1
00:00:04,120 --> 00:00:07,160
Speaker 1: Get in touch with technology with tech Stuff from how

2
00:00:07,200 --> 00:00:13,560
Speaker 1: stuff works dot Com. Hey there, and welcome to tech Stuff.

3
00:00:13,600 --> 00:00:18,360
Speaker 1: I'm Jonathan Strickland. I'm the executive producer of this here podcast,

4
00:00:18,480 --> 00:00:20,760
Speaker 1: and I worked with how Stuff Works and my Heart

5
00:00:20,840 --> 00:00:24,479
Speaker 1: Radio and love all things tech. And yes, I'm once

6
00:00:24,480 --> 00:00:28,200
Speaker 1: again recording from my hotel room in San Francisco to

7
00:00:28,280 --> 00:00:31,640
Speaker 1: talk about what I've seen and learned at the IBM

8
00:00:31,840 --> 00:00:35,519
Speaker 1: Think two thousand nineteen conference. Thanks again to IBM for

9
00:00:35,560 --> 00:00:37,479
Speaker 1: bringing me out here to really dive into all the

10
00:00:37,520 --> 00:00:41,600
Speaker 1: cool stuff going on. And this is my particular point

11
00:00:41,640 --> 00:00:44,280
Speaker 1: of view of what I saw. I'm really excited about

12
00:00:44,320 --> 00:00:48,600
Speaker 1: this particular topic. If you listened to the episodes I

13
00:00:48,640 --> 00:00:51,640
Speaker 1: recorded last year at IBM Think two thousand and eighteen,

14
00:00:51,720 --> 00:00:54,920
Speaker 1: which was in Las Vegas, Nevada, you heard my two

15
00:00:54,960 --> 00:00:58,200
Speaker 1: part series about the five and five presentation, which is

16
00:00:58,240 --> 00:01:01,760
Speaker 1: a session in which IBM researchers presents some of the

17
00:01:01,760 --> 00:01:04,200
Speaker 1: cool things they're working on and the results of some

18
00:01:04,319 --> 00:01:08,840
Speaker 1: high tech bleeding edge research. This year, IBM changed things

19
00:01:08,880 --> 00:01:11,520
Speaker 1: up a little bit by focusing the presentation on one

20
00:01:11,680 --> 00:01:15,959
Speaker 1: broad topic, and it's one of my favorites. Food. I

21
00:01:16,160 --> 00:01:19,520
Speaker 1: love food, particularly if there's hot sauce involved, but the

22
00:01:19,560 --> 00:01:22,679
Speaker 1: IBM research was a bit more ambitious than finding the

23
00:01:22,800 --> 00:01:26,760
Speaker 1: right condiment to make my burrito zing. Rather, the presentations

24
00:01:26,800 --> 00:01:29,600
Speaker 1: I saw brought the audience on a journey for the

25
00:01:29,800 --> 00:01:33,679
Speaker 1: entire ecosystem of our food, from growing it to distributing it,

26
00:01:33,760 --> 00:01:36,600
Speaker 1: to figuring out what to do with plastic waste that's

27
00:01:36,640 --> 00:01:40,840
Speaker 1: generated afterward. The subject is a really important one, so

28
00:01:40,880 --> 00:01:44,560
Speaker 1: when you combine the threats of climate change with the

29
00:01:44,600 --> 00:01:48,080
Speaker 1: growing population, you quickly come to the conclusion that feeding

30
00:01:48,120 --> 00:01:51,240
Speaker 1: the planet is just going to get more challenging than

31
00:01:51,280 --> 00:01:54,559
Speaker 1: it already is, and that managing resources and making food

32
00:01:54,600 --> 00:01:59,240
Speaker 1: available will be absolutely critical. Each presenter focused on a

33
00:01:59,280 --> 00:02:03,360
Speaker 1: particular topic, which led pretty smoothly into the next one.

34
00:02:03,480 --> 00:02:05,480
Speaker 1: So I'm going to give you a rundown on what

35
00:02:05,560 --> 00:02:09,920
Speaker 1: those presentations were and the related technologies. First up was

36
00:02:10,080 --> 00:02:15,320
Speaker 1: Juliet Mutahi, a software engineer from Nairobi, Kenya. Her main

37
00:02:15,400 --> 00:02:19,400
Speaker 1: focus was on the food chain, the food supply chain.

38
00:02:19,800 --> 00:02:23,160
Speaker 1: She personalized her story by telling the audience of her

39
00:02:23,200 --> 00:02:26,359
Speaker 1: background as the daughter of a coffee farmer in Kenya.

40
00:02:26,800 --> 00:02:29,400
Speaker 1: Her father's coffee farm is part of a cooperative or

41
00:02:29,440 --> 00:02:32,200
Speaker 1: a co op, and that's an association of business owners

42
00:02:32,200 --> 00:02:35,160
Speaker 1: who worked together for the common benefit of the members.

43
00:02:35,480 --> 00:02:38,600
Speaker 1: They can coordinate to negotiate the best prices for their products,

44
00:02:38,639 --> 00:02:40,799
Speaker 1: for example, and make sure that no one is failing

45
00:02:40,840 --> 00:02:43,880
Speaker 1: to get his or her fair share. And co ops

46
00:02:43,880 --> 00:02:47,360
Speaker 1: help establish best practices like fair pricing and labor and

47
00:02:47,639 --> 00:02:50,480
Speaker 1: they can negotiate long term contracts with buyers on a

48
00:02:50,560 --> 00:02:53,399
Speaker 1: level that an individual farm owner might not be able

49
00:02:53,400 --> 00:02:57,440
Speaker 1: to manage. In Kenya, there are twelve thousand members who

50
00:02:57,480 --> 00:03:00,000
Speaker 1: are part of these co ops and they contribute more

51
00:03:00,040 --> 00:03:04,200
Speaker 1: and half of Kenya's coffee production. Cooperatives work because their

52
00:03:04,240 --> 00:03:07,960
Speaker 1: members share information across the value chain. They do it

53
00:03:08,000 --> 00:03:12,560
Speaker 1: through spoken word. If one farm produces high quality coffee,

54
00:03:12,639 --> 00:03:15,400
Speaker 1: the cooperative would negotiate to get a fitting price, a

55
00:03:15,480 --> 00:03:19,200
Speaker 1: premium price for that coffee. So how can we use

56
00:03:19,240 --> 00:03:21,800
Speaker 1: technology to sort of achieve the same sort of things

57
00:03:21,800 --> 00:03:25,679
Speaker 1: that have been going on in cooperatives. Well, technology is

58
00:03:25,720 --> 00:03:28,480
Speaker 1: allowing for the next evolution of this model, and like

59
00:03:28,639 --> 00:03:31,960
Speaker 1: pretty much every digital solution you can think of, it

60
00:03:32,080 --> 00:03:36,400
Speaker 1: all revolves around data. How can farmers collect more information

61
00:03:36,440 --> 00:03:39,840
Speaker 1: about their land, their soil and make reliable predictions of

62
00:03:39,840 --> 00:03:44,240
Speaker 1: future harvests? To better anticipate contract negotiations or better manage

63
00:03:44,280 --> 00:03:47,280
Speaker 1: their farms. She spoke of an approach in which a

64
00:03:47,320 --> 00:03:49,960
Speaker 1: farmer would use a tractor with embedded sensors in it

65
00:03:50,080 --> 00:03:52,520
Speaker 1: to till the land. The tractor would be doing its

66
00:03:52,880 --> 00:03:57,400
Speaker 1: normal tractory duties while simultaneously creating a digital map of

67
00:03:57,440 --> 00:04:00,720
Speaker 1: the farmland itself, so that now there's a digital representation

68
00:04:00,760 --> 00:04:03,800
Speaker 1: of the farm. Feeding the information to IBM S Watson

69
00:04:03,840 --> 00:04:07,840
Speaker 1: for Agriculture Platform would allow for meaningful use of that data.

70
00:04:08,000 --> 00:04:10,760
Speaker 1: Watson can take that information and combine it with other

71
00:04:10,880 --> 00:04:15,000
Speaker 1: sources to make predictions about future yields and give farmers

72
00:04:15,080 --> 00:04:17,880
Speaker 1: ideas about the conditions of their land. It can also

73
00:04:18,400 --> 00:04:22,000
Speaker 1: analyze the data to estimate what past yields might have been.

74
00:04:22,400 --> 00:04:24,359
Speaker 1: And you might wonder, why would you ever need to

75
00:04:24,440 --> 00:04:27,120
Speaker 1: know what has already happened. Why would you need to

76
00:04:27,279 --> 00:04:31,040
Speaker 1: estimate a past yield? It becomes really important in cases

77
00:04:31,080 --> 00:04:34,120
Speaker 1: where a farmer has to file an insurance claim. It

78
00:04:34,240 --> 00:04:37,360
Speaker 1: helps justify that insurance claim. If the farmer says that,

79
00:04:37,480 --> 00:04:40,440
Speaker 1: due to whatever reason, the yield was a certain size

80
00:04:40,839 --> 00:04:43,040
Speaker 1: and the data backs that up, it can help the

81
00:04:43,080 --> 00:04:46,120
Speaker 1: farmer get that insurance claim and it also helps build

82
00:04:46,160 --> 00:04:50,040
Speaker 1: out models that will increase efficiency further down the supply chain.

83
00:04:51,080 --> 00:04:54,560
Speaker 1: Mutahi also talked about a cool analytical tool called the

84
00:04:54,640 --> 00:04:57,800
Speaker 1: IBM Argo Pod. This is a great example of an

85
00:04:57,839 --> 00:05:00,840
Speaker 1: Internet of Things device. It's about the size and shape

86
00:05:00,960 --> 00:05:04,280
Speaker 1: of a regular business card. Embedded in the card are

87
00:05:04,360 --> 00:05:07,640
Speaker 1: sensors that can do soil analysis, and a farmer just

88
00:05:07,680 --> 00:05:09,599
Speaker 1: needs to put a small sample of soil on the

89
00:05:09,640 --> 00:05:12,880
Speaker 1: card and chemical reactions will tell the sensor everything it

90
00:05:12,920 --> 00:05:15,520
Speaker 1: needs to know in just ten seconds, and then the

91
00:05:15,520 --> 00:05:18,000
Speaker 1: farmer can take a picture of the card using a

92
00:05:18,120 --> 00:05:21,640
Speaker 1: smartphone and use a related app to store the information

93
00:05:21,720 --> 00:05:24,640
Speaker 1: into a blockchain record. This doesn't just tell the farmer

94
00:05:24,680 --> 00:05:26,880
Speaker 1: of the conditions on the farm, it can also help

95
00:05:26,920 --> 00:05:30,680
Speaker 1: the farmer establish credit because a bank could extend credit

96
00:05:30,720 --> 00:05:34,600
Speaker 1: to a farm against a predicted harvest that's based on

97
00:05:34,640 --> 00:05:37,680
Speaker 1: this collected information. So for farmers all over the world,

98
00:05:37,680 --> 00:05:41,560
Speaker 1: this could be an enormous help. Mutahi then handed the

99
00:05:41,560 --> 00:05:44,640
Speaker 1: stage over to Shri ram rug Hoven. He is the

100
00:05:44,800 --> 00:05:48,640
Speaker 1: Vice president and chief Technical Officer of IBM Research in India.

101
00:05:48,880 --> 00:05:53,719
Speaker 1: He shared a pretty staggering pair of facts. One third

102
00:05:53,880 --> 00:05:57,920
Speaker 1: of all food produced and nearly half of all fruits

103
00:05:57,920 --> 00:06:02,600
Speaker 1: and vegetables never get assumed. It just goes to waste.

104
00:06:03,000 --> 00:06:06,920
Speaker 1: So imagine if half of your work was immediately dismissed.

105
00:06:07,120 --> 00:06:09,240
Speaker 1: You still had to do the work, but you know

106
00:06:09,520 --> 00:06:13,480
Speaker 1: that half of it wouldn't count. That would be frustrating

107
00:06:13,640 --> 00:06:16,000
Speaker 1: for most jobs, but when it comes to food production,

108
00:06:16,040 --> 00:06:19,200
Speaker 1: it can lead to waste management problems at best, and

109
00:06:19,440 --> 00:06:23,000
Speaker 1: at worst you could be facing starvation issues. So what

110
00:06:23,320 --> 00:06:25,919
Speaker 1: is the challenge here? Is this just a case of

111
00:06:26,000 --> 00:06:29,960
Speaker 1: some places having more food than the population can consume. Well,

112
00:06:30,000 --> 00:06:33,520
Speaker 1: it's actually a lot more complicated than that. The food

113
00:06:33,560 --> 00:06:37,240
Speaker 1: supply chain is a big issue. There are many points

114
00:06:37,279 --> 00:06:41,159
Speaker 1: along a supply chain, and at every stage spoilage can

115
00:06:41,240 --> 00:06:44,599
Speaker 1: and does occur, So there's a decent chance that a

116
00:06:44,640 --> 00:06:46,560
Speaker 1: lot of food will be spoiled before it can ever

117
00:06:46,640 --> 00:06:50,040
Speaker 1: find its way onto a market shelf. From the fields

118
00:06:50,279 --> 00:06:54,599
Speaker 1: to the storage facilities, to transportation vehicles to distribution centers,

119
00:06:54,600 --> 00:06:57,280
Speaker 1: to processors to shops to the home, there are a

120
00:06:57,320 --> 00:07:00,640
Speaker 1: lot of stops along the way, and presently this is

121
00:07:00,800 --> 00:07:04,240
Speaker 1: largely a dumb system, meaning there's no real way to

122
00:07:04,279 --> 00:07:07,800
Speaker 1: gather information and share it along the supply chain. So

123
00:07:07,920 --> 00:07:10,560
Speaker 1: if you receive a creative apples in a distribution center

124
00:07:10,600 --> 00:07:14,320
Speaker 1: that are maybe two days away from being at peak ripeness,

125
00:07:14,480 --> 00:07:17,000
Speaker 1: but you have no way of knowing that information. When

126
00:07:17,040 --> 00:07:19,120
Speaker 1: you've got the crate, you might put that create on

127
00:07:19,160 --> 00:07:21,160
Speaker 1: a truck that's going across the country, and by the

128
00:07:21,160 --> 00:07:24,119
Speaker 1: time the apples get to their destination, a large number

129
00:07:24,160 --> 00:07:26,120
Speaker 1: of them have already passed their prime and they just

130
00:07:26,200 --> 00:07:30,240
Speaker 1: get thrown out. So what's the solution to this problem.

131
00:07:30,280 --> 00:07:32,560
Speaker 1: The proposal we heard is that you would take a

132
00:07:32,600 --> 00:07:37,000
Speaker 1: combination of technologies, and that includes the Internet of things, blockchain,

133
00:07:37,120 --> 00:07:39,920
Speaker 1: and artificial intelligence in order to keep track of everything

134
00:07:39,960 --> 00:07:42,920
Speaker 1: and make decisions. The Internet of things and the blockchain

135
00:07:43,120 --> 00:07:46,880
Speaker 1: combined could log each stage of the journey the food

136
00:07:46,920 --> 00:07:49,960
Speaker 1: takes from field to the market and keep track on

137
00:07:50,000 --> 00:07:52,560
Speaker 1: the freshness of the food. There would be a record

138
00:07:52,840 --> 00:07:57,080
Speaker 1: for each crate or palette or whatever unit of food

139
00:07:57,400 --> 00:08:00,880
Speaker 1: that could record when it arrived and when it each point,

140
00:08:01,240 --> 00:08:03,880
Speaker 1: and you could understand quickly how much time had passed

141
00:08:04,120 --> 00:08:07,480
Speaker 1: since it was harvested. AI could help guide the decision

142
00:08:07,520 --> 00:08:10,280
Speaker 1: making process when it comes to deciding where do you

143
00:08:10,360 --> 00:08:13,280
Speaker 1: send this next. So the example we heard in the

144
00:08:13,320 --> 00:08:17,520
Speaker 1: presentation involved oranges, and here's how it goes. Let's say

145
00:08:17,560 --> 00:08:20,800
Speaker 1: that you run a distribution center in Florida near where

146
00:08:20,800 --> 00:08:24,320
Speaker 1: oranges are grown. So farmers oranges come into your distribution center,

147
00:08:24,360 --> 00:08:26,600
Speaker 1: and it's your job to send those oranges out to

148
00:08:27,240 --> 00:08:30,720
Speaker 1: UH stores in various cities. And the two main cities

149
00:08:30,840 --> 00:08:34,520
Speaker 1: under your responsibility are Atlanta and Chicago. And as it

150
00:08:34,520 --> 00:08:38,320
Speaker 1: turns out, in Atlanta, people are hog wild for these oranges.

151
00:08:38,360 --> 00:08:40,200
Speaker 1: And I can confirm that because at least from this

152
00:08:40,240 --> 00:08:43,319
Speaker 1: Atlanta's point of view, this is accurate. But in Chicago,

153
00:08:43,880 --> 00:08:46,920
Speaker 1: oranges for some reason just aren't moving nearly so fast

154
00:08:47,040 --> 00:08:50,360
Speaker 1: from the produce section. With access to this information, the

155
00:08:50,400 --> 00:08:53,520
Speaker 1: AI can make decisions. Oranges that still have a really

156
00:08:53,520 --> 00:08:56,480
Speaker 1: long time to ripen could be sent to Chicago because

157
00:08:56,720 --> 00:08:59,000
Speaker 1: they could sit in refrigeration a bit longer. They could

158
00:08:59,000 --> 00:09:02,080
Speaker 1: remain fresh while the inhabitants of the Windy City decide

159
00:09:02,120 --> 00:09:05,480
Speaker 1: they finally want to fight off scurvy. Oranges that are

160
00:09:05,559 --> 00:09:08,640
Speaker 1: close to passing prime ripeness can make the shorter trip

161
00:09:08,679 --> 00:09:11,320
Speaker 1: to Atlanta, where they are more likely to be purchased

162
00:09:11,360 --> 00:09:16,480
Speaker 1: and consumed quickly. The distributor can maximize efficiency and minimize waste.

163
00:09:16,960 --> 00:09:19,200
Speaker 1: Now next we're going to hear about a proposal that

164
00:09:19,400 --> 00:09:22,840
Speaker 1: is all about food safety. But first let's take a

165
00:09:22,920 --> 00:09:33,240
Speaker 1: quick break. The third presenter in the five and five

166
00:09:33,280 --> 00:09:37,280
Speaker 1: event was Gerroud Dubois, director of IBM research at Almondon.

167
00:09:37,640 --> 00:09:41,240
Speaker 1: Dubois began his presentation by talking about a catastrophe in

168
00:09:41,360 --> 00:09:44,800
Speaker 1: China in two thousand and eight. A shipment of baby

169
00:09:44,880 --> 00:09:49,079
Speaker 1: formula had been contaminated with a chemical called Melman. This

170
00:09:49,280 --> 00:09:52,920
Speaker 1: is an industrial chemical that manufacturers used to treat stuff

171
00:09:52,960 --> 00:09:56,480
Speaker 1: like ceramics and plastics. It is used in glue, in

172
00:09:56,600 --> 00:10:00,520
Speaker 1: flame retardants, and laminates. It is not, as you might imagine,

173
00:10:01,000 --> 00:10:04,680
Speaker 1: meant for consumption. Parents who fed their babies this formula

174
00:10:04,800 --> 00:10:07,559
Speaker 1: quickly became alarmed when the babies began to get sick.

175
00:10:08,120 --> 00:10:11,800
Speaker 1: Melman can cause kidney damage and Chinese hospitals had to

176
00:10:11,840 --> 00:10:16,000
Speaker 1: admit more than fifty thousand babies. And even darker part

177
00:10:16,000 --> 00:10:18,120
Speaker 1: of the story is that the addition of the chemical

178
00:10:18,720 --> 00:10:22,280
Speaker 1: was likely intentional. The chemical makes it appear that the formula,

179
00:10:22,320 --> 00:10:25,440
Speaker 1: when combined with milk, is more protein rich than it

180
00:10:25,600 --> 00:10:31,080
Speaker 1: actually is, so it was an attempt at deception. So

181
00:10:31,120 --> 00:10:35,960
Speaker 1: that's even more disturbing. Well, du Bois proposed that we

182
00:10:36,280 --> 00:10:40,680
Speaker 1: rely upon microbes as a sort of microscopic canary in

183
00:10:40,679 --> 00:10:43,839
Speaker 1: a coal mine, or as he called it, a microscopic

184
00:10:44,160 --> 00:10:48,319
Speaker 1: c I a agent, and it would detect when contaminants

185
00:10:48,320 --> 00:10:50,840
Speaker 1: are present in food products. And a microbe is a

186
00:10:50,880 --> 00:10:55,040
Speaker 1: micro organism. Bacteria are a type of microbe, and you've

187
00:10:55,120 --> 00:10:59,360
Speaker 1: likely used stuff like antimicrobial products to help sanitize stuff,

188
00:10:59,640 --> 00:11:02,200
Speaker 1: and this could give you the implication that microbes are

189
00:11:02,240 --> 00:11:05,480
Speaker 1: bad and some are definitely harmful to us, but some

190
00:11:05,640 --> 00:11:08,880
Speaker 1: microbes are beneficial. And the human body is host to

191
00:11:09,160 --> 00:11:14,560
Speaker 1: almost actually slightly more microbial cells than human cells. The

192
00:11:14,640 --> 00:11:18,040
Speaker 1: ratio appears to be somewhere around one point three bacterial

193
00:11:18,120 --> 00:11:21,080
Speaker 1: cells to every human cell, so you could say that

194
00:11:21,160 --> 00:11:25,000
Speaker 1: you're more bacteria than person, though that's not really the point.

195
00:11:25,040 --> 00:11:29,240
Speaker 1: Our microbial biome or biota is actually part of us,

196
00:11:29,240 --> 00:11:32,040
Speaker 1: so I would say we are collectively made of both

197
00:11:32,080 --> 00:11:37,240
Speaker 1: bacteria and human cells. We are bored, I guess. Anyway,

198
00:11:37,720 --> 00:11:40,080
Speaker 1: Not all microbes are bad. Some are very helpful and

199
00:11:40,120 --> 00:11:45,640
Speaker 1: they aid us in digesting certain materials, so some are

200
00:11:45,679 --> 00:11:48,280
Speaker 1: good and we should rely upon those. Do Boa proposes

201
00:11:48,320 --> 00:11:51,640
Speaker 1: we could use microbes to detect the presence of contaminants

202
00:11:51,679 --> 00:11:54,360
Speaker 1: and food. So for a long time, scientists thought that

203
00:11:54,440 --> 00:11:57,719
Speaker 1: the behaviors of microbes were too complex and unpredictable to

204
00:11:57,760 --> 00:12:01,839
Speaker 1: reveal meaningful information, that it was almost random. But by

205
00:12:01,840 --> 00:12:04,800
Speaker 1: studying them at a genetic level, looking at the d

206
00:12:04,960 --> 00:12:08,000
Speaker 1: n A and the RNA of microbes, we've gathered a

207
00:12:08,040 --> 00:12:11,240
Speaker 1: lot more information that reveals microbes react in different ways

208
00:12:11,400 --> 00:12:14,800
Speaker 1: to different conditions. To make that determination, we had to

209
00:12:14,920 --> 00:12:19,319
Speaker 1: use a big data approach. Dubai used a helpful analogy

210
00:12:19,400 --> 00:12:23,440
Speaker 1: to describe how challenging this process really was. So imagine

211
00:12:23,480 --> 00:12:28,319
Speaker 1: you have ten thousand boxes of jigsaw puzzles. They're different puzzles,

212
00:12:28,360 --> 00:12:31,680
Speaker 1: and you dump all the pieces out into one enormous pile.

213
00:12:31,760 --> 00:12:33,640
Speaker 1: You mix them up real good, then you throw the

214
00:12:33,679 --> 00:12:36,120
Speaker 1: boxes away, so you don't even have the record of

215
00:12:36,160 --> 00:12:38,360
Speaker 1: what the pictures look like, and now it's your job

216
00:12:38,400 --> 00:12:42,240
Speaker 1: to put together those ten thousand puzzles. That's sort of

217
00:12:42,280 --> 00:12:44,400
Speaker 1: the scale of the job we had to do to

218
00:12:44,520 --> 00:12:48,920
Speaker 1: suss out how microbes behave given different conditions. At IBM,

219
00:12:49,000 --> 00:12:52,520
Speaker 1: the research team created a database containing all the microbial

220
00:12:52,640 --> 00:12:56,439
Speaker 1: genomes the scientific world has mapped so far. The genomes

221
00:12:56,480 --> 00:13:00,960
Speaker 1: and the analysis of microbial behavior represents around five hundred

222
00:13:01,160 --> 00:13:04,920
Speaker 1: terabytes of data. But the process was successful and that

223
00:13:05,000 --> 00:13:08,360
Speaker 1: there are microbial behaviors that can indicate the presence of

224
00:13:08,400 --> 00:13:11,520
Speaker 1: contaminants in our food. You have to know which microbes

225
00:13:11,559 --> 00:13:15,760
Speaker 1: you're looking for and what behaviors indicates safe versus unsafe food.

226
00:13:15,920 --> 00:13:17,960
Speaker 1: But it could add a new method for food safety

227
00:13:17,960 --> 00:13:20,199
Speaker 1: inspectors to use to guarantee that the products that make

228
00:13:20,240 --> 00:13:24,520
Speaker 1: it to consumers are actually safe to consume. Du Bois

229
00:13:24,520 --> 00:13:28,360
Speaker 1: then introduced us to Donna Dillenberger and IBM Fellow at

230
00:13:28,360 --> 00:13:31,000
Speaker 1: the Thomas J. Watson Research Center. Now, I mentioned in

231
00:13:31,040 --> 00:13:34,520
Speaker 1: an earlier episode that the title of IBM Fellow is

232
00:13:34,559 --> 00:13:39,520
Speaker 1: the highest honor IBM bestows on distinguished researchers, scientists, engineers,

233
00:13:39,520 --> 00:13:43,520
Speaker 1: and the like. Dillenberger also talked about food safety. She

234
00:13:43,679 --> 00:13:46,640
Speaker 1: cited a CDC report that I tracked down. The report

235
00:13:46,720 --> 00:13:50,760
Speaker 1: is the Emerging Infectious Diseases Report, and the section Dillenberger

236
00:13:50,840 --> 00:13:54,319
Speaker 1: was specifically referencing is chapter five of that report titled

237
00:13:54,440 --> 00:13:57,920
Speaker 1: food Related Illness and Death in the United States. Now,

238
00:13:57,920 --> 00:14:01,120
Speaker 1: I'm going to quote the abstract of that report verbatim.

239
00:14:01,200 --> 00:14:04,760
Speaker 1: Here's part of that abstract. We estimate that food born

240
00:14:04,840 --> 00:14:09,840
Speaker 1: diseases cause approximately seventy six million illnesses, three hundred twenty

241
00:14:09,840 --> 00:14:14,079
Speaker 1: five thousand hospitalizations, and five thousand deaths in the United

242
00:14:14,120 --> 00:14:18,120
Speaker 1: States each year. Known pathogens account for an estimated fourteen

243
00:14:18,160 --> 00:14:23,600
Speaker 1: million illnesses, sixty thousand hospitalizations, and eighteen hundred deaths. Three

244
00:14:23,680 --> 00:14:29,480
Speaker 1: pathogens Salmonella, listeria, and toxoplasma, are responsible for fifteen hundred

245
00:14:29,480 --> 00:14:32,960
Speaker 1: deaths each year, more than seventy of those caused by

246
00:14:33,040 --> 00:14:36,960
Speaker 1: known pathogens, while unknown agents account for the remaining sixty

247
00:14:36,960 --> 00:14:41,520
Speaker 1: two million illnesses, two hundred sixty five thousand hospitalizations, and

248
00:14:41,640 --> 00:14:45,120
Speaker 1: three thousand, two hundred deaths. Overall, food born diseases appear

249
00:14:45,200 --> 00:14:48,840
Speaker 1: to cause more illnesses but fewer deaths than previously estimated.

250
00:14:49,360 --> 00:14:52,440
Speaker 1: End quote. Now, fewer deaths is a good thing, but

251
00:14:52,680 --> 00:14:55,880
Speaker 1: even fewer would be better, And the huge number of

252
00:14:55,880 --> 00:15:00,120
Speaker 1: illnesses represents not just discomfort, stress, anxiety, at a or

253
00:15:00,280 --> 00:15:03,280
Speaker 1: quality of life. There's a ripple effect. The hits society

254
00:15:03,280 --> 00:15:06,320
Speaker 1: as a whole in ways like lost productivity or additional

255
00:15:06,360 --> 00:15:09,920
Speaker 1: burden on the medical industry. So how can we tell

256
00:15:10,280 --> 00:15:12,880
Speaker 1: if the food we buy is safe to eat? The

257
00:15:12,920 --> 00:15:16,960
Speaker 1: bacteria responsible are microscopic, As I mentioned, just a moment ago.

258
00:15:17,160 --> 00:15:19,280
Speaker 1: We're not likely to have a lab set up in

259
00:15:19,320 --> 00:15:24,240
Speaker 1: our kitchens. Dyllenberger introduced a hardware and software tool that

260
00:15:24,280 --> 00:15:27,880
Speaker 1: could actually help. The hardware component is a smartphone peripheral.

261
00:15:28,040 --> 00:15:30,760
Speaker 1: It's essentially a microscope that plugs into your smartphone and

262
00:15:30,800 --> 00:15:33,920
Speaker 1: feeds a magnified image to the phone's camera sensor. The

263
00:15:34,000 --> 00:15:37,560
Speaker 1: software side is an analysis tool using AI and image

264
00:15:37,560 --> 00:15:41,960
Speaker 1: recognition strategies to identify bacteria present in food. The results

265
00:15:42,000 --> 00:15:44,800
Speaker 1: of the analysis pop up on the screen as shapes

266
00:15:44,920 --> 00:15:48,000
Speaker 1: around the bacteria, and the type and color of shape

267
00:15:48,240 --> 00:15:52,040
Speaker 1: indicates which kind of bacteria might be present. It can

268
00:15:52,080 --> 00:15:54,440
Speaker 1: scan down to the micron scale and let you know

269
00:15:54,520 --> 00:15:57,000
Speaker 1: if the food you have is safe to eat or

270
00:15:57,040 --> 00:15:59,880
Speaker 1: if it is host to say, a colony of eke

271
00:16:00,000 --> 00:16:03,880
Speaker 1: to lie. Dillenberger also revealed that the same technology could

272
00:16:03,880 --> 00:16:08,000
Speaker 1: be used to help discover food counterfeits, and yes, that

273
00:16:08,200 --> 00:16:11,560
Speaker 1: is a thing. In fact, it's a big thing. Dillenberger

274
00:16:11,600 --> 00:16:14,360
Speaker 1: referred to a study that found in the United States,

275
00:16:14,440 --> 00:16:18,320
Speaker 1: olive oil producers weren't always being totally honest, or at

276
00:16:18,360 --> 00:16:21,720
Speaker 1: least they weren't meeting the right standards. Because a study

277
00:16:21,760 --> 00:16:26,000
Speaker 1: in two found that seventy of the bottles of labeled

278
00:16:26,080 --> 00:16:30,000
Speaker 1: extra virgin olive oil actually failed to meet the standards

279
00:16:30,000 --> 00:16:33,240
Speaker 1: to qualify as extra virgin. You wouldn't be able to

280
00:16:33,280 --> 00:16:36,640
Speaker 1: tell the casual glance the difference between regular olive oil

281
00:16:36,680 --> 00:16:39,320
Speaker 1: and good old e v O O, but the scanner

282
00:16:39,360 --> 00:16:42,120
Speaker 1: and paired software can analyze the reflected light from a

283
00:16:42,120 --> 00:16:44,840
Speaker 1: sample of olive oil and determine whether or not it

284
00:16:44,920 --> 00:16:48,240
Speaker 1: matches the real deal or not. The same tech can

285
00:16:48,280 --> 00:16:50,960
Speaker 1: help you figure out if a label is legitimate or

286
00:16:50,960 --> 00:16:53,800
Speaker 1: if it's a clever fake. And it doesn't stop with food,

287
00:16:54,080 --> 00:16:56,160
Speaker 1: though that was the primary focus of the five and

288
00:16:56,240 --> 00:16:58,760
Speaker 1: five presentation, the scanner could also be used to sort

289
00:16:58,760 --> 00:17:01,440
Speaker 1: out the real McCoy from fakers and all sorts of products,

290
00:17:01,480 --> 00:17:06,640
Speaker 1: from fashion accessories to prescription drugs. Moreover, Dylan Berger said

291
00:17:06,640 --> 00:17:10,640
Speaker 1: that while the present implementation uses a smartphone, future versions

292
00:17:10,640 --> 00:17:14,560
Speaker 1: could see embedded sensors integrated into common kitchen tools like

293
00:17:14,720 --> 00:17:18,800
Speaker 1: cutting boards or knives or measuring cups or bowls, and

294
00:17:18,840 --> 00:17:22,320
Speaker 1: by looking for not just authenticity, but for the presence

295
00:17:22,359 --> 00:17:26,840
Speaker 1: of potential pathogens, we could improve our fine dining experience

296
00:17:26,920 --> 00:17:30,960
Speaker 1: and also prevent cases of food poisoning. Next, we're gonna

297
00:17:31,040 --> 00:17:34,040
Speaker 1: learn a little bit about the conclusion of the five

298
00:17:34,080 --> 00:17:37,160
Speaker 1: and five event and what we might do with some

299
00:17:37,320 --> 00:17:40,920
Speaker 1: of the plastic waste we generate. But first let's take

300
00:17:41,080 --> 00:17:51,440
Speaker 1: a quick break. The final presenter at five and five

301
00:17:51,560 --> 00:17:54,240
Speaker 1: was Jeanette Garcia, who has one of the most kick

302
00:17:54,320 --> 00:17:58,440
Speaker 1: ass titles I have ever seen. It's Master Inventor at

303
00:17:58,440 --> 00:18:03,080
Speaker 1: IBM Research Almada. She helped put into perspective exactly how

304
00:18:03,119 --> 00:18:06,159
Speaker 1: big a problem plastic waste has become, and it is

305
00:18:06,320 --> 00:18:10,920
Speaker 1: a huge problem. The world produces around three hundred million

306
00:18:11,200 --> 00:18:14,959
Speaker 1: tons of plastic every year, and about half of that

307
00:18:15,000 --> 00:18:17,679
Speaker 1: plastic is in the form of stuff that's intended for

308
00:18:17,840 --> 00:18:21,600
Speaker 1: single use, meaning we just toss it out afterward. Lots

309
00:18:21,680 --> 00:18:25,960
Speaker 1: of communities are now recycling, but sadly, only a small fraction,

310
00:18:26,160 --> 00:18:30,640
Speaker 1: about ten per cent of plastic gets recycled. So why

311
00:18:30,800 --> 00:18:33,960
Speaker 1: is that, Well, there are a few reasons. One is

312
00:18:34,000 --> 00:18:36,639
Speaker 1: that there are different types of plastics and they can't

313
00:18:36,680 --> 00:18:39,679
Speaker 1: all be processed in the same way, which means they

314
00:18:39,720 --> 00:18:43,040
Speaker 1: have to be sorted into different categories. That takes effort

315
00:18:43,080 --> 00:18:46,400
Speaker 1: and time, which also means it costs money. There are

316
00:18:46,440 --> 00:18:50,000
Speaker 1: contaminants that can be a problem particularly food waste, and

317
00:18:50,040 --> 00:18:52,600
Speaker 1: Garcia mentioned that we often don't know what the rules

318
00:18:52,640 --> 00:18:55,000
Speaker 1: are are we supposed to rinse off the plastic. First,

319
00:18:55,359 --> 00:18:58,240
Speaker 1: some types of plastic aren't recyclable at all, And then

320
00:18:58,280 --> 00:19:01,280
Speaker 1: there's the problem of economics. Pastic is pretty easy stuff

321
00:19:01,320 --> 00:19:04,880
Speaker 1: to manufacture. If it costs more money to recycle plastic

322
00:19:05,119 --> 00:19:07,720
Speaker 1: than it does to just make new plastic, you have

323
00:19:07,760 --> 00:19:11,080
Speaker 1: to come up with some other economic incentives to encourage recycling.

324
00:19:11,680 --> 00:19:14,960
Speaker 1: At the same time, plastic is undeniably useful stuff. We

325
00:19:15,000 --> 00:19:17,359
Speaker 1: rely on it for lots of things, not the least

326
00:19:17,400 --> 00:19:20,119
Speaker 1: of which is food packaging. It's hard to dismiss how

327
00:19:20,119 --> 00:19:23,760
Speaker 1: important plastic is in keeping our foods fresher longer, which

328
00:19:23,800 --> 00:19:26,760
Speaker 1: goes back to cutting down food waste. So how do

329
00:19:26,880 --> 00:19:31,080
Speaker 1: we resolve the problem. The specific type of plastic Garcia

330
00:19:31,160 --> 00:19:35,119
Speaker 1: talked about was pet or pet plastic, which is found

331
00:19:35,119 --> 00:19:38,400
Speaker 1: not only in packaging but also stuff like polyester clothing.

332
00:19:39,640 --> 00:19:42,760
Speaker 1: The seventies, this is the type of plastic used in

333
00:19:42,800 --> 00:19:45,600
Speaker 1: stuff like water and soda bottles. If you look at

334
00:19:45,600 --> 00:19:48,960
Speaker 1: a bottle made from pet, you'll see the chasing arrows

335
00:19:49,119 --> 00:19:51,920
Speaker 1: sign with the number one at the center. It makes

336
00:19:52,000 --> 00:19:54,360
Speaker 1: up a lot of plastic, but I should point out

337
00:19:54,400 --> 00:19:57,359
Speaker 1: that it's also the most recycled type of plastic in

338
00:19:57,400 --> 00:20:01,560
Speaker 1: the world. PET is completely recy cyclable. The United States

339
00:20:01,640 --> 00:20:04,760
Speaker 1: lags behind Europe when it comes to recycling PET plastic.

340
00:20:05,000 --> 00:20:07,760
Speaker 1: We in the US recycle a little more than of

341
00:20:07,760 --> 00:20:11,760
Speaker 1: PT plastic, while Europe is over the line, but we

342
00:20:11,800 --> 00:20:14,480
Speaker 1: can always do better. One of the methods we rely

343
00:20:14,600 --> 00:20:17,159
Speaker 1: upon to recycle this type of plastic is to wash

344
00:20:17,200 --> 00:20:21,040
Speaker 1: the plastic and then melt it down. Another version uses

345
00:20:21,119 --> 00:20:25,160
Speaker 1: chemicals to depolymerize the plastic. Polymer is a long chain

346
00:20:25,160 --> 00:20:29,320
Speaker 1: of molecules, so this approach effectively breaks those chains down.

347
00:20:29,760 --> 00:20:33,400
Speaker 1: But the melting process has a zero tolerance for contamination,

348
00:20:33,520 --> 00:20:35,920
Speaker 1: meaning the only stuff that can get melted down is

349
00:20:35,960 --> 00:20:39,240
Speaker 1: the plastic itself. Any other stuff will foul the melted

350
00:20:39,320 --> 00:20:42,119
Speaker 1: mixture and make it unusable. It also only works with

351
00:20:42,200 --> 00:20:45,639
Speaker 1: clear bottles. The chemical approach has its own drawbacks, a

352
00:20:45,640 --> 00:20:48,680
Speaker 1: big one being the cost of the process, which creates

353
00:20:48,680 --> 00:20:52,800
Speaker 1: that economic barrier I mentioned earlier. IBM solution is called

354
00:20:52,960 --> 00:20:56,880
Speaker 1: volcat which stands for volatile catalyst. So what the heck

355
00:20:56,960 --> 00:20:59,960
Speaker 1: does that mean? A catalyst is a substance that facility.

356
00:21:00,040 --> 00:21:03,080
Speaker 1: It's a chemical reaction. You would typically use a catalyst

357
00:21:03,160 --> 00:21:05,640
Speaker 1: to speed up a process that would otherwise take much

358
00:21:05,680 --> 00:21:09,800
Speaker 1: longer to complete. Catalysts do this without undergoing permanent chemical

359
00:21:09,920 --> 00:21:14,800
Speaker 1: changes themselves. They're incredibly useful in hundreds of different industrial applications.

360
00:21:15,240 --> 00:21:19,000
Speaker 1: With the volecat approach, IBM could grind up pet plastic

361
00:21:19,080 --> 00:21:21,960
Speaker 1: into flakes, and it wouldn't matter if the plastic was

362
00:21:22,040 --> 00:21:24,159
Speaker 1: clear or had color added to it, or if it

363
00:21:24,200 --> 00:21:27,360
Speaker 1: was clean or if it was dirty. With volcat, IBM

364
00:21:27,400 --> 00:21:30,240
Speaker 1: takes that plastic and puts it into a heating chamber.

365
00:21:30,480 --> 00:21:33,000
Speaker 1: The chamber heats the plastic up to about a hundred

366
00:21:33,040 --> 00:21:36,560
Speaker 1: nine degrees celsius or three seventy four degrees fahrenheit. At

367
00:21:36,600 --> 00:21:40,000
Speaker 1: that point researchers add the catalyst. Then they cool the

368
00:21:40,040 --> 00:21:42,840
Speaker 1: mixture down to get below one hundred degrees celsius or

369
00:21:42,880 --> 00:21:45,800
Speaker 1: two hundred twelve degrees fahrenheit. That's the temperature which water

370
00:21:45,880 --> 00:21:49,440
Speaker 1: boils under one atmosphere of pressure. The plastic polymers break

371
00:21:49,480 --> 00:21:52,679
Speaker 1: down into a more basic molecular form called B H

372
00:21:52,800 --> 00:21:55,240
Speaker 1: E T, which is a monomer. And you can think

373
00:21:55,240 --> 00:21:58,360
Speaker 1: of a monomer as a molecule that forms the basic

374
00:21:58,480 --> 00:22:03,639
Speaker 1: component of a polymer identical monomers linked together to form polymers.

375
00:22:03,680 --> 00:22:06,760
Speaker 1: So now you've got what is effectively the building blocks

376
00:22:06,920 --> 00:22:11,240
Speaker 1: of PET. The volatile catalyst is completely recoverable and IBM

377
00:22:11,240 --> 00:22:14,320
Speaker 1: engineers can filter the b ET from any other stuff

378
00:22:14,400 --> 00:22:16,359
Speaker 1: that was in the mix. The b h g T

379
00:22:16,520 --> 00:22:19,440
Speaker 1: can go on to form new pet containers, So we

380
00:22:19,480 --> 00:22:22,720
Speaker 1: could keep using the same plastic over and over again

381
00:22:22,800 --> 00:22:25,719
Speaker 1: without the need to make more of the stuff, and

382
00:22:25,760 --> 00:22:28,960
Speaker 1: should our demand for plastic exceed that amount, we could

383
00:22:29,000 --> 00:22:33,680
Speaker 1: literally mine the Pacific garbage patch and landfills for more material.

384
00:22:34,080 --> 00:22:39,240
Speaker 1: The process sounds incredibly promising and increasing recycling rates, particularly

385
00:22:39,280 --> 00:22:41,639
Speaker 1: for plastics that are dirty or have color added to

386
00:22:41,680 --> 00:22:44,960
Speaker 1: the plastic material. Since the process removes the need to

387
00:22:45,000 --> 00:22:48,280
Speaker 1: clean the plastic first, it could reduce the recycling workload.

388
00:22:48,520 --> 00:22:51,199
Speaker 1: If it is scalable, it could be a viable alternative

389
00:22:51,200 --> 00:22:55,040
Speaker 1: to the present approaches to plastic recycling. These research projects

390
00:22:55,040 --> 00:22:57,400
Speaker 1: were all really interesting to me, and they are all

391
00:22:57,440 --> 00:23:00,720
Speaker 1: trying to make big changes in the entire food life cycle.

392
00:23:01,119 --> 00:23:04,240
Speaker 1: It's a truly enormous challenge and there's still more to

393
00:23:04,320 --> 00:23:09,040
Speaker 1: work on developing technologies to reduce water waste, improve transportation

394
00:23:09,040 --> 00:23:12,959
Speaker 1: and distribution deal with other types of waste, and guaranteeing

395
00:23:13,040 --> 00:23:15,600
Speaker 1: everyone in the world has access to healthy and safe

396
00:23:15,680 --> 00:23:20,040
Speaker 1: food is a monumental effort. These research projects are just

397
00:23:20,119 --> 00:23:22,800
Speaker 1: a few of the ways innovators are looking into making

398
00:23:22,840 --> 00:23:26,160
Speaker 1: a big difference. Will we see each of these ideas

399
00:23:26,200 --> 00:23:28,920
Speaker 1: implemented in the real world. What's a bit early to say,

400
00:23:28,960 --> 00:23:31,879
Speaker 1: but all of those five presenters made a prediction of

401
00:23:31,920 --> 00:23:34,160
Speaker 1: what the world will be like in five years if

402
00:23:34,200 --> 00:23:38,040
Speaker 1: we do further develop, scale and deploy those technologies, and

403
00:23:38,160 --> 00:23:40,960
Speaker 1: it was a pretty good start to fixing some incredibly

404
00:23:41,080 --> 00:23:44,480
Speaker 1: tough problems. Research will continue to play a huge part

405
00:23:44,560 --> 00:23:48,040
Speaker 1: at IBM. It's ingrained in the company's culture. Much of

406
00:23:48,080 --> 00:23:51,040
Speaker 1: it focuses on the company's core businesses, which is to

407
00:23:51,040 --> 00:23:53,560
Speaker 1: be expected. You can't stay in business if you never

408
00:23:53,600 --> 00:23:56,399
Speaker 1: focus on your services and products. But a lot of

409
00:23:56,440 --> 00:24:00,400
Speaker 1: that work has applications beyond the enterprise world, and it's

410
00:24:00,480 --> 00:24:03,760
Speaker 1: this drive to leverage powerful technologies to make real changes

411
00:24:03,760 --> 00:24:06,600
Speaker 1: out there that I find so interesting. I'd like to

412
00:24:06,640 --> 00:24:08,920
Speaker 1: thank IBM for bringing me out here. It was great

413
00:24:09,000 --> 00:24:13,320
Speaker 1: once again getting to explore and experience the Think Conference.

414
00:24:13,880 --> 00:24:17,480
Speaker 1: I got to see a lot of cool presentations about

415
00:24:17,560 --> 00:24:20,080
Speaker 1: technologies that I was aware of but didn't know very

416
00:24:20,160 --> 00:24:22,800
Speaker 1: much about. And I also really am thankful for the

417
00:24:22,800 --> 00:24:26,600
Speaker 1: opportunity to talk to so many incredible people here at

418
00:24:26,600 --> 00:24:29,960
Speaker 1: the conference and get their perspectives on technology and how

419
00:24:30,000 --> 00:24:32,160
Speaker 1: we might apply it in the future. If you guys

420
00:24:32,240 --> 00:24:35,480
Speaker 1: have any suggestions for future episodes of tech Stuff, contact

421
00:24:35,520 --> 00:24:38,320
Speaker 1: me the email addresses tech Stuff at how stuff works

422
00:24:38,359 --> 00:24:40,840
Speaker 1: dot com, or go to our website that's tech Stuff

423
00:24:40,880 --> 00:24:44,159
Speaker 1: podcast dot com and you can find the ways to

424
00:24:44,240 --> 00:24:46,439
Speaker 1: get in touch with me through social media. There. You

425
00:24:46,440 --> 00:24:49,040
Speaker 1: can also find the link to our merchandise store and

426
00:24:49,080 --> 00:24:57,160
Speaker 1: I will talk to you again really soon for more

427
00:24:57,200 --> 00:24:59,479
Speaker 1: on this and thousands of other topics. Is it how

428
00:24:59,520 --> 00:25:00,520
Speaker 1: Stuff Work Stacom