WEBVTT - Research Revealed at Think 2019 0:00:04.120 --> 0:00:07.160 Get in touch with technology with tech Stuff from how 0:00:07.200 --> 0:00:13.560 stuff works dot Com. Hey there, and welcome to tech Stuff. 0:00:13.600 --> 0:00:18.360 I'm Jonathan Strickland. I'm the executive producer of this here podcast, 0:00:18.480 --> 0:00:20.760 and I worked with how Stuff Works and my Heart 0:00:20.840 --> 0:00:24.479 Radio and love all things tech. And yes, I'm once 0:00:24.480 --> 0:00:28.200 again recording from my hotel room in San Francisco to 0:00:28.280 --> 0:00:31.640 talk about what I've seen and learned at the IBM 0:00:31.840 --> 0:00:35.519 Think two thousand nineteen conference. Thanks again to IBM for 0:00:35.560 --> 0:00:37.479 bringing me out here to really dive into all the 0:00:37.520 --> 0:00:41.600 cool stuff going on. And this is my particular point 0:00:41.640 --> 0:00:44.280 of view of what I saw. I'm really excited about 0:00:44.320 --> 0:00:48.600 this particular topic. If you listened to the episodes I 0:00:48.640 --> 0:00:51.640 recorded last year at IBM Think two thousand and eighteen, 0:00:51.720 --> 0:00:54.920 which was in Las Vegas, Nevada, you heard my two 0:00:54.960 --> 0:00:58.200 part series about the five and five presentation, which is 0:00:58.240 --> 0:01:01.760 a session in which IBM researchers presents some of the 0:01:01.760 --> 0:01:04.200 cool things they're working on and the results of some 0:01:04.319 --> 0:01:08.840 high tech bleeding edge research. This year, IBM changed things 0:01:08.880 --> 0:01:11.520 up a little bit by focusing the presentation on one 0:01:11.680 --> 0:01:15.959 broad topic, and it's one of my favorites. Food. I 0:01:16.160 --> 0:01:19.520 love food, particularly if there's hot sauce involved, but the 0:01:19.560 --> 0:01:22.679 IBM research was a bit more ambitious than finding the 0:01:22.800 --> 0:01:26.760 right condiment to make my burrito zing. Rather, the presentations 0:01:26.800 --> 0:01:29.600 I saw brought the audience on a journey for the 0:01:29.800 --> 0:01:33.679 entire ecosystem of our food, from growing it to distributing it, 0:01:33.760 --> 0:01:36.600 to figuring out what to do with plastic waste that's 0:01:36.640 --> 0:01:40.840 generated afterward. The subject is a really important one, so 0:01:40.880 --> 0:01:44.560 when you combine the threats of climate change with the 0:01:44.600 --> 0:01:48.080 growing population, you quickly come to the conclusion that feeding 0:01:48.120 --> 0:01:51.240 the planet is just going to get more challenging than 0:01:51.280 --> 0:01:54.559 it already is, and that managing resources and making food 0:01:54.600 --> 0:01:59.240 available will be absolutely critical. Each presenter focused on a 0:01:59.280 --> 0:02:03.360 particular topic, which led pretty smoothly into the next one. 0:02:03.480 --> 0:02:05.480 So I'm going to give you a rundown on what 0:02:05.560 --> 0:02:09.920 those presentations were and the related technologies. First up was 0:02:10.080 --> 0:02:15.320 Juliet Mutahi, a software engineer from Nairobi, Kenya. Her main 0:02:15.400 --> 0:02:19.400 focus was on the food chain, the food supply chain. 0:02:19.800 --> 0:02:23.160 She personalized her story by telling the audience of her 0:02:23.200 --> 0:02:26.359 background as the daughter of a coffee farmer in Kenya. 0:02:26.800 --> 0:02:29.400 Her father's coffee farm is part of a cooperative or 0:02:29.440 --> 0:02:32.200 a co op, and that's an association of business owners 0:02:32.200 --> 0:02:35.160 who worked together for the common benefit of the members. 0:02:35.480 --> 0:02:38.600 They can coordinate to negotiate the best prices for their products, 0:02:38.639 --> 0:02:40.799 for example, and make sure that no one is failing 0:02:40.840 --> 0:02:43.880 to get his or her fair share. And co ops 0:02:43.880 --> 0:02:47.360 help establish best practices like fair pricing and labor and 0:02:47.639 --> 0:02:50.480 they can negotiate long term contracts with buyers on a 0:02:50.560 --> 0:02:53.399 level that an individual farm owner might not be able 0:02:53.400 --> 0:02:57.440 to manage. In Kenya, there are twelve thousand members who 0:02:57.480 --> 0:03:00.000 are part of these co ops and they contribute more 0:03:00.040 --> 0:03:04.200 and half of Kenya's coffee production. Cooperatives work because their 0:03:04.240 --> 0:03:07.960 members share information across the value chain. They do it 0:03:08.000 --> 0:03:12.560 through spoken word. If one farm produces high quality coffee, 0:03:12.639 --> 0:03:15.400 the cooperative would negotiate to get a fitting price, a 0:03:15.480 --> 0:03:19.200 premium price for that coffee. So how can we use 0:03:19.240 --> 0:03:21.800 technology to sort of achieve the same sort of things 0:03:21.800 --> 0:03:25.679 that have been going on in cooperatives. Well, technology is 0:03:25.720 --> 0:03:28.480 allowing for the next evolution of this model, and like 0:03:28.639 --> 0:03:31.960 pretty much every digital solution you can think of, it 0:03:32.080 --> 0:03:36.400 all revolves around data. How can farmers collect more information 0:03:36.440 --> 0:03:39.840 about their land, their soil and make reliable predictions of 0:03:39.840 --> 0:03:44.240 future harvests? To better anticipate contract negotiations or better manage 0:03:44.280 --> 0:03:47.280 their farms. She spoke of an approach in which a 0:03:47.320 --> 0:03:49.960 farmer would use a tractor with embedded sensors in it 0:03:50.080 --> 0:03:52.520 to till the land. The tractor would be doing its 0:03:52.880 --> 0:03:57.400 normal tractory duties while simultaneously creating a digital map of 0:03:57.440 --> 0:04:00.720 the farmland itself, so that now there's a digital representation 0:04:00.760 --> 0:04:03.800 of the farm. Feeding the information to IBM S Watson 0:04:03.840 --> 0:04:07.840 for Agriculture Platform would allow for meaningful use of that data. 0:04:08.000 --> 0:04:10.760 Watson can take that information and combine it with other 0:04:10.880 --> 0:04:15.000 sources to make predictions about future yields and give farmers 0:04:15.080 --> 0:04:17.880 ideas about the conditions of their land. It can also 0:04:18.400 --> 0:04:22.000 analyze the data to estimate what past yields might have been. 0:04:22.400 --> 0:04:24.359 And you might wonder, why would you ever need to 0:04:24.440 --> 0:04:27.120 know what has already happened. Why would you need to 0:04:27.279 --> 0:04:31.040 estimate a past yield? It becomes really important in cases 0:04:31.080 --> 0:04:34.120 where a farmer has to file an insurance claim. It 0:04:34.240 --> 0:04:37.360 helps justify that insurance claim. If the farmer says that, 0:04:37.480 --> 0:04:40.440 due to whatever reason, the yield was a certain size 0:04:40.839 --> 0:04:43.040 and the data backs that up, it can help the 0:04:43.080 --> 0:04:46.120 farmer get that insurance claim and it also helps build 0:04:46.160 --> 0:04:50.040 out models that will increase efficiency further down the supply chain. 0:04:51.080 --> 0:04:54.560 Mutahi also talked about a cool analytical tool called the 0:04:54.640 --> 0:04:57.800 IBM Argo Pod. This is a great example of an 0:04:57.839 --> 0:05:00.840 Internet of Things device. It's about the size and shape 0:05:00.960 --> 0:05:04.280 of a regular business card. Embedded in the card are 0:05:04.360 --> 0:05:07.640 sensors that can do soil analysis, and a farmer just 0:05:07.680 --> 0:05:09.599 needs to put a small sample of soil on the 0:05:09.640 --> 0:05:12.880 card and chemical reactions will tell the sensor everything it 0:05:12.920 --> 0:05:15.520 needs to know in just ten seconds, and then the 0:05:15.520 --> 0:05:18.000 farmer can take a picture of the card using a 0:05:18.120 --> 0:05:21.640 smartphone and use a related app to store the information 0:05:21.720 --> 0:05:24.640 into a blockchain record. This doesn't just tell the farmer 0:05:24.680 --> 0:05:26.880 of the conditions on the farm, it can also help 0:05:26.920 --> 0:05:30.680 the farmer establish credit because a bank could extend credit 0:05:30.720 --> 0:05:34.600 to a farm against a predicted harvest that's based on 0:05:34.640 --> 0:05:37.680 this collected information. So for farmers all over the world, 0:05:37.680 --> 0:05:41.560 this could be an enormous help. Mutahi then handed the 0:05:41.560 --> 0:05:44.640 stage over to Shri ram rug Hoven. He is the 0:05:44.800 --> 0:05:48.640 Vice president and chief Technical Officer of IBM Research in India. 0:05:48.880 --> 0:05:53.719 He shared a pretty staggering pair of facts. One third 0:05:53.880 --> 0:05:57.920 of all food produced and nearly half of all fruits 0:05:57.920 --> 0:06:02.600 and vegetables never get assumed. It just goes to waste. 0:06:03.000 --> 0:06:06.920 So imagine if half of your work was immediately dismissed. 0:06:07.120 --> 0:06:09.240 You still had to do the work, but you know 0:06:09.520 --> 0:06:13.480 that half of it wouldn't count. That would be frustrating 0:06:13.640 --> 0:06:16.000 for most jobs, but when it comes to food production, 0:06:16.040 --> 0:06:19.200 it can lead to waste management problems at best, and 0:06:19.440 --> 0:06:23.000 at worst you could be facing starvation issues. So what 0:06:23.320 --> 0:06:25.919 is the challenge here? Is this just a case of 0:06:26.000 --> 0:06:29.960 some places having more food than the population can consume. Well, 0:06:30.000 --> 0:06:33.520 it's actually a lot more complicated than that. The food 0:06:33.560 --> 0:06:37.240 supply chain is a big issue. There are many points 0:06:37.279 --> 0:06:41.159 along a supply chain, and at every stage spoilage can 0:06:41.240 --> 0:06:44.599 and does occur, So there's a decent chance that a 0:06:44.640 --> 0:06:46.560 lot of food will be spoiled before it can ever 0:06:46.640 --> 0:06:50.040 find its way onto a market shelf. From the fields 0:06:50.279 --> 0:06:54.599 to the storage facilities, to transportation vehicles to distribution centers, 0:06:54.600 --> 0:06:57.280 to processors to shops to the home, there are a 0:06:57.320 --> 0:07:00.640 lot of stops along the way, and presently this is 0:07:00.800 --> 0:07:04.240 largely a dumb system, meaning there's no real way to 0:07:04.279 --> 0:07:07.800 gather information and share it along the supply chain. So 0:07:07.920 --> 0:07:10.560 if you receive a creative apples in a distribution center 0:07:10.600 --> 0:07:14.320 that are maybe two days away from being at peak ripeness, 0:07:14.480 --> 0:07:17.000 but you have no way of knowing that information. When 0:07:17.040 --> 0:07:19.120 you've got the crate, you might put that create on 0:07:19.160 --> 0:07:21.160 a truck that's going across the country, and by the 0:07:21.160 --> 0:07:24.119 time the apples get to their destination, a large number 0:07:24.160 --> 0:07:26.120 of them have already passed their prime and they just 0:07:26.200 --> 0:07:30.240 get thrown out. So what's the solution to this problem. 0:07:30.280 --> 0:07:32.560 The proposal we heard is that you would take a 0:07:32.600 --> 0:07:37.000 combination of technologies, and that includes the Internet of things, blockchain, 0:07:37.120 --> 0:07:39.920 and artificial intelligence in order to keep track of everything 0:07:39.960 --> 0:07:42.920 and make decisions. The Internet of things and the blockchain 0:07:43.120 --> 0:07:46.880 combined could log each stage of the journey the food 0:07:46.920 --> 0:07:49.960 takes from field to the market and keep track on 0:07:50.000 --> 0:07:52.560 the freshness of the food. There would be a record 0:07:52.840 --> 0:07:57.080 for each crate or palette or whatever unit of food 0:07:57.400 --> 0:08:00.880 that could record when it arrived and when it each point, 0:08:01.240 --> 0:08:03.880 and you could understand quickly how much time had passed 0:08:04.120 --> 0:08:07.480 since it was harvested. AI could help guide the decision 0:08:07.520 --> 0:08:10.280 making process when it comes to deciding where do you 0:08:10.360 --> 0:08:13.280 send this next. So the example we heard in the 0:08:13.320 --> 0:08:17.520 presentation involved oranges, and here's how it goes. Let's say 0:08:17.560 --> 0:08:20.800 that you run a distribution center in Florida near where 0:08:20.800 --> 0:08:24.320 oranges are grown. So farmers oranges come into your distribution center, 0:08:24.360 --> 0:08:26.600 and it's your job to send those oranges out to 0:08:27.240 --> 0:08:30.720 UH stores in various cities. And the two main cities 0:08:30.840 --> 0:08:34.520 under your responsibility are Atlanta and Chicago. And as it 0:08:34.520 --> 0:08:38.320 turns out, in Atlanta, people are hog wild for these oranges. 0:08:38.360 --> 0:08:40.200 And I can confirm that because at least from this 0:08:40.240 --> 0:08:43.319 Atlanta's point of view, this is accurate. But in Chicago, 0:08:43.880 --> 0:08:46.920 oranges for some reason just aren't moving nearly so fast 0:08:47.040 --> 0:08:50.360 from the produce section. With access to this information, the 0:08:50.400 --> 0:08:53.520 AI can make decisions. Oranges that still have a really 0:08:53.520 --> 0:08:56.480 long time to ripen could be sent to Chicago because 0:08:56.720 --> 0:08:59.000 they could sit in refrigeration a bit longer. They could 0:08:59.000 --> 0:09:02.080 remain fresh while the inhabitants of the Windy City decide 0:09:02.120 --> 0:09:05.480 they finally want to fight off scurvy. Oranges that are 0:09:05.559 --> 0:09:08.640 close to passing prime ripeness can make the shorter trip 0:09:08.679 --> 0:09:11.320 to Atlanta, where they are more likely to be purchased 0:09:11.360 --> 0:09:16.480 and consumed quickly. The distributor can maximize efficiency and minimize waste. 0:09:16.960 --> 0:09:19.200 Now next we're going to hear about a proposal that 0:09:19.400 --> 0:09:22.840 is all about food safety. But first let's take a 0:09:22.920 --> 0:09:33.240 quick break. The third presenter in the five and five 0:09:33.280 --> 0:09:37.280 event was Gerroud Dubois, director of IBM research at Almondon. 0:09:37.640 --> 0:09:41.240 Dubois began his presentation by talking about a catastrophe in 0:09:41.360 --> 0:09:44.800 China in two thousand and eight. A shipment of baby 0:09:44.880 --> 0:09:49.079 formula had been contaminated with a chemical called Melman. This 0:09:49.280 --> 0:09:52.920 is an industrial chemical that manufacturers used to treat stuff 0:09:52.960 --> 0:09:56.480 like ceramics and plastics. It is used in glue, in 0:09:56.600 --> 0:10:00.520 flame retardants, and laminates. It is not, as you might imagine, 0:10:01.000 --> 0:10:04.680 meant for consumption. Parents who fed their babies this formula 0:10:04.800 --> 0:10:07.559 quickly became alarmed when the babies began to get sick. 0:10:08.120 --> 0:10:11.800 Melman can cause kidney damage and Chinese hospitals had to 0:10:11.840 --> 0:10:16.000 admit more than fifty thousand babies. And even darker part 0:10:16.000 --> 0:10:18.120 of the story is that the addition of the chemical 0:10:18.720 --> 0:10:22.280 was likely intentional. The chemical makes it appear that the formula, 0:10:22.320 --> 0:10:25.440 when combined with milk, is more protein rich than it 0:10:25.600 --> 0:10:31.080 actually is, so it was an attempt at deception. So 0:10:31.120 --> 0:10:35.960 that's even more disturbing. Well, du Bois proposed that we 0:10:36.280 --> 0:10:40.680 rely upon microbes as a sort of microscopic canary in 0:10:40.679 --> 0:10:43.839 a coal mine, or as he called it, a microscopic 0:10:44.160 --> 0:10:48.319 c I a agent, and it would detect when contaminants 0:10:48.320 --> 0:10:50.840 are present in food products. And a microbe is a 0:10:50.880 --> 0:10:55.040 micro organism. Bacteria are a type of microbe, and you've 0:10:55.120 --> 0:10:59.360 likely used stuff like antimicrobial products to help sanitize stuff, 0:10:59.640 --> 0:11:02.200 and this could give you the implication that microbes are 0:11:02.240 --> 0:11:05.480 bad and some are definitely harmful to us, but some 0:11:05.640 --> 0:11:08.880 microbes are beneficial. And the human body is host to 0:11:09.160 --> 0:11:14.560 almost actually slightly more microbial cells than human cells. The 0:11:14.640 --> 0:11:18.040 ratio appears to be somewhere around one point three bacterial 0:11:18.120 --> 0:11:21.080 cells to every human cell, so you could say that 0:11:21.160 --> 0:11:25.000 you're more bacteria than person, though that's not really the point. 0:11:25.040 --> 0:11:29.240 Our microbial biome or biota is actually part of us, 0:11:29.240 --> 0:11:32.040 so I would say we are collectively made of both 0:11:32.080 --> 0:11:37.240 bacteria and human cells. We are bored, I guess. Anyway, 0:11:37.720 --> 0:11:40.080 Not all microbes are bad. Some are very helpful and 0:11:40.120 --> 0:11:45.640 they aid us in digesting certain materials, so some are 0:11:45.679 --> 0:11:48.280 good and we should rely upon those. Do Boa proposes 0:11:48.320 --> 0:11:51.640 we could use microbes to detect the presence of contaminants 0:11:51.679 --> 0:11:54.360 and food. So for a long time, scientists thought that 0:11:54.440 --> 0:11:57.719 the behaviors of microbes were too complex and unpredictable to 0:11:57.760 --> 0:12:01.839 reveal meaningful information, that it was almost random. But by 0:12:01.840 --> 0:12:04.800 studying them at a genetic level, looking at the d 0:12:04.960 --> 0:12:08.000 n A and the RNA of microbes, we've gathered a 0:12:08.040 --> 0:12:11.240 lot more information that reveals microbes react in different ways 0:12:11.400 --> 0:12:14.800 to different conditions. To make that determination, we had to 0:12:14.920 --> 0:12:19.319 use a big data approach. Dubai used a helpful analogy 0:12:19.400 --> 0:12:23.440 to describe how challenging this process really was. So imagine 0:12:23.480 --> 0:12:28.319 you have ten thousand boxes of jigsaw puzzles. They're different puzzles, 0:12:28.360 --> 0:12:31.680 and you dump all the pieces out into one enormous pile. 0:12:31.760 --> 0:12:33.640 You mix them up real good, then you throw the 0:12:33.679 --> 0:12:36.120 boxes away, so you don't even have the record of 0:12:36.160 --> 0:12:38.360 what the pictures look like, and now it's your job 0:12:38.400 --> 0:12:42.240 to put together those ten thousand puzzles. That's sort of 0:12:42.280 --> 0:12:44.400 the scale of the job we had to do to 0:12:44.520 --> 0:12:48.920 suss out how microbes behave given different conditions. At IBM, 0:12:49.000 --> 0:12:52.520 the research team created a database containing all the microbial 0:12:52.640 --> 0:12:56.439 genomes the scientific world has mapped so far. The genomes 0:12:56.480 --> 0:13:00.960 and the analysis of microbial behavior represents around five hundred 0:13:01.160 --> 0:13:04.920 terabytes of data. But the process was successful and that 0:13:05.000 --> 0:13:08.360 there are microbial behaviors that can indicate the presence of 0:13:08.400 --> 0:13:11.520 contaminants in our food. You have to know which microbes 0:13:11.559 --> 0:13:15.760 you're looking for and what behaviors indicates safe versus unsafe food. 0:13:15.920 --> 0:13:17.960 But it could add a new method for food safety 0:13:17.960 --> 0:13:20.199 inspectors to use to guarantee that the products that make 0:13:20.240 --> 0:13:24.520 it to consumers are actually safe to consume. Du Bois 0:13:24.520 --> 0:13:28.360 then introduced us to Donna Dillenberger and IBM Fellow at 0:13:28.360 --> 0:13:31.000 the Thomas J. Watson Research Center. Now, I mentioned in 0:13:31.040 --> 0:13:34.520 an earlier episode that the title of IBM Fellow is 0:13:34.559 --> 0:13:39.520 the highest honor IBM bestows on distinguished researchers, scientists, engineers, 0:13:39.520 --> 0:13:43.520 and the like. Dillenberger also talked about food safety. She 0:13:43.679 --> 0:13:46.640 cited a CDC report that I tracked down. The report 0:13:46.720 --> 0:13:50.760 is the Emerging Infectious Diseases Report, and the section Dillenberger 0:13:50.840 --> 0:13:54.319 was specifically referencing is chapter five of that report titled 0:13:54.440 --> 0:13:57.920 food Related Illness and Death in the United States. Now, 0:13:57.920 --> 0:14:01.120 I'm going to quote the abstract of that report verbatim. 0:14:01.200 --> 0:14:04.760 Here's part of that abstract. We estimate that food born 0:14:04.840 --> 0:14:09.840 diseases cause approximately seventy six million illnesses, three hundred twenty 0:14:09.840 --> 0:14:14.079 five thousand hospitalizations, and five thousand deaths in the United 0:14:14.120 --> 0:14:18.120 States each year. Known pathogens account for an estimated fourteen 0:14:18.160 --> 0:14:23.600 million illnesses, sixty thousand hospitalizations, and eighteen hundred deaths. Three 0:14:23.680 --> 0:14:29.480 pathogens Salmonella, listeria, and toxoplasma, are responsible for fifteen hundred 0:14:29.480 --> 0:14:32.960 deaths each year, more than seventy of those caused by 0:14:33.040 --> 0:14:36.960 known pathogens, while unknown agents account for the remaining sixty 0:14:36.960 --> 0:14:41.520 two million illnesses, two hundred sixty five thousand hospitalizations, and 0:14:41.640 --> 0:14:45.120 three thousand, two hundred deaths. Overall, food born diseases appear 0:14:45.200 --> 0:14:48.840 to cause more illnesses but fewer deaths than previously estimated. 0:14:49.360 --> 0:14:52.440 End quote. Now, fewer deaths is a good thing, but 0:14:52.680 --> 0:14:55.880 even fewer would be better, And the huge number of 0:14:55.880 --> 0:15:00.120 illnesses represents not just discomfort, stress, anxiety, at a or 0:15:00.280 --> 0:15:03.280 quality of life. There's a ripple effect. The hits society 0:15:03.280 --> 0:15:06.320 as a whole in ways like lost productivity or additional 0:15:06.360 --> 0:15:09.920 burden on the medical industry. So how can we tell 0:15:10.280 --> 0:15:12.880 if the food we buy is safe to eat? The 0:15:12.920 --> 0:15:16.960 bacteria responsible are microscopic, As I mentioned, just a moment ago. 0:15:17.160 --> 0:15:19.280 We're not likely to have a lab set up in 0:15:19.320 --> 0:15:24.240 our kitchens. Dyllenberger introduced a hardware and software tool that 0:15:24.280 --> 0:15:27.880 could actually help. The hardware component is a smartphone peripheral. 0:15:28.040 --> 0:15:30.760 It's essentially a microscope that plugs into your smartphone and 0:15:30.800 --> 0:15:33.920 feeds a magnified image to the phone's camera sensor. The 0:15:34.000 --> 0:15:37.560 software side is an analysis tool using AI and image 0:15:37.560 --> 0:15:41.960 recognition strategies to identify bacteria present in food. The results 0:15:42.000 --> 0:15:44.800 of the analysis pop up on the screen as shapes 0:15:44.920 --> 0:15:48.000 around the bacteria, and the type and color of shape 0:15:48.240 --> 0:15:52.040 indicates which kind of bacteria might be present. It can 0:15:52.080 --> 0:15:54.440 scan down to the micron scale and let you know 0:15:54.520 --> 0:15:57.000 if the food you have is safe to eat or 0:15:57.040 --> 0:15:59.880 if it is host to say, a colony of eke 0:16:00.000 --> 0:16:03.880 to lie. Dillenberger also revealed that the same technology could 0:16:03.880 --> 0:16:08.000 be used to help discover food counterfeits, and yes, that 0:16:08.200 --> 0:16:11.560 is a thing. In fact, it's a big thing. Dillenberger 0:16:11.600 --> 0:16:14.360 referred to a study that found in the United States, 0:16:14.440 --> 0:16:18.320 olive oil producers weren't always being totally honest, or at 0:16:18.360 --> 0:16:21.720 least they weren't meeting the right standards. Because a study 0:16:21.760 --> 0:16:26.000 in two found that seventy of the bottles of labeled 0:16:26.080 --> 0:16:30.000 extra virgin olive oil actually failed to meet the standards 0:16:30.000 --> 0:16:33.240 to qualify as extra virgin. You wouldn't be able to 0:16:33.280 --> 0:16:36.640 tell the casual glance the difference between regular olive oil 0:16:36.680 --> 0:16:39.320 and good old e v O O, but the scanner 0:16:39.360 --> 0:16:42.120 and paired software can analyze the reflected light from a 0:16:42.120 --> 0:16:44.840 sample of olive oil and determine whether or not it 0:16:44.920 --> 0:16:48.240 matches the real deal or not. The same tech can 0:16:48.280 --> 0:16:50.960 help you figure out if a label is legitimate or 0:16:50.960 --> 0:16:53.800 if it's a clever fake. And it doesn't stop with food, 0:16:54.080 --> 0:16:56.160 though that was the primary focus of the five and 0:16:56.240 --> 0:16:58.760 five presentation, the scanner could also be used to sort 0:16:58.760 --> 0:17:01.440 out the real McCoy from fakers and all sorts of products, 0:17:01.480 --> 0:17:06.640 from fashion accessories to prescription drugs. Moreover, Dylan Berger said 0:17:06.640 --> 0:17:10.640 that while the present implementation uses a smartphone, future versions 0:17:10.640 --> 0:17:14.560 could see embedded sensors integrated into common kitchen tools like 0:17:14.720 --> 0:17:18.800 cutting boards or knives or measuring cups or bowls, and 0:17:18.840 --> 0:17:22.320 by looking for not just authenticity, but for the presence 0:17:22.359 --> 0:17:26.840 of potential pathogens, we could improve our fine dining experience 0:17:26.920 --> 0:17:30.960 and also prevent cases of food poisoning. Next, we're gonna 0:17:31.040 --> 0:17:34.040 learn a little bit about the conclusion of the five 0:17:34.080 --> 0:17:37.160 and five event and what we might do with some 0:17:37.320 --> 0:17:40.920 of the plastic waste we generate. But first let's take 0:17:41.080 --> 0:17:51.440 a quick break. The final presenter at five and five 0:17:51.560 --> 0:17:54.240 was Jeanette Garcia, who has one of the most kick 0:17:54.320 --> 0:17:58.440 ass titles I have ever seen. It's Master Inventor at 0:17:58.440 --> 0:18:03.080 IBM Research Almada. She helped put into perspective exactly how 0:18:03.119 --> 0:18:06.159 big a problem plastic waste has become, and it is 0:18:06.320 --> 0:18:10.920 a huge problem. The world produces around three hundred million 0:18:11.200 --> 0:18:14.959 tons of plastic every year, and about half of that 0:18:15.000 --> 0:18:17.679 plastic is in the form of stuff that's intended for 0:18:17.840 --> 0:18:21.600 single use, meaning we just toss it out afterward. Lots 0:18:21.680 --> 0:18:25.960 of communities are now recycling, but sadly, only a small fraction, 0:18:26.160 --> 0:18:30.640 about ten per cent of plastic gets recycled. So why 0:18:30.800 --> 0:18:33.960 is that, Well, there are a few reasons. One is 0:18:34.000 --> 0:18:36.639 that there are different types of plastics and they can't 0:18:36.680 --> 0:18:39.679 all be processed in the same way, which means they 0:18:39.720 --> 0:18:43.040 have to be sorted into different categories. That takes effort 0:18:43.080 --> 0:18:46.400 and time, which also means it costs money. There are 0:18:46.440 --> 0:18:50.000 contaminants that can be a problem particularly food waste, and 0:18:50.040 --> 0:18:52.600 Garcia mentioned that we often don't know what the rules 0:18:52.640 --> 0:18:55.000 are are we supposed to rinse off the plastic. First, 0:18:55.359 --> 0:18:58.240 some types of plastic aren't recyclable at all, And then 0:18:58.280 --> 0:19:01.280 there's the problem of economics. Pastic is pretty easy stuff 0:19:01.320 --> 0:19:04.880 to manufacture. If it costs more money to recycle plastic 0:19:05.119 --> 0:19:07.720 than it does to just make new plastic, you have 0:19:07.760 --> 0:19:11.080 to come up with some other economic incentives to encourage recycling. 0:19:11.680 --> 0:19:14.960 At the same time, plastic is undeniably useful stuff. We 0:19:15.000 --> 0:19:17.359 rely on it for lots of things, not the least 0:19:17.400 --> 0:19:20.119 of which is food packaging. It's hard to dismiss how 0:19:20.119 --> 0:19:23.760 important plastic is in keeping our foods fresher longer, which 0:19:23.800 --> 0:19:26.760 goes back to cutting down food waste. So how do 0:19:26.880 --> 0:19:31.080 we resolve the problem. The specific type of plastic Garcia 0:19:31.160 --> 0:19:35.119 talked about was pet or pet plastic, which is found 0:19:35.119 --> 0:19:38.400 not only in packaging but also stuff like polyester clothing. 0:19:39.640 --> 0:19:42.760 The seventies, this is the type of plastic used in 0:19:42.800 --> 0:19:45.600 stuff like water and soda bottles. If you look at 0:19:45.600 --> 0:19:48.960 a bottle made from pet, you'll see the chasing arrows 0:19:49.119 --> 0:19:51.920 sign with the number one at the center. It makes 0:19:52.000 --> 0:19:54.360 up a lot of plastic, but I should point out 0:19:54.400 --> 0:19:57.359 that it's also the most recycled type of plastic in 0:19:57.400 --> 0:20:01.560 the world. PET is completely recy cyclable. The United States 0:20:01.640 --> 0:20:04.760 lags behind Europe when it comes to recycling PET plastic. 0:20:05.000 --> 0:20:07.760 We in the US recycle a little more than of 0:20:07.760 --> 0:20:11.760 PT plastic, while Europe is over the line, but we 0:20:11.800 --> 0:20:14.480 can always do better. One of the methods we rely 0:20:14.600 --> 0:20:17.159 upon to recycle this type of plastic is to wash 0:20:17.200 --> 0:20:21.040 the plastic and then melt it down. Another version uses 0:20:21.119 --> 0:20:25.160 chemicals to depolymerize the plastic. Polymer is a long chain 0:20:25.160 --> 0:20:29.320 of molecules, so this approach effectively breaks those chains down. 0:20:29.760 --> 0:20:33.400 But the melting process has a zero tolerance for contamination, 0:20:33.520 --> 0:20:35.920 meaning the only stuff that can get melted down is 0:20:35.960 --> 0:20:39.240 the plastic itself. Any other stuff will foul the melted 0:20:39.320 --> 0:20:42.119 mixture and make it unusable. It also only works with 0:20:42.200 --> 0:20:45.639 clear bottles. The chemical approach has its own drawbacks, a 0:20:45.640 --> 0:20:48.680 big one being the cost of the process, which creates 0:20:48.680 --> 0:20:52.800 that economic barrier I mentioned earlier. IBM solution is called 0:20:52.960 --> 0:20:56.880 volcat which stands for volatile catalyst. So what the heck 0:20:56.960 --> 0:20:59.960 does that mean? A catalyst is a substance that facility. 0:21:00.040 --> 0:21:03.080 It's a chemical reaction. You would typically use a catalyst 0:21:03.160 --> 0:21:05.640 to speed up a process that would otherwise take much 0:21:05.680 --> 0:21:09.800 longer to complete. Catalysts do this without undergoing permanent chemical 0:21:09.920 --> 0:21:14.800 changes themselves. They're incredibly useful in hundreds of different industrial applications. 0:21:15.240 --> 0:21:19.000 With the volecat approach, IBM could grind up pet plastic 0:21:19.080 --> 0:21:21.960 into flakes, and it wouldn't matter if the plastic was 0:21:22.040 --> 0:21:24.159 clear or had color added to it, or if it 0:21:24.200 --> 0:21:27.360 was clean or if it was dirty. With volcat, IBM 0:21:27.400 --> 0:21:30.240 takes that plastic and puts it into a heating chamber. 0:21:30.480 --> 0:21:33.000 The chamber heats the plastic up to about a hundred 0:21:33.040 --> 0:21:36.560 nine degrees celsius or three seventy four degrees fahrenheit. At 0:21:36.600 --> 0:21:40.000 that point researchers add the catalyst. Then they cool the 0:21:40.040 --> 0:21:42.840 mixture down to get below one hundred degrees celsius or 0:21:42.880 --> 0:21:45.800 two hundred twelve degrees fahrenheit. That's the temperature which water 0:21:45.880 --> 0:21:49.440 boils under one atmosphere of pressure. The plastic polymers break 0:21:49.480 --> 0:21:52.679 down into a more basic molecular form called B H 0:21:52.800 --> 0:21:55.240 E T, which is a monomer. And you can think 0:21:55.240 --> 0:21:58.360 of a monomer as a molecule that forms the basic 0:21:58.480 --> 0:22:03.639 component of a polymer identical monomers linked together to form polymers. 0:22:03.680 --> 0:22:06.760 So now you've got what is effectively the building blocks 0:22:06.920 --> 0:22:11.240 of PET. The volatile catalyst is completely recoverable and IBM 0:22:11.240 --> 0:22:14.320 engineers can filter the b ET from any other stuff 0:22:14.400 --> 0:22:16.359 that was in the mix. The b h g T 0:22:16.520 --> 0:22:19.440 can go on to form new pet containers, So we 0:22:19.480 --> 0:22:22.720 could keep using the same plastic over and over again 0:22:22.800 --> 0:22:25.719 without the need to make more of the stuff, and 0:22:25.760 --> 0:22:28.960 should our demand for plastic exceed that amount, we could 0:22:29.000 --> 0:22:33.680 literally mine the Pacific garbage patch and landfills for more material. 0:22:34.080 --> 0:22:39.240 The process sounds incredibly promising and increasing recycling rates, particularly 0:22:39.280 --> 0:22:41.639 for plastics that are dirty or have color added to 0:22:41.680 --> 0:22:44.960 the plastic material. Since the process removes the need to 0:22:45.000 --> 0:22:48.280 clean the plastic first, it could reduce the recycling workload. 0:22:48.520 --> 0:22:51.199 If it is scalable, it could be a viable alternative 0:22:51.200 --> 0:22:55.040 to the present approaches to plastic recycling. These research projects 0:22:55.040 --> 0:22:57.400 were all really interesting to me, and they are all 0:22:57.440 --> 0:23:00.720 trying to make big changes in the entire food life cycle. 0:23:01.119 --> 0:23:04.240 It's a truly enormous challenge and there's still more to 0:23:04.320 --> 0:23:09.040 work on developing technologies to reduce water waste, improve transportation 0:23:09.040 --> 0:23:12.959 and distribution deal with other types of waste, and guaranteeing 0:23:13.040 --> 0:23:15.600 everyone in the world has access to healthy and safe 0:23:15.680 --> 0:23:20.040 food is a monumental effort. These research projects are just 0:23:20.119 --> 0:23:22.800 a few of the ways innovators are looking into making 0:23:22.840 --> 0:23:26.160 a big difference. Will we see each of these ideas 0:23:26.200 --> 0:23:28.920 implemented in the real world. What's a bit early to say, 0:23:28.960 --> 0:23:31.879 but all of those five presenters made a prediction of 0:23:31.920 --> 0:23:34.160