This is so great. My long term dream is that robotics take over farming, individually plucking each weed or weevil, and metering just the right amount of water for each individual plant, so that all the crops are organic.
Most of the chemicals (yes, including nitrogen fertilizers) offset labor, so when the labor is free we shouldn’t need them. And people won’t have to spend their lives in stoop-back work or exposed to toxic chemicals.
In case anyone’s reading this who is interested in working on it:
I’m building a company/platform that does a lot of this, particularly the “metering just the right amount of water for each individual plant” part.
The thing I have in mind is very low cost devices (sub-$20) with mesh radio comms, inputs to read from sensors and outputs to control irrigation, and TinyML running the devices to optimize everything in real time.
I have about 10 years experience working in the field (mostly with high-value crops like wine grapes, nuts, avocados) and several iterations of prototype devices and web software, but am keen to attract people who are excited at the idea of working on this kind of thing.
Anyone - particularly low-level programmers or hardware engineers - interested in working on it can contact me (email in bio).
I wonder if in a large farm it will be worth running hoses and deploying a frob next to each device vs having an electric robot with a refillable tank walking the rows.
Such a robot is still SF today, so deploying a frob with each seedling would be the only choice at the moment (or continue current irrigation practices). The frobs have to be cheap enough to be consumables.
My gut tells me that the robot will cost less in the long run. It also doesn't seem like a hard problem (yeah, easy to say) since row crops are planted at fixed spacings and detecting that the thing next you is a plant and not a rabbit should not be a difficult task. The combination of GPS mapping (planter knows where it was during planting), known plant & row spacing, and basic visual imaging should simplify the problem.
So why isn't it done today? Probably still cheaper to rely on the weather or center pivot irrigation.
Scale, I imagine. Orchards are big. How many robot waterers would you need when you have to spend time at each individual tree (or groups of trees) to water it/them? How far is it to the nearest refill?
Put another way, drip is massively parallel. Robot waterers, not so much.
Oh, I wasn't thinking orchards. I thought OP was talking about row crops which can't feasibly be irrigated with hoses.
Row crops can be (and already are) irrigated with hoses. In dry areas of the world, drip tape is buried throughout the entire field because it allows farmers to make more efficient use of the water available to them. It does require the machinery has auto-steer (which is standard practice now anyway), because tearing up the drip tape with a planter is an expensive mistake.
https://whyfarmit.com/drip-tape-irrigation/
Are we talking about irrigation pivots[1] here? Because those are a known technology.
If we are thinking about robots driving up and down the rows and watering plants from a tank, and then returning to some central location to re-fill their tank that feels like a "carrying water for elephants" situation. I suspect the logistics won't work out. Could try to run some numbers on it of course. Is that how you are thinking about it?
1: https://www.youtube.com/watch?v=7j1lMs7fcIQ
Let's say the RoboWater(tm) rolls down a row of trees in the orchard, water hose unreeling behind it. At each tree, it dumps the calculated dose of water into a clay pot that is sunken into the ground near the trunk (from which the water slowly soaks into the soil). When the row is done - it reverses direction, reeling the hose back up in the process. Then some side-shuffling, and it's soon rolling down the next row of trees in the orchard, again dumping the calculated dose of water...
This is not robust. Humans don't use GPS for this purpose (and anyway, the plants are closer than GPS resolution.
Looking and using the local data is the more robust approach. Trying to assume the real world is the same as your model has been the source of countless visual gags since the advent of movies.
The Open Source Ecology folks have been working on this sort of thing for a while --- check in with them?
https://www.opensourceecology.org/
I’ve always been supportive of open-source and plan to make much of our tech open source [1], but I’m not seeing anything on their site that’s anything like what we’re doing (it alls seems to be large machinery, no microelectronics).
The thing about this field that I’ve learned over the decade I’ve been involved is that creating the tech is less than half the challenge; the distribution - building awareness, selling it, installing it, maintaining it - is a huge undertaking, and a lot of money needs to come from somewhere to make that viable.
[1] I’d like to have a RTOS to run on these devices that is as approachable and familiar as common Linux distros like Ubuntu, for people to install and customise themselves, with a full open source license.
In another comment I wrote that you probably need a BOM less than $0.50. At that price you don’t have a massive OS like Linux, you need something embedded that can run in a few KB.
But a bunch of small devices can be managed by a huge device running Linux — maybe even something as expensive as a Raspberry Pi.
(Apart from some time trying to sell in the Ag sector I spent a lot of time on embedded devices)
Well I already have a firmware version that can run in a few KB, which my father developed in Motorola assembly and that ran most of the soil moisture monitoring devices sold to the big-volume wine grape producers in Australia (mostly in Riverland SA supplying Treasury etc) from the late 90s till about 2010, after which newer products using Zigbee and cellular IoT took over (though we worked together on our own newer versions supporting Bluetooth LE and Cat-M1 up until his retirement a couple of years ago).
I hear you that $20 is high - but the status quo in this business now is monitoring devices that sell for AUD $600+, and with LTE-M or LoRa comms modules that cost over AUD $60 alone.
I'm forever thinking about ways you could drive the cost down further. I'd love it if there were a way to get the on-plant modules under $1. Feel free to get in touch if you want to discuss further.
BLE mesh and solar power should get your BoM cost below $20, but I don't see any way that you're going to hit a sub $1 price point. Assuming your mesh can cover the entire field (reasonable if you have one monitoring point every few plants), you can have one or a small handful of LTE-M basestation points to handle the data uplinks.
It's an interesting problem and I am sure reference designs already exist. Maybe talk to someone at Nordic.
Yeah I think that's right. It's a matter of trading off the water cost savings (and produce quality/yield gains) per plant vs unit cost per device, to determine the optimal density of devices.
As I said in the previous comment, right now, high-value crop growers like wine grape growers pay $700-$1000 or more per site (including reader/comms module and sensors), and generally only install one monitoring point per block (I have a system running at one of Australia's top boutique/biodynamic wine makers and at current prices he can only cost-justify having one 10 monitoring sites over his 70 acres of vines).
So, whatever we can do to drive down the cost to $20 or less should deliver big wins.
Yep, we're working with hardware engineers who are well connected to people at Nordic.
There's (relatively) lots of water in the Barossa Valley and it's worth growing a thirsty high value crop like grapes there. And even there the cost structure you say is unsupportable.
But the economics of farming in the Eyre Peninsula is quite different and they really have a water problem. From a food PoV these are the people we really need to help.
(I have family in both, not to mention in laws in Germany who also have a water problem...getting rid of it!)
that website/project looks pretty dead
If you use an Olla, the plants self regulate their water intake.
See the book gardening with less water by David A. Bainbridge
Great for backyard tomato plants, not a commercial farming option for tens of thousands of acres.
Not the way farms are run today, sure. But if it’s worth it, farms will adapt.
This sounds like the optimum use case for LoRa, doesn't it?
LoRa gets talked about plenty for ag monitoring, and sure it can be great for certain use cases. Optional support for LoRa is certainly something we want to support (via device variants or plug-on comms modules).
For the use case invoked in this subthread (an individual monitoring device on each plant), I don’t think it’s the best.
We’re currently working with Nordic nRF52xx/53xx/54xx modules, which have dual ARM cores and built-in 2.4GHz radio, so, support for protocols like Bluetooth Mesh, Zibgee, Thread.
That means you can have a single module that can handle mesh comms with neighboring devices, as well as sensor reading, machine learning and output control. You wouldn’t need a separate comms module to communicate back to a base station or a high post and antenna for long-range comms. So it offers big savings on the device production side and the installation time/cost side.
Ha. Didn't see this post before I responded to your other one :-)
$20 is a lot (I assume that’s the customer price buying them in volume). You have to save a lot of water / increase yield enough to justify that. That suggests a BOM well under a buck, probably less than $0.50.
I spent some time in this sector (at one company irrigation of almonds and stone fruit, another in wine) and the margins are very tight. Fortunately the farmers have sharp pencils.
When you think about it, farming is the perfect physical application of scaling.
And more, smaller, robots vs large tractors could put an end to monocultures. Monoculture is the result of optimizing for minimal human labour, not an optimization for yields. So when labour is free, mixed fields are the way to maximize profits
How about harvest? Machines are quite specialized, how do you see that working out?
Bigger farms overall, which is anyway the trend so they utilize economies of scale. Or machine rentals if there is plenty of need from smaller farmers.
You might run into time of use contention unless you have a ver diversified crop neighborhood or adaptable robot. Don’t harvests usually happens at the same time for all the same species of crop in an area?
Unfortunately machine rental math does not work out for most of the specialised farming equipment in areas with changing seasons — when combine harvesters are needed (at the harvest time), they are needed for everyone within the same time window.
That’s a failure of imagination. Hordes of people used to do all the work, and Industrial Age engineering (thinking) replaced them with a combination of large, specialized devices and large, specialized farm layouts. It was more efficient for the technology of the time.
But we don’t build computing like that any more. Instead of large centralized single devices we use a large amount of protean hardware with various adapts (software).
Hordes of small devices can flood through the fields, using sensors to decide at any point what to do, and can use different effectors for different tasks at different times of the year, like the humans used to do.
You mean picking each ear/grain by a single device? rofl
I didn’t mean that — I agree that would be absurd!
I mean an autonomous device that picks a row, then does the same on the next row on the way back, then maybe unloads into a hopper and continues with the next couple of rows. And you don’t one, you have 50 or a couple of hundred of them rather than one huge combine harvester.
And if you have 50 of these platforms designed to go up and down the rows they could have been doing the planting at the beginning of the season (or desuckering your vines in spring or whatever) using a different tool, so your capex isn’t tied up in a few huge single-application devices, but amortized over a whole season. And when you have a fleet, if one fails and needs maintenance it’s no more of a big deal than when one server in a datacenter fails.
I was reading that and thinking family sized farm scale. If the machines are cheaper farms can be smaller and still justify buying a machine. Asian markets have quite a few small machines for managing rice crops.
Like these: https://en.wikipedia.org/wiki/Rice_transplanter https://sda-industries.com/equipment-parts/rice-harvester/
Compare that to "small" machines sold in the US. https://www.deere.com/en/harvesting/
That's false. Homogeneity makes it easier to harvest, process, and store crops. It also drives perfect competition which brings cost down on the commodity market.
Harvesting, processing, and storing, are human labor.
They involve human labor, just like every industrial process in existence. What's your point?
Yes, the GP’s reasoning is faulty (actually, “imperfect” would be a better term), but things aren’t as clear as you put it either.
Homogeneity helps with trading commodities, no question. And commodities reduce risk by allowing a very wide fan out on both sides of a two sided market…which has advantages and disadvantages for all participants.
More along your argument, it also lets the farmer use capital better in the short term (you buy the equipment you need for your monocrop).
But if you have multimodal devices you have the opportunity to take advantage of more flexibility. You can do crop rotation to use less chemicals or to take advantage of trends in the commodity market. You can have a different mix of crops for the same reason (half corn, half row crops, though they re typically worth less). You have more flexibility to adapt to climate change. The commodity markets can handle all this, in fact they help enable it.
This isn’t magic wand — crop rotation doesn’t make sense if, say, you have an orchard. But mechanization also caused us to abandon growing multiple crops in the same field, which can have benefits and improve yield. It was just way too labor intensive. If we go back to individual “labor” (automated in this case) it could be worthwhile.
wouldn't a monoculture help the robots, too?
But it doesn’t help us, and the robots are for our benefit. Make the robots go the the extra effort.
Contrary to bizzarre claims made earlier, robots don't actually work for free. In fact, they are more staunch about getting paid than humans are. They will stop working as soon as you stop paying them. Humans, on the other hand, will usually keep working for a while until they finally give in to the realization that you aren't going to pay up.
As a result, we're still going to optimize for the most productive use of robots, just as we do for humans.
I disagree. I think we should have more human labor take over farming but on an individual level that's working much much closer to the consumption source. Think having your own farmer and food-producer in your own house or property, or perhaps shared with your small flock of neighbors.
Way too-many of the problems plaguing society atm can be solved by reducing transport and eliminating all the huge intermediate steps between our food (other other food-related products) and ourselves. Just think about how much effort is put into something simple like flour or butter or cheese (nevermind all the crazy processed stuff). The food will be more natural, it'll be healthier and with less additives, we'll be be contributing less to AGI/automation and creating actual valuable jobs, we'll be reducing the amount of plastic, fuel and electricity used for transport, storage, processing, packaging, labelling, accounting, lawyering. Every one of the major food production + distribution industries has huge support networks.
Impossible. The world is too urbanized, there simply is no space to do this for more than a few % of the population.
Maybe some problems can be solved, many more will be unsolved. Reducing our transport capacity of food increases the vulnerability to crop failures. De-centralizing processing will make it harder (read: more expensive) to test for pathogens, nutrients and ensure hygiene.
No, we would be shrinking the GDP by moving labour from highly productive sectors into agriculture. At the same time food will become much more expensive, even more so if those new employees are paid minimum wage.
How? You're simply replacing one set of steps for another, more labor-intensive one. I encourage you to visit one of those museums where people demonstrate how people in the 18th century lived for some perspective.
You didn't quite state the full conditions to achieve this reduction, so I'll do it for you. Basically we have to completely change our diets. Fresh food can only be eaten in season, and only what is locally available. We can only store food that does not need climate control to keep, so in winter there are only conserved vegetables and fruits. Not using any modern packaging and storage methods means that even in season things have to be eaten really quickly.
On the whole, your insinuation that our food distribution is some kind of unnecessary luxury that we can do away with just rubs me the wrong way. It is the reason the amount of people in famine has been dropping every decade despite a population explosion. It ensures that there are no mass-scale outbreaks of botulism, moulds and other pathogens that used to kill lots of people and waste huge quantities of food. Its efficiency (along with high productivity) guarantees that almost everyone can afford to eat sufficient nutrients even through winter.
Sure we could get some of those benefits in your agrarian fantasy, but the cost would be enormous.
If we accept subpar nutrition we could propably plant GMO potatoes and things like that all over the place
Gmo can also increase nutrition. anti gmo and anti vaccine come from theisame anti scienece background, don't fall for either. Yes deand safety studies but then use what is good.
Just because it's not 100% possible right now, doesn't mean we shouldn't work towards it.
Your first criticism as an example. "World too urbanized". Again, the solution solves a big chunk of other problems we have. One need only read HN a bit to see a bunch of them. E.g. 1. Food islands. 2. Focus on transport to get food because mom and pop stores closed and we only have Walmart. 3. Car culture.
My point is don't shoot the idea down, we have to consider how working towards this arguable ideal moves the needle in a better direction. And yes, maybe the end-goal I presented isn't 100% possible or the right direction for society. But working towards it means we solve a host of intermediate problems, with each one making things a bit better.
Sorry I'm not answering all your points, which some are 100% valid and I agree, but others are just us talking past eachother. E.g. I'm not entirely advocating for us to go to the middle-ages and churn butter for 2 hours a day. But there has to be an in-between that opens up additional options and ideas that I can't possibly envision, or articulate well-enough, or consider every angle and potential criticism.
Oh yes, taking agriculture back to where it was 2 centuries ago, when there definitely weren't any famines at all.
counterpoint: like the great chinese famine, when the government forced the country from an agrarian economy to an industrialized economy, and they fucked up the local food systems.
The same thing happened when the Soviet government forced the country from an agrarian economy to an industrialized one.
A lot of people have drawn inferences that it may have been the government, their leadership and application of ideology rather then the shift from agrarian economy.
seems to me that taking farmers away from their land will make people starve.
similar to how in the american south in the 20th century, sharecroppers were forced to work on commodity farms and didn't grow food. instead, they imported processed corn from the midwest that gave them pellagra. thanks in part to market forces of the midwest corn trade.
This is the typical utopian dream that is complete horse manure. We like to look back and think how quaint and healthy things were but they were not. While there are a lot of improvements to be had in our current supply chain, going back to smaller farms is not the way to get there.
What you described would be more costly and I don't think there is really any relationship to health. Your food would end up being more expensive as most of the things you listed cost very little in the grand scheme, labor is the most expensive part.
I haven't crunched the math or anything, but you don't feed 8 billion people with small farms unless every 10th person is willing to go farm. Currently it's more like every 150th.
Local, small-scale food production used to be the only way food was produced - people didn't eat better then, and there were many, many fewer people to feed.
There's huge variability in what can be grown where, especially if you want to reduce the amount and number of inputs that are imported from further afield. There are places that can support all the crops and livestock that provide a healthy, balanced, and sustainable human diet, but not everywhere can. What if you want to eat flour in a place where grain crops aren't tenable, or butter where cows, sheep and goats don't do well?
Producing food this way also means that we need to build houses on fertile land that's good for growing things. That happens a _lot_ where I live, and I hate the site of previously productive soil disappearing under concrete house-slabs.
You can have both large scale production and small scale production at the same time. It is actually required for survival on a large scale long term. Technologies enabling small scale farms to be more efficient are as great an enabler as the advent of industrial farming.
If you want to see less fertile land covered up make it easier for people to make money growing on their own land.
This would be utterly horrible. AGI/automation is a valuable thing while being forced to toil working the land sucks hard.
Small-scale agriculture like that is _vastly_ less efficient than industrialised agriculture. It won't create valuable jobs, it'll take labor away from valuable jobs.
Out of curiosity how does nitrogen fertilizer offset labor?
Directly, as a substitute for more labour intensive sources like manure, compost or crop rotation.
Indirectly by increasing yield per acre per day.
But in the end you have to replace at least some of the nitrogen (and other nutrients) you are taking from the field in some way. And without a major shift in consumption patterns (less meat) this will mean fertilizer, as the alternatives usually lead to a much lower yield.
I was very disappointed on my last trip to Iowa to see that most farmers weren't even bothering with cover crops.
I wonder whether genetic engineering can give nitrogen fixing abilities to plants that currently lack this ability?
You could do that, the problem is the same as in making nitrogen fertilizer in a chemical plant: energy cost. It just takes so much energy to break the nitrogen tripple bond.
Even if you made a plant that fixes nitrogen extremely efficiently, every joule of sunlight it pumps into the ground is not available as calories you harvest. And fixing nitrogen will take an amount of energy per acre on the order of what you harvested from that acre in a year.
Well, only being as efficient as existing nitrogen fixing plants (or rather their microbes) would already be quite interesting.
Btw, I don't think plants are close to optimal efficiency in terms of using sunlight. See eg C3 vs C4 plants.
My point is that you can't have corn that is as nitrogen-fixing as a legume and still produce nearly as much corn - the plant (or its microbes) will need the majority of the available photosynthesis products to fix nitrogen. This directly makes the cobs smaller.
That's true, even photovoltaic panels (which are still far away from their theoretical maximal efficiency) are an order of magnitude more efficient at pulling energy from the sun than plants are. But significantly improving photosynthesis in crop plants is far beyond our current genetic engineering ability.
And I'm not aware of any way to organically fix nitrogen that uses energy outside what is provided by photosynthesis - or gets its energy from digesting dead organic matter, which also doesn't beat the limits of photosynthetic efficiency on a per-acre basis.
I can believe that. However for people who don't want to use nitrogen fertiliser, this might still be useful.
You can see it as an alternative to clover (or manure), that happens to produce eg a bit of grain.
It's not the plants themselves that fix nitrogen but endosymbiotic microorganisms in the soil.
N-fixation does happen in the soil, but legumes have root nodules that host rhizobium bacteria and can assimilate the N much more easily
I know. For simplicity, I was talking about the plants in the same generic sense that your gut microbiome is a part of you, and the dead tissues that form your hair and skin are also a part of you.
You still need to hack up the eg cereal plants so they can actually engage in that symbiotic relationship (or perhaps actually directly fix nitrogen all by themselves, without any outside help at all).
Nitrogen can also be replenished by crop rotation. Legumes will naturally add nitrogen back.
Meat farming replaces artificial fertilizer, by providing a source of manure, so doesn't that relationship run the other way?
But having 1/4 of the land under soy beans or other locally appropriate nitrogen-fixing plants doesn't seem like it would hurt yields too much.
By growing nitrogen fixers such as peas and beans on the same fields.
Robot labor isn’t free. You pay in capital costs, energy costs to run them, and ongoing maintenance costs if you use them a lot. Environmentally, these costs might be more or less than the chemicals they replace, but it isn’t am obvious comparison.
Changing farming methods along with automation might work better, like vertical farming techniques.
Vertical farming is complete bullshit for most plants. I don't know why people keep talking about it.
Plant growth is (for most plants) limited by available energy, which comes in the form of sunlight. Sunlight is extremely bright compared to artificial light sources and extremely cheap, i.e. free. Replacing it makes no economic sense in most situations.
If we talk about producing a lot of calories to feed the starving, even most reservations go out of the window, because staple crops are staples because they are very efficient at turning sunlight into chemical energy and they need all the sunlight they can get.
It's weird, vertical farming has gotten so much hype but really only makes sense for luxury products like microgreens, and still only makes sense if you specifically want to grow them in an expensive, dense city. Even things like mature lettuces, tomatoes, and strawberries have been tried extensively and simply don't make economic sense to grow indoors in stacks the vast majority of cases.
Non-subsistence farming is basically all cap ex at this point. Farmers have Ag Ec degrees and think about cap ex first. With the price of energy on a secular decline, imagine a world with ubiquitous renewables. The robots can go to a charge point and recharge themselves.
Sorry, but in every example of vertical farming I've seen, there's nothing that actually works. Nearly all of the farms and companies I've visited and been exposed to use a lot more water and energy (in all forms) compared to a conventional farm. The only appeal I see are for places with limited agricultural land space such as Singapore or the Netherlands, or arid regions such as the Middle East or Central Asia. Even then, it's much cheaper for most of these places to simply import from abroad.
In a recent episode of Countryfile [1](popular UK BBC1 program on the country and farming) the resident farmer was mentioning both crop rotation and the issue of black grass invading his wheat fields.
The black grass was slowly out competing his cash crop and would difficult to remove (perhaps taking the entire field out of any production for a year or the use of chemicals).
Having a horde of little robots might greatly assist in manually keeping other plants at bay without indiscriminately affecting the field with chemicals (extra one-use expense, robots would last many years).
[1] https://en.wikipedia.org/wiki/Countryfile
I am searching for solutions in this field. Do you have any links to any consumer hardware for this. like drones which can cut down small invasive plants which were selected by AI?
Have you looked at laser weeding? A camera looks at the plants, an ML model identifies which plants are crop and which are weeds, and then a laser burns the weeds just enough so they die from water loss.
Research: https://ethz.ch/en/industry/industry/news/data/2022/03/laser...
Commercial product (first one I found, there are countless others): https://carbonrobotics.com/
Tertill cuts weeds but the ai is “if object is tall and firm enough to trip my bumper, turn”
This already exists! There's a company called Carbon Robotics that has a prototype of a robot that eliminates individual weeds with a lazer: https://www.youtube.com/watch?v=_2s-0wgQWXM
I'm also looking forward to this technology being widely available and helping solve the issue of herbicide run-off, and later additionally the same for pesticides and fertilization.
Not even close. The sorts of critters and diseases that pesticides combat cannot be mitigated by plucking things off plants, nor can nitrogen fertilizer be replaced with elbow grease. Identifying and removing (burning) infected plants would help, but only if each plants was isolated from its neighbors, otherwise you are just back to burning fields once infection is detected. Growing each potato inside its own little box cannot scale.
For many farmers the "right amount of water" ends up being however much is available. Crop fields are not home gardens. The amounts of water needed are measured in acre-feet. Metering it out to each corn stalk individually would certainly help, but likely fails the cost/benefit analyses at scale. A corn field has roughly 50,000 plants per acre, and commercial farm several hundred acres. That will be a heck of a lot of plastic tubing to install/maintain.
Short of the singularity happening - "labor" (even Robotic) - at this scale - is not going to be anywhere near free.
I mean, in some ways, "labor" is already "free" in agriculture if you compare current cost of labor per yield vs what you would get before the industrial revolution.
The average labor cost to farm an acre of wheat pre-industrial revolution was 50-100 hours. Today, it's <1.
Short of the singularity, we are not getting a 100x improvement from here in our lifetime.
There's not only so many 100x improvements you can make until you need a perpetual motion machine traveling faster than light...
We're not moving away from nitrogen fertilizers. Ever. Why?
Look at the following three graphs: global population, staple crop yield, and nitrogen fertilizer application.
Now overlay them. That's why.
Also, there are myriad chemical inputs that cannot be removed simply due to free labor. Sure, a robot can pluck weeds, but what about fungal and bacterial diseases?
None of the inputs to farming will ever be free. Whomever owns the robots will be charging for their labour you are only substituting one form for another. Potentially it might workout better for production numbers still tbd. Farmers these days are beholden to the agri tech companies for costs and maintenance.
That is a great dream to have. In the energy world it was supposed that prices would go to close to zero with fully adopted solar but thats an equivalent far fetched dream.