment you have the ah the particle analyzer and you know you're you're developing the algorithms for this since this paper came out not too long ago. Have you been approached by anybody else to say hey can you analyze my soil can you do this? You guys might be setting up a business here. 11:06.60 Markus I'm not yet there? No but I'm getting really I mean people are getting really fascinated by it I mean so and and I should say I mean I'm also getting requests from Archaeologists who suddenly hear about the machine and have completely new ideas. 11:20.20 archpodnet Um, sure. 11:21.51 Markus For example, a colleague in my department. His wife works with she's interested in the development of maize ah corn across time and so she for example, excavates Mittens where she has in differentffer layers like from. 11:31.00 archpodnet Um, yeah. 11:38.97 Markus Thousands of years back until more recently different chart Mace Kernels and so she asked me whether she could run these hundreds of Mace Kernels through the particle analyzer to study how the individual kernels how they differ in size or dimensions across time. 11:41.30 archpodnet Um, but. 11:58.50 Markus So the point is you know you can apply this particle analyzer and not only to microdebotage but you know you can come up with really interesting new ideas about how to look at archaeology. So yeah I mean um I assume that there will be more people knocking on my door and then asking about that. 12:13.58 archpodnet Could be an easy way to fund your research. 12:17.35 Markus Um, about if we would be that wealthy term as archaeologists. You know our funding limits. 12:26.62 archpodnet Ah, indeed indeed. Well where do where do you go from here. What do? what are you looking at next to I mean without giving away any papers or anything that are in production I mean what? what do you? hope? what kind of questions are you hoping to answer after this. 12:40.49 Markus so so 1 thing is really that we tried to nail down quite a few of the questions that you just brought up I mean for example is micro debotage the same across different raw materials. Do you see differences among male, female or. 12:52.33 archpodnet Sure. 12:58.47 Markus Stonenappers let's say in the experience a stonenapper who has 5 years experience versus a stonenapper who has 20 years of experience so we are really my team and I should really say it's a team I mean it's not just me I mean they are credit students and others who are working on that we're really to trying to to answer. 13:01.83 archpodnet Um. 13:09.34 archpodnet Yeah. 13:17.21 Markus These questions through this part so this is really one of the biggest hopes to to find answers to these questions. Another thing that I'm actually what I did this summer I mean I came back from Israel. So for example, I'm also using the particle analyzer to study ancient mortars so we got an any age grant to look into the different components that ancient peoples put into mortars and so I collected. 13:36.73 archpodnet Well. 13:47.48 Markus Mortar samples and now ah well we started ready to to run them through the particle analyzer and we hope to be able to find out how mortars from different cultures differ in the composition of of their mortars. 14:00.67 archpodnet Nice, nice. That's really cool. Well. 14:05.90 Paul Yeah I've got ah at in Iraq you know Chris you know? Well I've been working there for the last couple of years and 1 of my colleagues is doing all sorts of soil cores looking at environmental change and the advance in the retreat of the waters there and I could see this being maybe a. 14:11.52 archpodnet Um, yeah. 14:22.26 Paul Ah, way of you know he looks at at you know, very small funnel remains to tell us what kind of of environment it was and I could see this being or this set of tools being a way of ah of looking at finer grin changes. Between 1 layer and another then he can currently do just because it's too slow to do it manually. 14:40.80 Markus Yeah, yeah, no I mean and you know if if anybody's interested I mean you know you can approach me I mean people can run their samples and go with it I mean that's. 14:43.25 archpodnet Um. 14:49.81 Paul Um. 14:51.32 archpodnet Yeah, awesome. All right? Well this has been super fascinating I hope we can follow you on this and and and and really stay on top of some of these changes because this is you know we've we've talked about machine learning. We've talked about you know, Ai and and doing some stuff like that before. And and a lot of it is really fascinating but this really this really kind of hits one of my sweet spots. You know as ah as a cultural resource management archeologist out here in the west of the United States we deal with a lot of lithics and sometimes you know we're on a site and we're like okay so we found like 20 flakes that's pretty much it here's the story of the site. When in reality there's two hundred Thousand Microdebotage flakes because somebody already picked up the tools somebody already even picked up some of the flakes and the real story. The site hasn't been told I think that's just super interesting from ah from a management standpoint. You know we we say the site is not significant because we didn't find anything big. 15:28.34 Paul Name. 15:42.98 Paul Um, yeah, yeah and I'm looking at it with interest because it it's not about the tech. It's not about the stats. It's about how those are being used to analyze what people did which is you know as anthropological archeologists here. That's really what it's all about. 15:43.99 Markus Yeah, you're right. 15:44.29 archpodnet But what about all the small stuff that could really tell you about the site and so. 15:58.13 archpodnet Yeah, yeah, exactly all right? Well Marcus. Thank you! We really appreciate it and always feel free to come on the show when you're you know, ready to talk about some more fascinating tech stuff that you guys are doing and and and just chat about what you're doing. 15:59.33 Markus Absolutely yeah. 16:06.31 Paul Um, yep. 16:12.41 Markus Thank you so much. Thank you for having me. 16:13.87 Paul Ah, thanks, thanks for coming on take care.