1 00:00:00,400 --> 00:00:03,520 Speaker 1: This is Dana Perkins and you're listening to Switched on 2 00:00:04,040 --> 00:00:08,600 Speaker 1: the BNF podcast. Pesticides are considered an indispensable part of 3 00:00:08,640 --> 00:00:13,160 Speaker 1: modern agriculture for many farmers. They're used to prevent weeds, insects, 4 00:00:13,200 --> 00:00:16,639 Speaker 1: and fungus from attacking crops and decreasing yields. But the 5 00:00:16,760 --> 00:00:20,320 Speaker 1: use of these chemicals comes at a cost because pesticides 6 00:00:20,360 --> 00:00:23,560 Speaker 1: are a driver of environmental damage and soil pollution, and 7 00:00:23,600 --> 00:00:26,239 Speaker 1: they have been linked to declines in bird and insect 8 00:00:26,280 --> 00:00:30,680 Speaker 1: populations and aquatic biodiversity on today's modern farms. The most 9 00:00:30,680 --> 00:00:34,600 Speaker 1: common way to apply pesticides involves broadcast spraying. This is 10 00:00:34,600 --> 00:00:38,320 Speaker 1: where chemicals are sprayed uniformly over crops, but this method 11 00:00:38,520 --> 00:00:42,280 Speaker 1: is exceptionally inefficient, with ninety five percent of herbicides and 12 00:00:42,479 --> 00:00:48,239 Speaker 1: ninety eight percent of insecticides not actually reaching their intended pest. However, 13 00:00:48,680 --> 00:00:52,080 Speaker 1: new precision delivery technologies could change all of this through 14 00:00:52,120 --> 00:00:55,520 Speaker 1: the use of cameras and artificial intelligence, and it would 15 00:00:55,640 --> 00:00:59,720 Speaker 1: enable green on green sensors to detect and target individual 16 00:00:59,720 --> 00:01:04,000 Speaker 1: weed with pesticides, leaving the other green crops untouched. How 17 00:01:04,000 --> 00:01:07,080 Speaker 1: does this technology work and just how efficient is it? 18 00:01:07,360 --> 00:01:11,240 Speaker 1: And beyond environmental protection, what other benefits does it offer 19 00:01:11,280 --> 00:01:14,640 Speaker 1: to farmers? To find out more, today, I am joined 20 00:01:14,680 --> 00:01:19,920 Speaker 1: by Alexander Littington, an analyst from bnaf's Sustainable Agriculture team. Together, 21 00:01:20,000 --> 00:01:23,679 Speaker 1: we discuss the significance of green on green technology, the 22 00:01:23,720 --> 00:01:27,560 Speaker 1: positive environmental impact it promises, and the potential cost savings 23 00:01:27,560 --> 00:01:31,120 Speaker 1: for farmers. We also discuss the conditions required to use 24 00:01:31,160 --> 00:01:34,800 Speaker 1: these new sensors and whether drones are a viable option, 25 00:01:35,120 --> 00:01:39,480 Speaker 1: And finally, we discuss whether pesticide manufacturers are embracing this 26 00:01:39,640 --> 00:01:45,479 Speaker 1: technological revolution. To access associated BNF research highlighted on today's show, 27 00:01:45,520 --> 00:01:50,320 Speaker 1: including Alex's research note with a terrific title, Precision Pesticide 28 00:01:50,320 --> 00:01:53,880 Speaker 1: Delivery Booming to Spray the Least, you can find it 29 00:01:54,000 --> 00:01:56,800 Speaker 1: on BNF dot com or at BNF go on the 30 00:01:56,800 --> 00:02:00,040 Speaker 1: Bloomberg terminal. If you like this podcast, make sure to 31 00:01:59,880 --> 00:02:02,920 Speaker 1: subscribe or give us a review. But right now, let's 32 00:02:03,000 --> 00:02:18,360 Speaker 1: jump into our conversation with Alex about precision agriculture. Alex, 33 00:02:18,440 --> 00:02:20,799 Speaker 1: thank you very much for joining the show today morning. 34 00:02:20,800 --> 00:02:22,080 Speaker 2: Thank you for having me well. 35 00:02:22,160 --> 00:02:24,240 Speaker 1: Alex is very kindly saying good morning to me, But 36 00:02:24,280 --> 00:02:27,160 Speaker 1: it's actually evening where you are, so I'm located in London, 37 00:02:27,200 --> 00:02:30,400 Speaker 1: you're located in Australia, and we're here to discuss pesticides. 38 00:02:30,680 --> 00:02:32,400 Speaker 1: It would be great if you could give us a 39 00:02:32,400 --> 00:02:34,880 Speaker 1: little bit of context as we head into this regarding 40 00:02:35,400 --> 00:02:38,919 Speaker 1: why we think there might be the opportunity to have 41 00:02:39,200 --> 00:02:44,200 Speaker 1: a breakthrough on being motivated to actually fix the pesticide problem. Because, 42 00:02:44,280 --> 00:02:47,760 Speaker 1: as many people know, in the agriculture space, farming is 43 00:02:47,800 --> 00:02:52,120 Speaker 1: incredibly distributed and so trying to rally behind organized common 44 00:02:52,200 --> 00:02:56,160 Speaker 1: solutions that are centrally managed can be somewhat difficult to do. 45 00:02:56,400 --> 00:02:58,280 Speaker 1: And I think you can give us a little bit 46 00:02:58,320 --> 00:03:02,040 Speaker 1: of context around some of those central sources of motivation 47 00:03:02,440 --> 00:03:04,400 Speaker 1: that are just starting to emerge now. 48 00:03:05,080 --> 00:03:08,160 Speaker 3: So we've got all these new policies emerging, like the 49 00:03:08,160 --> 00:03:12,519 Speaker 3: Global Biodiversity Framework, these big supernational targets to reduce the 50 00:03:12,560 --> 00:03:14,960 Speaker 3: amount of chemical pesticide that we need to apply. And 51 00:03:15,000 --> 00:03:18,040 Speaker 3: this is pretty much the best solution for that, and 52 00:03:18,040 --> 00:03:20,280 Speaker 3: that is to protect nature because obviously all these chemicals 53 00:03:20,360 --> 00:03:22,760 Speaker 3: that leach out and leave the cropping system, they then 54 00:03:22,960 --> 00:03:27,560 Speaker 3: enter the natural environment, They enter organisms, they cause reproductive distress, 55 00:03:27,639 --> 00:03:30,600 Speaker 3: They cause trofic cascade, which is when one species essentially 56 00:03:30,680 --> 00:03:33,480 Speaker 3: falls out of the food web and the whole food 57 00:03:33,600 --> 00:03:35,080 Speaker 3: chain then collapses. 58 00:03:35,560 --> 00:03:36,960 Speaker 1: So it would be great if you could give us 59 00:03:37,000 --> 00:03:40,640 Speaker 1: a little bit of color on the current way we 60 00:03:40,800 --> 00:03:44,040 Speaker 1: are using pesticides in most places in the world so 61 00:03:44,080 --> 00:03:46,320 Speaker 1: that we can understand what it is that actually needs 62 00:03:46,320 --> 00:03:46,920 Speaker 1: to be fixed. 63 00:03:47,480 --> 00:03:50,680 Speaker 3: So agriculture has a trilemma. We need to feed ten 64 00:03:50,760 --> 00:03:54,280 Speaker 3: billion people by twenty fifty on potentially less land as 65 00:03:54,320 --> 00:03:57,800 Speaker 3: it's protected by nature, and to halt the biodiversity crisis 66 00:03:57,800 --> 00:03:59,960 Speaker 3: which we're currently experiencing. As I said, we need to 67 00:04:00,040 --> 00:04:02,880 Speaker 3: feed ten billion people by twenty to fifty. Unfortunately, that 68 00:04:02,880 --> 00:04:04,640 Speaker 3: does mean that we still need to rely on a 69 00:04:04,680 --> 00:04:08,960 Speaker 3: portion of chemical crop inputs as well as implementing integrated 70 00:04:08,960 --> 00:04:12,600 Speaker 3: pest management systems, which are a methodology of reducing the 71 00:04:12,600 --> 00:04:14,520 Speaker 3: amount of chemical pesticide that is used. 72 00:04:14,880 --> 00:04:16,760 Speaker 2: So currently we spray. 73 00:04:16,600 --> 00:04:21,039 Speaker 3: Chemical pesticides at very high volumes, very indiscriminately, and that 74 00:04:21,080 --> 00:04:24,320 Speaker 3: can either be via aerial with a crop duster, which 75 00:04:24,360 --> 00:04:27,039 Speaker 3: is a small plane with a payload that just drops 76 00:04:27,080 --> 00:04:29,640 Speaker 3: the chemical onto the field, or we do it via. 77 00:04:29,440 --> 00:04:30,919 Speaker 2: A big boom spread which is. 78 00:04:30,880 --> 00:04:33,200 Speaker 3: An effect attractor with a tank attached to it with 79 00:04:33,320 --> 00:04:36,600 Speaker 3: two large wings which then deliver that pesticide along the 80 00:04:36,720 --> 00:04:38,960 Speaker 3: rows of crops. Now, what this means is that the 81 00:04:39,080 --> 00:04:42,200 Speaker 3: chemical can actually then either blow away in spray drift 82 00:04:42,240 --> 00:04:44,960 Speaker 3: as the air picks up, or more chemical is released 83 00:04:45,120 --> 00:04:47,720 Speaker 3: then is actually necessary to kill the pest. And that 84 00:04:47,760 --> 00:04:50,360 Speaker 3: pest can either be a weed, it can be a fungus, 85 00:04:50,480 --> 00:04:54,839 Speaker 3: it can be an insect or something even more obscure 86 00:04:54,880 --> 00:04:57,440 Speaker 3: like a nematode which exists in the soil and can 87 00:04:57,480 --> 00:04:59,960 Speaker 3: harm the plant's growth. And eventually what that means is 88 00:05:00,040 --> 00:05:02,080 Speaker 3: the yield that we obtain from the crops. 89 00:05:02,400 --> 00:05:04,560 Speaker 1: So why don't you give me a little bit of 90 00:05:04,760 --> 00:05:08,840 Speaker 1: context around just how bad the problem is in terms 91 00:05:08,920 --> 00:05:13,080 Speaker 1: of the overuse or inefficient use of pesticides, be those 92 00:05:13,160 --> 00:05:14,600 Speaker 1: insecticides or herbicides. 93 00:05:14,839 --> 00:05:17,839 Speaker 3: Absolutely so when we spray these chemicals in these big 94 00:05:17,880 --> 00:05:21,520 Speaker 3: broadcast methods, ninety eight percent of insecticides and ninety five 95 00:05:21,520 --> 00:05:24,880 Speaker 3: percent of herbicides don't even reach their target pests. 96 00:05:24,920 --> 00:05:26,240 Speaker 2: So what that means is. 97 00:05:26,200 --> 00:05:28,640 Speaker 3: It that chemical can then leave the cropping zone and 98 00:05:28,680 --> 00:05:31,520 Speaker 3: the cropping system or the farm and then cause knock 99 00:05:31,520 --> 00:05:35,040 Speaker 3: on consequences to nature and ecology, whether that be disrupting 100 00:05:35,200 --> 00:05:40,080 Speaker 3: breeding cycles of aquatic organisms, killing native plants, affecting the 101 00:05:40,120 --> 00:05:43,400 Speaker 3: behavior of large animals, that neurotoxicity as we call it, 102 00:05:43,480 --> 00:05:46,000 Speaker 3: and even up to the human level. There was traces 103 00:05:46,040 --> 00:05:49,599 Speaker 3: of glyphosate found in human urine at very, very shocking 104 00:05:49,720 --> 00:05:51,560 Speaker 3: levels recently in the United States. 105 00:05:51,920 --> 00:05:55,520 Speaker 1: I think there is a general understanding that for overall 106 00:05:55,560 --> 00:05:59,200 Speaker 1: health of organisms, we want to reduce pesticide use. I mean, 107 00:05:59,200 --> 00:06:03,480 Speaker 1: these are micals designed to kill things, including insects, which 108 00:06:03,560 --> 00:06:07,560 Speaker 1: we do need for biodiversity. So the urgency is so 109 00:06:07,720 --> 00:06:10,200 Speaker 1: well laid out by the fact that ninety eight percent 110 00:06:10,240 --> 00:06:11,960 Speaker 1: I mean, I'm just going to repeat that, because that 111 00:06:12,080 --> 00:06:16,400 Speaker 1: is such a huge amount of overall pesticides not reaching 112 00:06:16,440 --> 00:06:19,960 Speaker 1: their desired location. But Aha, we are here to discuss 113 00:06:20,160 --> 00:06:23,360 Speaker 1: solutions as we always do, and I find this. We're 114 00:06:23,360 --> 00:06:27,680 Speaker 1: going to launch into a conversation around how AI can 115 00:06:27,960 --> 00:06:30,880 Speaker 1: actually address this, which going to be learning a lot 116 00:06:30,880 --> 00:06:32,840 Speaker 1: on this show, because when I think about the natural 117 00:06:32,880 --> 00:06:36,479 Speaker 1: world and I think about plants in particular, the interventions 118 00:06:36,480 --> 00:06:38,719 Speaker 1: that immediately come to mind are not ones that I 119 00:06:38,760 --> 00:06:42,200 Speaker 1: would think involve computers sitting in a lab somewhere and 120 00:06:42,360 --> 00:06:46,560 Speaker 1: a technology fix. So explain to us how AI has 121 00:06:46,600 --> 00:06:49,440 Speaker 1: an application in reducing pesticides. 122 00:06:49,680 --> 00:06:54,240 Speaker 3: Absolutely, so there's a leading technology which is emerging that 123 00:06:54,320 --> 00:06:56,839 Speaker 3: we call as a blanket variable right technology, and it 124 00:06:56,920 --> 00:06:58,400 Speaker 3: kind of does what it says on the tin. It 125 00:06:58,520 --> 00:07:02,039 Speaker 3: varies the right in which we apply these chemical pesticides. Now, 126 00:07:02,080 --> 00:07:05,880 Speaker 3: the pinnacle of that the best performing technology is green 127 00:07:05,960 --> 00:07:09,640 Speaker 3: on green optical spot spray and that essentially is cameras 128 00:07:09,680 --> 00:07:13,880 Speaker 3: that amounted to a conventional broadcast boom spray that then 129 00:07:14,080 --> 00:07:18,240 Speaker 3: uses artificial intelligence algorithms to detect the weeds in the 130 00:07:18,360 --> 00:07:21,240 Speaker 3: row of the crops. As this machine is working down 131 00:07:21,400 --> 00:07:24,080 Speaker 3: the field and it chooses to turn on and off 132 00:07:24,080 --> 00:07:27,480 Speaker 3: the nozzles to only spray the weed that is present. 133 00:07:27,640 --> 00:07:29,560 Speaker 3: So the reason we call it green on green as 134 00:07:29,560 --> 00:07:33,400 Speaker 3: opposed to green on brown was the previous technology was 135 00:07:33,840 --> 00:07:36,480 Speaker 3: a green on brown, meaning that it can sense green 136 00:07:36,680 --> 00:07:39,840 Speaker 3: plants on brown soil. Now we're talking about green on 137 00:07:40,000 --> 00:07:43,440 Speaker 3: green technologies. This means that we can sense green weeds 138 00:07:43,560 --> 00:07:47,400 Speaker 3: amongst green crops. So it's selecting green within green to 139 00:07:47,480 --> 00:07:49,720 Speaker 3: then deliver that precise dose of herbicide. 140 00:07:49,800 --> 00:07:52,720 Speaker 1: So, if I'm understanding this correctly, this is basically a 141 00:07:53,160 --> 00:07:57,240 Speaker 1: very advanced facial recognition technology but for weeds, so it 142 00:07:57,280 --> 00:07:59,520 Speaker 1: can tell the difference between the plant that you want 143 00:07:59,520 --> 00:08:01,320 Speaker 1: to have there and the plant that you don't want 144 00:08:01,360 --> 00:08:01,840 Speaker 1: to have there. 145 00:08:02,160 --> 00:08:04,360 Speaker 2: In essence, yes, okay. 146 00:08:04,160 --> 00:08:06,240 Speaker 1: So this is interesting. I wonder if there'll be any 147 00:08:06,280 --> 00:08:09,160 Speaker 1: mistaken identity moments there. But the point is that this 148 00:08:09,240 --> 00:08:13,280 Speaker 1: seems like a technology solution to detecting the pests that 149 00:08:13,320 --> 00:08:17,400 Speaker 1: are within the desired crops. But why is this considered 150 00:08:17,480 --> 00:08:21,680 Speaker 1: an artificial intelligence application? What about it makes it AI? 151 00:08:22,320 --> 00:08:25,080 Speaker 3: So what they do is they feed a model, a 152 00:08:25,120 --> 00:08:29,520 Speaker 3: computer model, annotated images of weeds thousands of thousands of times, 153 00:08:29,640 --> 00:08:32,240 Speaker 3: and the model begins to learn the shape of the weed, 154 00:08:32,440 --> 00:08:35,160 Speaker 3: the color of the leaf compared to a crop, and 155 00:08:35,200 --> 00:08:37,160 Speaker 3: it can eventually manage to do that at speed and 156 00:08:37,240 --> 00:08:40,000 Speaker 3: make the decision by itself which is the weed and 157 00:08:40,040 --> 00:08:41,760 Speaker 3: which is the crop. Now a lot of this is 158 00:08:41,880 --> 00:08:45,160 Speaker 3: done in house by the big machinery manufacturers, but there's 159 00:08:45,160 --> 00:08:47,080 Speaker 3: also a push to make this open source so that 160 00:08:47,120 --> 00:08:49,840 Speaker 3: it can be used globally free to use, and that's 161 00:08:49,880 --> 00:08:53,080 Speaker 3: by actually a chap working over here in Sydney at 162 00:08:53,120 --> 00:08:56,400 Speaker 3: the Sydney University called the University of Sydney Weed AI. 163 00:08:56,920 --> 00:09:00,560 Speaker 1: So also to simplify this, it enables precision application, so 164 00:09:00,559 --> 00:09:04,760 Speaker 1: it's able to really make the location of the pesticide 165 00:09:04,760 --> 00:09:08,880 Speaker 1: that's being used quite specific to address the specific weed. Now, 166 00:09:09,120 --> 00:09:12,520 Speaker 1: how much of an improvement would this lead to, because 167 00:09:12,720 --> 00:09:15,840 Speaker 1: it's all going into the soil in this general area. 168 00:09:15,960 --> 00:09:19,319 Speaker 1: Is this actually going to dramatically reduce the amount of 169 00:09:19,320 --> 00:09:22,360 Speaker 1: pesticides that are used in a commercial farm? 170 00:09:22,640 --> 00:09:25,920 Speaker 3: Absolutely, the best available technologies are promising an up to 171 00:09:26,040 --> 00:09:29,079 Speaker 3: ninety seven point five percent production in the amount of 172 00:09:29,120 --> 00:09:30,200 Speaker 3: chemical that is used. 173 00:09:30,440 --> 00:09:32,920 Speaker 1: Wow, So that's a huge improvement. And then that begs 174 00:09:32,960 --> 00:09:37,439 Speaker 1: the question does this then have a net economic benefit 175 00:09:37,480 --> 00:09:41,440 Speaker 1: for the farmer? What are the financial savings for the 176 00:09:41,440 --> 00:09:45,840 Speaker 1: farm in terms of reducing pesticides and pesticides essentially a 177 00:09:45,880 --> 00:09:47,680 Speaker 1: really expensive part of farming. 178 00:09:48,040 --> 00:09:50,600 Speaker 3: So yeah, with our modeling that we've done here at 179 00:09:50,600 --> 00:09:54,120 Speaker 3: Bloomberg NIA, we've found that this employing this green on 180 00:09:54,160 --> 00:09:56,880 Speaker 3: green technology can be up to sixty percent cheaper. 181 00:09:56,640 --> 00:09:58,079 Speaker 2: Than current broadcast methods. 182 00:09:58,160 --> 00:10:01,040 Speaker 3: So that takes into account the fuel, all the changes 183 00:10:01,280 --> 00:10:05,000 Speaker 3: in cost of labor, the chemical itself, the herbicide, and 184 00:10:05,200 --> 00:10:08,720 Speaker 3: the cost of the actually implementing and fitting one of 185 00:10:08,760 --> 00:10:10,680 Speaker 3: these new green on green machines. 186 00:10:11,040 --> 00:10:14,520 Speaker 1: So presumably the machines themselves have a pretty substantial capital 187 00:10:14,559 --> 00:10:17,320 Speaker 1: outlaid the beginning, and then the savings that you make 188 00:10:17,440 --> 00:10:19,840 Speaker 1: on reducing your pesticide use is going to help you 189 00:10:20,000 --> 00:10:22,120 Speaker 1: pay for that over time. But let's get into that 190 00:10:22,200 --> 00:10:24,800 Speaker 1: to begin with. How expensive is it? How much cost 191 00:10:24,880 --> 00:10:27,560 Speaker 1: is it going to be for the farmer to start 192 00:10:27,640 --> 00:10:29,400 Speaker 1: using this technology to begin with. 193 00:10:29,760 --> 00:10:32,400 Speaker 3: So there's two models that you can go for here. 194 00:10:32,520 --> 00:10:35,960 Speaker 3: You can either buy a new sprayer which is equipped 195 00:10:36,000 --> 00:10:39,920 Speaker 3: with this technology, or you can be buying a retrofit part, 196 00:10:40,120 --> 00:10:42,800 Speaker 3: which is where a secondary manufacturer will fit this to 197 00:10:42,880 --> 00:10:46,079 Speaker 3: your current existing sprayre Now, most farmers already own a spray, 198 00:10:46,160 --> 00:10:49,600 Speaker 3: they've already outlaid that capsule expenditure. Most of these models 199 00:10:49,720 --> 00:10:52,160 Speaker 3: sit around one hundred and twenty thousand dollars. 200 00:10:52,559 --> 00:10:55,520 Speaker 1: And are these sprayers stationary? Are you capable of moving 201 00:10:55,559 --> 00:10:58,040 Speaker 1: them around? And the real question I'm getting at is 202 00:10:58,120 --> 00:11:00,240 Speaker 1: whether or not you need to have a lot out 203 00:11:00,240 --> 00:11:02,440 Speaker 1: of them on a farm or you'd be able to 204 00:11:02,480 --> 00:11:05,800 Speaker 1: invest in a smaller number and actually move them around. 205 00:11:06,160 --> 00:11:09,040 Speaker 3: Typically a farmer will have one sprayer and that'll be 206 00:11:09,040 --> 00:11:11,200 Speaker 3: the one spread that they use. Now, obviously, in the 207 00:11:11,240 --> 00:11:13,440 Speaker 3: really really large operations, when we get up to the 208 00:11:13,480 --> 00:11:15,959 Speaker 3: thousands upon thousands of hectors. You may need to have 209 00:11:16,120 --> 00:11:18,480 Speaker 3: a couple of machines, but for the most part, one 210 00:11:18,520 --> 00:11:21,280 Speaker 3: machine will definitely take care of all of the land 211 00:11:21,280 --> 00:11:21,679 Speaker 3: that you have. 212 00:11:22,360 --> 00:11:25,520 Speaker 1: So where in the world are these being adopted right now? 213 00:11:25,640 --> 00:11:30,320 Speaker 1: Are there more technology friendly farming communities that we should 214 00:11:30,320 --> 00:11:32,920 Speaker 1: know about somewhere between where you live and I live 215 00:11:33,000 --> 00:11:34,880 Speaker 1: on this beautiful blue planet? 216 00:11:35,320 --> 00:11:37,000 Speaker 2: There certainly are there, certainly are. 217 00:11:37,160 --> 00:11:39,960 Speaker 3: Actually Australia, where we're sitting right now, has had the 218 00:11:40,040 --> 00:11:44,880 Speaker 3: greatest adoption of variable rate technology or precision application. In 219 00:11:44,960 --> 00:11:48,800 Speaker 3: the earlier stages, there was a technology called green on Brown, 220 00:11:49,000 --> 00:11:50,960 Speaker 3: not quite as advanced and can only be used under 221 00:11:50,960 --> 00:11:54,120 Speaker 3: certain applications. It just so happened that those applications fitted 222 00:11:54,120 --> 00:11:57,880 Speaker 3: Australia's agronomy and in geography perfectly, so we had a 223 00:11:57,880 --> 00:12:01,640 Speaker 3: great uptake of the technology and that equates to around 224 00:12:01,720 --> 00:12:04,760 Speaker 3: seventy percent of grain along the eastern parts of Australia 225 00:12:04,920 --> 00:12:08,360 Speaker 3: being sprayed with variable rate technology. Now looking at the 226 00:12:08,400 --> 00:12:10,880 Speaker 3: green on green technology which are starting to become really 227 00:12:10,920 --> 00:12:13,600 Speaker 3: popular here in Australia, but they also will be able 228 00:12:13,640 --> 00:12:17,160 Speaker 3: to provide savings to farmers in the US, in Brazil 229 00:12:17,360 --> 00:12:19,440 Speaker 3: and in the EU. Are the key cropping areas. 230 00:12:19,679 --> 00:12:22,320 Speaker 1: So you mentioned the conditions being right in Australia for 231 00:12:22,360 --> 00:12:25,040 Speaker 1: early adoption of some of these technologies. What are the 232 00:12:25,080 --> 00:12:27,760 Speaker 1: conditions that need to be in place in order for 233 00:12:27,800 --> 00:12:28,360 Speaker 1: this to work. 234 00:12:28,600 --> 00:12:32,640 Speaker 3: Older technologies were only able to spray when they sensed 235 00:12:32,800 --> 00:12:35,880 Speaker 3: a plant and not use AI to detect the difference 236 00:12:35,880 --> 00:12:38,520 Speaker 3: between a plant, a crop and a weed. So that 237 00:12:38,559 --> 00:12:40,640 Speaker 3: means they could only be used when the field was 238 00:12:40,679 --> 00:12:42,960 Speaker 3: being fallowed and that is when the field is empty 239 00:12:42,960 --> 00:12:45,800 Speaker 3: of any crops. So we were only spraying during that 240 00:12:45,880 --> 00:12:51,240 Speaker 3: period between harvest and sewing, again to avoid the cost 241 00:12:51,440 --> 00:12:55,400 Speaker 3: of accidentally spraying your crops. Now with the newer technology, 242 00:12:55,480 --> 00:12:57,760 Speaker 3: we can use it year round because it's able to 243 00:12:57,840 --> 00:13:02,080 Speaker 3: detect the weed in crop. Means whilst the field bears crops, 244 00:13:02,200 --> 00:13:05,200 Speaker 3: we can use this technology to spray throughout the full 245 00:13:05,280 --> 00:13:06,040 Speaker 3: cropping cycle. 246 00:13:06,679 --> 00:13:09,240 Speaker 1: When we're thinking about the sort of crops that this 247 00:13:09,320 --> 00:13:13,480 Speaker 1: would be most used for, whether they're the economically beneficial 248 00:13:13,520 --> 00:13:16,160 Speaker 1: ones because certainly some of them make more money than others, 249 00:13:16,360 --> 00:13:19,160 Speaker 1: or the way that they're harvested does it make a difference. 250 00:13:19,280 --> 00:13:22,120 Speaker 1: I mean, I'm from Napa Valley, which is well known 251 00:13:22,280 --> 00:13:25,200 Speaker 1: as a wine growing region, and there's multiple different ways 252 00:13:25,240 --> 00:13:28,120 Speaker 1: to go about growing grapes, and some of them are 253 00:13:28,400 --> 00:13:30,760 Speaker 1: dry farmed, but most of them are in rows with 254 00:13:30,760 --> 00:13:33,120 Speaker 1: some sort of irrigation. Is this something that would be 255 00:13:33,200 --> 00:13:35,800 Speaker 1: used for the wine industry perhaps, or does it have 256 00:13:35,960 --> 00:13:39,240 Speaker 1: more applicability in let's say corn or even I'm thinking 257 00:13:39,320 --> 00:13:42,679 Speaker 1: about really fast rotation crops near the equator, like bananas. 258 00:13:43,520 --> 00:13:45,600 Speaker 3: So the most gains that we're going to see here 259 00:13:45,760 --> 00:13:49,040 Speaker 3: are typically in row crops. Now, these are big, broad 260 00:13:49,080 --> 00:13:55,240 Speaker 3: acre operations that are growing grains, oil seeds, things like corn, wheat, canola. 261 00:13:55,600 --> 00:13:57,520 Speaker 3: Now that's not to say that it can't be used 262 00:13:57,520 --> 00:14:01,000 Speaker 3: and it isn't used in tree crops. The amount of 263 00:14:01,000 --> 00:14:02,480 Speaker 3: gains that we're going to see are going to be 264 00:14:02,480 --> 00:14:06,040 Speaker 3: best from these larger row crops, big operations. We think 265 00:14:06,080 --> 00:14:08,200 Speaker 3: here in Australia there's some farmers who can go for 266 00:14:08,240 --> 00:14:10,760 Speaker 3: ten kilometers without having to turn their vehicle around. And 267 00:14:10,800 --> 00:14:13,520 Speaker 3: then in terms of frequency of use in the US 268 00:14:13,600 --> 00:14:17,400 Speaker 3: and in THEEU, there's typically one crop per year in 269 00:14:17,520 --> 00:14:19,960 Speaker 3: each field. Now, if we move down close to the equator, 270 00:14:20,080 --> 00:14:22,280 Speaker 3: take Brazil for example, Brazil, you can have up to 271 00:14:22,480 --> 00:14:25,080 Speaker 3: three crops per year being taken out of the field. 272 00:14:25,160 --> 00:14:27,880 Speaker 3: So that really equates to a lot of savings on 273 00:14:27,960 --> 00:14:29,520 Speaker 3: the amount of pesticide that we're spraying. 274 00:14:29,960 --> 00:14:32,760 Speaker 1: So you've painted a picture in my mind of fairly 275 00:14:32,960 --> 00:14:36,840 Speaker 1: large farms monocropping, and you know, the things that are 276 00:14:36,880 --> 00:14:40,240 Speaker 1: actually reaching most people on their dinner plate. And there 277 00:14:40,280 --> 00:14:43,640 Speaker 1: have been concerns not just regarding pesticides, but actually the 278 00:14:43,680 --> 00:14:47,040 Speaker 1: vulnerabilities of monocropping and also what it does to the 279 00:14:47,080 --> 00:14:50,600 Speaker 1: soil to constantly be rotating the same crops on the 280 00:14:50,640 --> 00:14:53,600 Speaker 1: same space. Is there a benefit to soil health when 281 00:14:53,600 --> 00:14:56,120 Speaker 1: it comes to reducing the amount of pesticides And is 282 00:14:56,120 --> 00:14:58,040 Speaker 1: this going to make that plot of land that the 283 00:14:58,080 --> 00:15:00,400 Speaker 1: farmer is working on something they're going to be able 284 00:15:00,440 --> 00:15:03,120 Speaker 1: to be on for longer and maybe even reduce their 285 00:15:03,280 --> 00:15:04,480 Speaker 1: need for fertilizers. 286 00:15:04,840 --> 00:15:05,280 Speaker 2: Certainly. 287 00:15:05,360 --> 00:15:08,360 Speaker 3: So, a lot of these chemicals reduce the health of 288 00:15:08,400 --> 00:15:12,600 Speaker 3: the soils, not only in the microorganisms, but also those 289 00:15:12,840 --> 00:15:17,360 Speaker 3: larger organisms that are existing, the beneficial insects and invertebrates. 290 00:15:17,640 --> 00:15:20,520 Speaker 3: So by reducing the amount of damage that we're causing 291 00:15:20,680 --> 00:15:24,440 Speaker 3: to the soil by overspraying pesticides, we actually stop the 292 00:15:24,520 --> 00:15:28,440 Speaker 3: vicious cycle, which is damage soil less beneficial insects and 293 00:15:28,480 --> 00:15:30,520 Speaker 3: therefore more chemical needing to be sprayed. 294 00:15:32,160 --> 00:15:36,240 Speaker 1: The pesticide business is a big business. By reducing the 295 00:15:36,240 --> 00:15:38,840 Speaker 1: amount that are actually being used, there could potentially be 296 00:15:39,120 --> 00:15:41,280 Speaker 1: a lot of money at stake. What is the current 297 00:15:41,400 --> 00:15:44,160 Speaker 1: market size for this and how much are they doing? 298 00:15:44,360 --> 00:15:47,240 Speaker 1: I guess annually in terms of how many pesticides are 299 00:15:47,280 --> 00:15:48,960 Speaker 1: being sold around the world. 300 00:15:49,280 --> 00:15:53,160 Speaker 3: So the global pesticide industry or crop protection industries is 301 00:15:53,200 --> 00:15:56,000 Speaker 3: also known, is around forty three billion dollars a year. 302 00:15:56,120 --> 00:15:58,920 Speaker 3: Now that's completely under threat at the moment, both due 303 00:15:58,960 --> 00:16:01,680 Speaker 3: to legislative pressures but also due to the farmer being 304 00:16:01,760 --> 00:16:04,400 Speaker 3: very squeezed. The farmer doesn't receive very much of the 305 00:16:04,400 --> 00:16:08,200 Speaker 3: share of the dollar, so wherever they can reasonably cut costs, 306 00:16:08,320 --> 00:16:11,560 Speaker 3: they will. Now this technology is allowing them to reduce 307 00:16:11,760 --> 00:16:14,800 Speaker 3: both their cost base but also to improve the productivity 308 00:16:14,840 --> 00:16:15,840 Speaker 3: of their farm. 309 00:16:15,960 --> 00:16:19,840 Speaker 1: How are the pesticide companies viewing this new technology that's 310 00:16:19,880 --> 00:16:22,240 Speaker 1: emerging and is it something that they're interested in and 311 00:16:22,280 --> 00:16:25,960 Speaker 1: potentially developing a house or even acquiring, or is it 312 00:16:26,000 --> 00:16:29,800 Speaker 1: something that they're threatened by and trying to figure out 313 00:16:29,880 --> 00:16:33,040 Speaker 1: how long they can avoid it becoming mainstream. 314 00:16:33,320 --> 00:16:36,840 Speaker 3: The crop protection industry has been able to move very agile, 315 00:16:36,880 --> 00:16:42,040 Speaker 3: and they've learned from previous legislative knocks such as in 316 00:16:42,120 --> 00:16:45,360 Speaker 3: the EU the amount of pesticides that are being restricted 317 00:16:45,360 --> 00:16:47,400 Speaker 3: for use on a yearly basis. So they've really grabbed 318 00:16:47,440 --> 00:16:49,440 Speaker 3: the ball by the horns and they've jumped in at 319 00:16:49,440 --> 00:16:52,360 Speaker 3: the deep end. For instance, there's a startup called the 320 00:16:52,440 --> 00:16:56,440 Speaker 3: Eco Robotics ARA, which is a precision delivery unit which 321 00:16:56,480 --> 00:16:59,680 Speaker 3: promises to reduce crop inputs from herbicide insect side and 322 00:16:59,680 --> 00:17:02,760 Speaker 3: funger side as well as fertilizer. Now that's had investment 323 00:17:02,960 --> 00:17:07,280 Speaker 3: from notable investors, both the ASF, the German crop protection company, 324 00:17:07,320 --> 00:17:10,400 Speaker 3: but also Yara, the global fertilizer company. 325 00:17:10,880 --> 00:17:13,600 Speaker 1: So when you're talking about this AI technology being used 326 00:17:13,640 --> 00:17:18,400 Speaker 1: to spot those pesky pests, you specifically referenced it being 327 00:17:18,560 --> 00:17:22,880 Speaker 1: put onto a boom and kind of coming across the 328 00:17:23,080 --> 00:17:27,040 Speaker 1: entire field. But I'm thinking now of drones that are 329 00:17:27,080 --> 00:17:30,679 Speaker 1: not actually connected to the ground flying over. That is 330 00:17:30,720 --> 00:17:34,159 Speaker 1: something that has been i think excitedly talked about. And 331 00:17:34,200 --> 00:17:36,439 Speaker 1: the question for you, is someone who's looked at this 332 00:17:36,560 --> 00:17:40,040 Speaker 1: in more detail, is whether or not you think that 333 00:17:40,040 --> 00:17:42,200 Speaker 1: that's got legs No pun intended. 334 00:17:42,720 --> 00:17:48,000 Speaker 3: So there absolutely is an application for drones in agriculture. However, 335 00:17:48,160 --> 00:17:52,440 Speaker 3: the spraying of large sways of cropping land is probably 336 00:17:52,480 --> 00:17:54,879 Speaker 3: not it. The payloads are just too small at the 337 00:17:54,920 --> 00:17:58,440 Speaker 3: moment and we haven't really seen advances in swarming technology, 338 00:17:58,440 --> 00:18:01,399 Speaker 3: and that's when we deploy multiple drones. So I think 339 00:18:01,480 --> 00:18:05,080 Speaker 3: the largest drone which is currently available is the Guardian 340 00:18:05,119 --> 00:18:09,040 Speaker 3: Agriculture sc one, which has around seventy to eighty liters 341 00:18:09,280 --> 00:18:12,600 Speaker 3: of payload capacity. It has also been invested by big 342 00:18:12,720 --> 00:18:15,800 Speaker 3: names in the industry like leaps by Buyer. Now, the 343 00:18:15,920 --> 00:18:19,720 Speaker 3: case for drones is that we can apply chemical to 344 00:18:19,960 --> 00:18:22,400 Speaker 3: hard to reach areas, which will mean that the use 345 00:18:22,400 --> 00:18:25,399 Speaker 3: of the chemical is more efficient, so such as the 346 00:18:25,600 --> 00:18:28,720 Speaker 3: tops of tree crops, which previously we haven't been able 347 00:18:28,760 --> 00:18:32,280 Speaker 3: to apply to very efficiently we've therefore lost yield. It 348 00:18:32,320 --> 00:18:35,520 Speaker 3: also can be used on areas such as boundaries where 349 00:18:35,720 --> 00:18:36,720 Speaker 3: the spray is. 350 00:18:36,640 --> 00:18:38,280 Speaker 2: Not able to get to as easily. 351 00:18:38,640 --> 00:18:43,480 Speaker 3: Alternatively, and areas of sprayer can't enter, like greenhouse agriculture 352 00:18:43,520 --> 00:18:45,879 Speaker 3: or glasshouse agriculture. So there certainly is a case for 353 00:18:45,920 --> 00:18:48,720 Speaker 3: spray drones. The technology is just not there yet at 354 00:18:48,760 --> 00:18:53,359 Speaker 3: the moment to spray big swathes of agricultural arable land. 355 00:18:53,760 --> 00:18:57,120 Speaker 3: Another application of the use of drones will be in 356 00:18:57,240 --> 00:19:00,520 Speaker 3: mapping and surveillance of fields. So that is something that 357 00:19:00,640 --> 00:19:03,280 Speaker 3: currently takes a lot of time and effort and also 358 00:19:03,280 --> 00:19:05,520 Speaker 3: a lot of money to get a satellite map done 359 00:19:05,680 --> 00:19:08,959 Speaker 3: of the characteristics of your farm land, which are very 360 00:19:09,000 --> 00:19:12,240 Speaker 3: useful in applying inputs. So that may be the yields, 361 00:19:12,320 --> 00:19:15,200 Speaker 3: that may be the presence of pests, that may be 362 00:19:15,480 --> 00:19:16,680 Speaker 3: the availability of. 363 00:19:16,760 --> 00:19:18,199 Speaker 2: Water for your cropping. 364 00:19:18,240 --> 00:19:22,320 Speaker 3: So this will enable us to work smarter using imagery 365 00:19:22,440 --> 00:19:25,400 Speaker 3: mapping software that then can be loaded up to farm 366 00:19:25,400 --> 00:19:29,159 Speaker 3: management software to deploy chemicals smarter. So the case for 367 00:19:29,240 --> 00:19:34,280 Speaker 3: drones is either as surveillance and mapping imagery technology or 368 00:19:34,400 --> 00:19:37,520 Speaker 3: as in small payloads in areas that we can't get 369 00:19:37,520 --> 00:19:38,280 Speaker 3: a boom spread to. 370 00:19:38,760 --> 00:19:41,560 Speaker 1: So the drone technology is actually a compliment to the 371 00:19:41,560 --> 00:19:44,760 Speaker 1: boomsprayer as opposed to an alternative to it, at least 372 00:19:44,760 --> 00:19:47,040 Speaker 1: in the picture that you've painted of the future, where 373 00:19:47,080 --> 00:19:49,800 Speaker 1: we're looking at the field and being strategic and then 374 00:19:49,800 --> 00:19:53,280 Speaker 1: the boom sprayer has that ability to actually do the 375 00:19:53,440 --> 00:19:56,840 Speaker 1: end application in that quite precision way. This seems like 376 00:19:56,880 --> 00:19:59,399 Speaker 1: a great solution. You've got me very excited about what 377 00:19:59,440 --> 00:20:02,360 Speaker 1: this technology could accomplish. So let's pivot a little bit 378 00:20:02,480 --> 00:20:06,360 Speaker 1: to what parts of the pest world that it could 379 00:20:06,400 --> 00:20:09,120 Speaker 1: actually be applied to. A lot of our conversation thus 380 00:20:09,160 --> 00:20:14,439 Speaker 1: far has really focused on weeds and the plant based 381 00:20:14,560 --> 00:20:17,240 Speaker 1: problems that we have there, but invariably there are also 382 00:20:17,560 --> 00:20:23,480 Speaker 1: fungus and insects. Is that the next frontier for this technology? 383 00:20:23,560 --> 00:20:26,560 Speaker 1: And I guess, without asking you to predict the future, 384 00:20:26,760 --> 00:20:30,040 Speaker 1: how soon do you think it'll be applicable to a 385 00:20:30,200 --> 00:20:32,200 Speaker 1: wider range of pests? 386 00:20:32,600 --> 00:20:36,639 Speaker 3: Absolutely so, we already have companies offering drone surveillance to 387 00:20:36,840 --> 00:20:39,840 Speaker 3: be able to detect other types of pests, such as 388 00:20:40,400 --> 00:20:44,080 Speaker 3: Xavio for instance. However, what we haven't yet seen is 389 00:20:44,440 --> 00:20:47,960 Speaker 3: a machine that is actually capable of seeing and detecting 390 00:20:48,040 --> 00:20:51,160 Speaker 3: the other types of pests in real time and then 391 00:20:51,280 --> 00:20:55,320 Speaker 3: therefore delivering the precise dose of required pesticide, whether it 392 00:20:55,400 --> 00:20:58,280 Speaker 3: be a herbicide, insecticide, or fungicide. Now we've put a 393 00:20:58,400 --> 00:21:01,200 Speaker 3: rough estimate there together that we think by at least 394 00:21:01,240 --> 00:21:04,320 Speaker 3: twenty thirty we'll have this detection available for fungicide, so 395 00:21:04,359 --> 00:21:08,080 Speaker 3: that disease will be detectable by a machine in real time, 396 00:21:08,280 --> 00:21:11,280 Speaker 3: and then for insects, we think that should come land 397 00:21:11,440 --> 00:21:14,920 Speaker 3: somewhere between now and twenty fifty. The problem with insects 398 00:21:15,040 --> 00:21:18,400 Speaker 3: is that they are mobile, they're fast, and they're cryptic. 399 00:21:18,680 --> 00:21:21,040 Speaker 3: That means that they can hide, so actually spotting them 400 00:21:21,040 --> 00:21:23,760 Speaker 3: in a crop is a particularly difficult endeavor. 401 00:21:24,160 --> 00:21:26,919 Speaker 1: So when I'm imagining the future, I should not be 402 00:21:27,000 --> 00:21:30,120 Speaker 1: imagining some sort of robot, whether on a boom or 403 00:21:30,160 --> 00:21:33,240 Speaker 1: as a drone, flying around chasing insects in some sort 404 00:21:33,240 --> 00:21:35,400 Speaker 1: of a field. But who is coming up with these 405 00:21:35,400 --> 00:21:39,880 Speaker 1: technology solutions. Are they Silicon valley tech companies, Are they 406 00:21:40,119 --> 00:21:44,480 Speaker 1: smaller startups or are they the pesticide companies themselves thinking 407 00:21:44,520 --> 00:21:49,040 Speaker 1: about these new and innovative ways to essentially make farming better. 408 00:21:49,200 --> 00:21:50,440 Speaker 2: So it's actually a mixture. 409 00:21:50,640 --> 00:21:53,959 Speaker 3: What we've seen is we've seen two roots to market, 410 00:21:54,280 --> 00:21:57,359 Speaker 3: and that is from either in house R and D 411 00:21:57,600 --> 00:22:00,600 Speaker 3: and bolt on acquisitions, or it's from parts ships with 412 00:22:00,880 --> 00:22:04,880 Speaker 3: larger companies and smaller startups. So John Deere has gone 413 00:22:05,000 --> 00:22:07,840 Speaker 3: the complete in house route. It's kept its doors shut, 414 00:22:07,880 --> 00:22:10,400 Speaker 3: It's acquired a couple of interesting companies along the way, 415 00:22:10,520 --> 00:22:14,439 Speaker 3: such as Blue River Technology and bear Flag Robotics. On 416 00:22:14,480 --> 00:22:18,000 Speaker 3: the flip side, we've seen companies like CNCH Industrial and 417 00:22:18,040 --> 00:22:22,400 Speaker 3: Agco who have entered into partnerships with spot spray startups 418 00:22:22,480 --> 00:22:26,000 Speaker 3: like Zavio and one smart Spray now there. Recently, there's 419 00:22:26,040 --> 00:22:28,320 Speaker 3: been a joint venture between Agco and one of the 420 00:22:28,359 --> 00:22:32,520 Speaker 3: world's biggest technology companies, Trimble. This acquisition has enabled ADCO 421 00:22:32,880 --> 00:22:38,439 Speaker 3: to really take control of the retrofit precision agriculture suite. 422 00:22:38,520 --> 00:22:42,399 Speaker 3: This is across both spraying, harvesting, delivery of fertilizers. But 423 00:22:42,520 --> 00:22:45,960 Speaker 3: one key part of that joint venture is Bilbury. Now, 424 00:22:46,000 --> 00:22:50,119 Speaker 3: Bilbury is the best performing green on green sprayer on paper. 425 00:22:50,240 --> 00:22:52,639 Speaker 3: What this means is they have the best promises to 426 00:22:52,720 --> 00:22:55,439 Speaker 3: reduce the most amount of chemical pesticide and that is 427 00:22:55,440 --> 00:22:57,199 Speaker 3: sitting at ninety seven point five percent. 428 00:22:57,480 --> 00:23:00,679 Speaker 1: Now let's just pivot again to adaption. Going back to 429 00:23:00,720 --> 00:23:03,199 Speaker 1: what you were saying earlier about some of these units 430 00:23:03,240 --> 00:23:06,199 Speaker 1: being over one hundred thousand US dollars to install. This 431 00:23:06,359 --> 00:23:09,640 Speaker 1: is a big capital outlay, and we know that farming 432 00:23:09,920 --> 00:23:12,040 Speaker 1: is a tough business to be in and the margins 433 00:23:12,040 --> 00:23:15,280 Speaker 1: are not amazingly great, so this may be a fairly 434 00:23:15,320 --> 00:23:18,640 Speaker 1: big hurdle for some farms to actually cross. What are 435 00:23:18,720 --> 00:23:21,280 Speaker 1: governments doing and maybe we can use the case of 436 00:23:21,280 --> 00:23:25,400 Speaker 1: Australia where we've seen good farmer uptake. What it's driven that. 437 00:23:25,480 --> 00:23:28,920 Speaker 1: Has it been entirely the market or have there been 438 00:23:29,000 --> 00:23:32,200 Speaker 1: in government incentives and schemes that have facilitated it. 439 00:23:32,440 --> 00:23:33,280 Speaker 2: That's a great question. 440 00:23:33,400 --> 00:23:36,240 Speaker 3: And actually the geography with the highest adoption in Australia 441 00:23:36,280 --> 00:23:38,480 Speaker 3: has seen most of its adoption of infact all of 442 00:23:38,520 --> 00:23:41,679 Speaker 3: its adoption driven by savings to the farmer. Now, with 443 00:23:41,800 --> 00:23:44,720 Speaker 3: nineteen percent of the variable costs for a grower in 444 00:23:44,760 --> 00:23:48,440 Speaker 3: each year being comprised of crop protection reducing that can 445 00:23:48,480 --> 00:23:50,960 Speaker 3: really cause a benefit to the bottom line for the 446 00:23:50,960 --> 00:23:54,040 Speaker 3: grower themselves. Now, with our modeling, what we've seen is 447 00:23:54,240 --> 00:23:57,439 Speaker 3: the cost of spraying one hecta employing this green on 448 00:23:57,520 --> 00:24:00,439 Speaker 3: green optical spot spraying is about sixty percent saving. 449 00:24:00,760 --> 00:24:04,600 Speaker 1: So really the farmers are very much motivated by how 450 00:24:04,680 --> 00:24:07,240 Speaker 1: much money they're going to save and the payback period 451 00:24:07,520 --> 00:24:10,040 Speaker 1: in terms of money saved on pesticides. It's going to 452 00:24:10,080 --> 00:24:14,920 Speaker 1: make it worthwhile pretty quickly to buy these machines. They 453 00:24:14,920 --> 00:24:17,160 Speaker 1: may even be able to get loans for them. 454 00:24:17,440 --> 00:24:19,760 Speaker 3: Absolutely, So now that does bring a little bit of 455 00:24:19,800 --> 00:24:22,560 Speaker 3: a question into it, and the limitations are that in 456 00:24:22,920 --> 00:24:25,880 Speaker 3: countries where or with a grow who is not large 457 00:24:25,960 --> 00:24:29,760 Speaker 3: enough to be able to outlay the capital expenditure to 458 00:24:29,800 --> 00:24:33,040 Speaker 3: actually obtain the chemical, then what does that mean for them? 459 00:24:33,200 --> 00:24:36,840 Speaker 3: But we are hearing certain calls, whether it be tax 460 00:24:36,840 --> 00:24:41,280 Speaker 3: breaks or tax incentives or subsidies for purchase of precision 461 00:24:41,320 --> 00:24:42,280 Speaker 3: agriculture equipment. 462 00:24:42,640 --> 00:24:44,960 Speaker 1: So we're thinking about the future of farming here, and 463 00:24:45,119 --> 00:24:48,520 Speaker 1: this AI application is certainly one important way for us 464 00:24:48,560 --> 00:24:51,680 Speaker 1: to think about tackling a problem pesticide use. So tell 465 00:24:51,680 --> 00:24:54,680 Speaker 1: me a bit about the future. How soon and what 466 00:24:54,760 --> 00:24:58,080 Speaker 1: does it look like in these modern farms that are 467 00:24:58,119 --> 00:25:00,640 Speaker 1: going to be much more efficient. 468 00:25:01,200 --> 00:25:04,000 Speaker 3: So what we'll see in the future is we'll see fungicide, 469 00:25:04,280 --> 00:25:07,240 Speaker 3: herbicide and insecticide all being able to be delivered from 470 00:25:07,240 --> 00:25:09,520 Speaker 3: the same machine. But not only that, the machine will 471 00:25:09,760 --> 00:25:12,640 Speaker 3: be able to make decisions in real time to detect 472 00:25:12,720 --> 00:25:15,280 Speaker 3: all types of pests, but also be able to learn 473 00:25:15,600 --> 00:25:18,200 Speaker 3: year on year what the trends are, what does the 474 00:25:18,920 --> 00:25:21,919 Speaker 3: local area look like, what does the agronomy request or 475 00:25:21,960 --> 00:25:24,760 Speaker 3: require to be applied, and so essentially what we're doing 476 00:25:24,800 --> 00:25:27,960 Speaker 3: is we're building a large data model of the farm. 477 00:25:28,080 --> 00:25:31,199 Speaker 3: So as the machine goes through the farm, it learns 478 00:25:31,200 --> 00:25:33,680 Speaker 3: the farm, and that's from both we're talking earlier about 479 00:25:33,760 --> 00:25:37,080 Speaker 3: drone surveillance and drone surveying, but also from the. 480 00:25:37,080 --> 00:25:38,000 Speaker 2: On farm cameras. 481 00:25:38,080 --> 00:25:40,600 Speaker 3: So as they learn, the machines get better and they 482 00:25:40,640 --> 00:25:42,160 Speaker 3: get better and more precise. 483 00:25:42,880 --> 00:25:49,720 Speaker 1: So in this increasingly technology reliant agriculture future, what are 484 00:25:49,840 --> 00:25:52,639 Speaker 1: the potential downsides? You know, with the exception of the 485 00:25:52,680 --> 00:25:56,320 Speaker 1: obvious ones, which are that there is required energy use 486 00:25:56,480 --> 00:25:59,480 Speaker 1: for operating any sort of machine, as well as energy 487 00:25:59,560 --> 00:26:02,520 Speaker 1: use for the servers that will very much be required 488 00:26:02,560 --> 00:26:06,000 Speaker 1: in order to facilitate this AI technology the energy transition. 489 00:26:06,400 --> 00:26:10,280 Speaker 1: This makes it intrinsically linked to the changes that may 490 00:26:10,280 --> 00:26:13,160 Speaker 1: be required in the agriculture space. But are there any 491 00:26:13,240 --> 00:26:16,360 Speaker 1: other downsides to this that maybe I haven't considered. 492 00:26:16,800 --> 00:26:19,240 Speaker 3: We haven't spoken at all about autonomy on these machines, 493 00:26:19,280 --> 00:26:21,399 Speaker 3: and actually what we're moving to as a smart vehicle 494 00:26:21,440 --> 00:26:24,080 Speaker 3: that can actually work and operate without the requirement of 495 00:26:24,119 --> 00:26:25,879 Speaker 3: a human. But what that means is then the farmer 496 00:26:26,040 --> 00:26:29,120 Speaker 3: can spend more time monitoring their crops and actually paying 497 00:26:29,119 --> 00:26:33,359 Speaker 3: attention to the local agronomy. Even if these machines moved 498 00:26:33,400 --> 00:26:37,040 Speaker 3: to being fully autonomous, being able to operate by themselves. 499 00:26:37,320 --> 00:26:39,000 Speaker 3: That will mean that we'll free up time on the 500 00:26:39,040 --> 00:26:43,040 Speaker 3: farm for growers who conventionally quite time poor, to be 501 00:26:43,080 --> 00:26:45,240 Speaker 3: able to pay more attention to their crops, to be 502 00:26:45,240 --> 00:26:47,680 Speaker 3: able to monitor for pests, monifor the presence of pests, 503 00:26:47,800 --> 00:26:50,560 Speaker 3: monitor the health and monitorf really for their plant need 504 00:26:50,600 --> 00:26:52,200 Speaker 3: as opposed to spending a lot of the time in 505 00:26:52,280 --> 00:26:55,640 Speaker 3: the cab actually applying these products. Now there's a startup 506 00:26:55,720 --> 00:26:59,920 Speaker 3: also based here in Australia called swarm Farm Robotics. Now, 507 00:27:00,119 --> 00:27:03,479 Speaker 3: what swarm Farm does is they operate a driverless vehicle 508 00:27:03,560 --> 00:27:06,520 Speaker 3: that is capable of towing a sprayer. However, this vehicle 509 00:27:06,640 --> 00:27:10,040 Speaker 3: can choose or has the smarts to operate only when 510 00:27:10,080 --> 00:27:12,959 Speaker 3: the timing is perfect for the chemical to be applied, 511 00:27:13,000 --> 00:27:15,920 Speaker 3: and that is when there is low rain and low wind. 512 00:27:16,000 --> 00:27:18,000 Speaker 3: That means that the chemical is less likely to be 513 00:27:18,119 --> 00:27:21,960 Speaker 3: pulled off of the cropping system or escape the cropping system. 514 00:27:22,480 --> 00:27:25,159 Speaker 1: So, Alex, my final question really comes down to the 515 00:27:25,200 --> 00:27:27,400 Speaker 1: fact that when I think of technology now, I think 516 00:27:27,440 --> 00:27:30,760 Speaker 1: about all of these subscription models that we all subscribe to. 517 00:27:31,119 --> 00:27:34,320 Speaker 1: Will this apply to this technology and will there essentially 518 00:27:34,359 --> 00:27:37,560 Speaker 1: be software updates to the AI technology where it becomes 519 00:27:37,680 --> 00:27:40,880 Speaker 1: more sophisticated and can do a better job of figuring 520 00:27:40,920 --> 00:27:44,280 Speaker 1: out what the precision sprayer needs to do. And as 521 00:27:44,320 --> 00:27:48,000 Speaker 1: a result, is this both a hardware and software conversation? 522 00:27:48,760 --> 00:27:49,760 Speaker 2: It absolutely is. 523 00:27:50,000 --> 00:27:55,440 Speaker 3: So there's essentially three models that the machinery manufacturers are employing. Firstly, 524 00:27:55,560 --> 00:27:59,240 Speaker 3: is a one off fee to purchase both the software 525 00:27:59,320 --> 00:28:02,000 Speaker 3: and the hardware. Then we have a second where you 526 00:28:02,000 --> 00:28:04,760 Speaker 3: would purchase the hardware and then choose to turn on 527 00:28:04,840 --> 00:28:07,399 Speaker 3: the software for a year, and that would enable you 528 00:28:07,440 --> 00:28:10,480 Speaker 3: to spray the amount of hectares per year paying for 529 00:28:10,680 --> 00:28:15,160 Speaker 3: the algorithm that actually detects these pests in field. Now, 530 00:28:15,160 --> 00:28:18,360 Speaker 3: the third option is paying per use, So every time 531 00:28:18,400 --> 00:28:20,800 Speaker 3: you turn on your tractor and choose to use that function, 532 00:28:20,960 --> 00:28:23,639 Speaker 3: you'll pay a fee. So what this means essentially is 533 00:28:23,640 --> 00:28:26,680 Speaker 3: that the current quotes that we're currently seeing are around 534 00:28:26,760 --> 00:28:31,280 Speaker 3: five to seven dollars per hecta to use the technology. 535 00:28:31,760 --> 00:28:34,000 Speaker 1: So this is really interesting because not only is this 536 00:28:34,080 --> 00:28:37,119 Speaker 1: technology going to help save the farmer money on its 537 00:28:37,160 --> 00:28:39,920 Speaker 1: pesticide use, but there actually is a long term revenue 538 00:28:39,920 --> 00:28:42,920 Speaker 1: stream for the companies that are actually selling the technology. 539 00:28:43,120 --> 00:28:46,120 Speaker 1: So I am very interested to see how these business 540 00:28:46,120 --> 00:28:49,280 Speaker 1: models evolve and invariably where it ends up in the world, 541 00:28:49,360 --> 00:28:52,320 Speaker 1: because Australia great first place to start. But I am 542 00:28:52,760 --> 00:28:54,920 Speaker 1: seeing a lot of potential here for other parts of 543 00:28:54,920 --> 00:28:57,360 Speaker 1: the world which you've already identified, such as parts of 544 00:28:57,360 --> 00:29:00,480 Speaker 1: Europe and Brazil and North America. So we will wait 545 00:29:00,480 --> 00:29:02,280 Speaker 1: and see. We look forward to having you back on 546 00:29:02,320 --> 00:29:06,120 Speaker 1: the show telling us about more developments in the agriculture space. 547 00:29:06,240 --> 00:29:07,720 Speaker 1: Thank you for sharing your thoughts. 548 00:29:07,680 --> 00:29:09,000 Speaker 2: Thanks for having me, It's been great. 549 00:29:17,960 --> 00:29:21,280 Speaker 1: Bloomberg NF is a service provided by Bloomberg Finance LP 550 00:29:21,440 --> 00:29:24,880 Speaker 1: and its affiliates. This recording does not constitute, nor should 551 00:29:24,880 --> 00:29:28,920 Speaker 1: it be construed as investment advice, investment recommendations, or a 552 00:29:28,960 --> 00:29:32,520 Speaker 1: recommendation as to an investment or other strategy. Bloomberg n 553 00:29:32,520 --> 00:29:36,040 Speaker 1: EF should not be considered as information sufficient upon which 554 00:29:36,080 --> 00:29:39,760 Speaker 1: to base an investment decision. Neither Bloomberg Finance LP nor 555 00:29:39,800 --> 00:29:43,240 Speaker 1: any of its affiliates makes any representation or warranty as 556 00:29:43,280 --> 00:29:46,120 Speaker 1: to the accuracy or completeness of the information contained in 557 00:29:46,160 --> 00:29:49,320 Speaker 1: this recording, and any liability as a result of this 558 00:29:49,360 --> 00:29:51,120 Speaker 1: recording is expressly disclaimed.