[davehcker]

Vertical indoor farm to reach the highest throughout possible per cubic meter are, using only non-GMO plants by discovering the right phenomics- https://hexafarms.com

Vertical indoor farms are getting a lot of attention in the recent times, but the issue is the lack of plant expertise. Even if you were to go through all the literature, you would never find a holistic study that takes into account all the optimal factors for specific plant growth. For example, for lettuce, the best you will get would be EC, Ph, Light Intensity, CO2 ppm over an average range. However, approaching it from a perspective of 'systems' design where all these things play a role (often in an interaction with all factors) is still missing. For example, what part of the artificial light spectrum + nutrition level + air composition would be most optimal is still missing.

I'm a computer scientist by training and I'm trying to solve this with ML. It's a really hard problem, but I'm doing it. I have a mini-farm setup in my appt where I collect the data, but hopefully I'm getting some more seed-money to build a 10m^2 farm to be able to demonstrate the optimization. My goal is to hit as high as 370 kilos of herbs per m^2 (or 2.5 cubic meter) per year from only a four layer farm.

[new_here]

The Dutch are apparently the second largest vegetable exporter in the world (!) using these kinds of techniques. Lots of interesting research happening at Wageningen University and Research. A greenhouse that keeps getting mentioned is Duijvestijn Tomatoes.

Further reading here if you're interested:

1. https://www.dw.com/en/could-high-tech-netherlands-style-farm...

2. https://www.nationalgeographic.com/magazine/2017/09/holland-...

I agree though, there's not enough info out there about an integrated approach. Perhaps it's proprietary.

[tasuki]

Ah yes, the Dutch and Belgian tomatoes: they're atrocious. I'm from Eastern Europe, and our local variety of tomatoes is way tastier. Or any other variety for that matter.

[Hitton]

I agree about the taste, but I don't think it's caused by variety taste difference. Problem is that when tomatoes are imported from further away, they are picked and transported (more) unripe and later exposed to ethylene gas to ripen closer to consumer. Being grown using hydroponics or bags of mineral wool certainly doesn't help with the taste either.

[NoOneNew]

I can agree that many people who eat salads, will not care about the difference in taste between hydroponics and well composted soil. Especially when it comes to the cost difference. But that doesn't mean there isn't a difference, because there is. Any home gardener can tell you that the exact same lettuce variety grown in well composted soil, over produced commercial soil void of natural nutrients (and biological ecosystem in the soil) and hydroponics, are all difference in taste. I think Butter Lettuce varieties are the most intense and shocking in difference (my experience).

Economically speaking, for wide scale production, most people don't care about the flavor of their lettuce or spinach. Which I understand and don't have a qualm with. I just have a problem with people who have never held a shovel in their lives try to act they know everything about farming and make wide sweeping judgements (what's that fallacy about lack of knowledge and thinking you know it all?). When you grow it yourself in a good environment, you enjoy eating leafy greens alone because you can taste actual flavor.

What a lot of people outside of agriculture don't know is the movement to recreating the top soil back to a healthy state. Commercial farmland soil is borderline clay and sand, especially compared to well maintained soil. Chemical fertilizers only go so far. A wide variety of decomposing organic matter is needed in soil to help maintain it. Along with letting a field sit for a few years with a cover crop (or variety of cover crops to speed up the process) is needed. Adding in grazing livestock is even better.

Mostly, I know you all think farming and agricultural science are stupid, numbskull pursuits because you're all techies. The obvious and only way to save agriculture is to use silicon chips, plastic and metal to fix it all. But "dirt" agriculture is extremely in-depth and complex. Especially the last 2 decades worth of research has been insane due to the realization that our "tried and true" commercial farming operations are more unsustainable than our dependency on fossil fuels. I don't see an inherent problem with vertical farming. I have a problem with the hubris that over commercialization is the only method of fixing these problems, even though that's the reason we have the problems to begin with.

[eecc]

I will also add the constant aggression by the scorching sun of Southern Italy. Why do you think they’re supposed to be full of antioxidants and other healthy nutrients? Coincidentally for your consumer pleasure, or did the plants evolve them to survive weeks upon weeks of implacable 40C temperatures and a flood of UVA-B.

[new_here]

From the first article:

> they grow almost 70 kilograms (154 pounds) of tomatoes per square meter. That's at least 10 times the average yield from an open field in Spain or Morocco, but with eight times less water and practically no chemical pesticides.

A promising method with a yield like this shouldn't be abandoned just because the taste isn't as good. This is just something the market will force them to improve, if customers don't continue to buy them. Personally, I've never tasted a tomato that I would label as atrocious so I'm now intrigued to try them :)

[Mumps]

Please tell me "seed-money" was a pun intended moment.

Jokes aside, from a biology perspective why the aversion to GMO? From an ML perspective, what are you optimizing for - maximized growth rate?

[davehcker]

It was!!! Personally, I have no aversion towards GMO. But in the end, it's the customers. It's already so hard to convince that food grown in clean and sterilized nutrient medium is far better than the romantic soil everyone is clinging to; GMO would take way more convincing. However, there are tastes that are indeed only found in the 'old' seeds, so there is do see the aversion non-GMO from customer side.

In terms of optimization, here are some:

1. What is the optimal time for getting a lettuce plant until harvest without juicing it up with nitrates?

2. What parameters could double the functional components of my mint (think about essential oils) and basil plants just by proper timing in stress and nutrition. These are already questions that botany departments have worked on- I want to bring them out in commercial setting (and may be a bit better).

3. Does back-radiation i.e. reflected light from plant leaves help in measuring plant well-being?

4. What's the right grow medium

5. In general, I BELIEVE, that there is a sub-optimal application (as in wastage) of light (which is roughly 20-30% of indoor farm expense), sub-optimal production in terms of the harvest we get. An improvement in harvest timing by a day would still be a very big volume once you scale it to bigger grow area; more importantly, I believe plant experts are good (even though very rare and expensive), but a DeepFarmer might be able to do better (and this is my main bet), both in terms of scaling and expertise.

[rorykoehler]

The one place I'd be happy to see GMO utilised is in siloed and controlled indoor farms.

[fsflover]

> using only non-GMO plants

What's the point in such restriction? AFAIK, GMO was never proven harmful.

https://en.wikipedia.org/wiki/Genetically_modified_crops#Con...

[davehcker]

OP here; not kidding, but once you get down to talking to your actual customers, one has only so much energy to convince people that GMO is not necessarily bad. May be I'm harming myself by being so honest here- but the general consumer is so pleased to know that our produce is so good and is not 'the plastic GMO thing'. This, so far, has been what I've found in over 10 restaurant/gourmet/general consumer interviews.

[fsflover]

You are probably right. But directly advertising your product as "GMO-free" helps spread fake-news that GMO may be harmful. Please don't do it.

[consumer451]

> fake-news that GMO may be harmful.

I would argue that saying all GMO products are equal and the entire concept is safe is also not correct. To me, "GMOs are totally safe" sounds a lot like saying "chemicals are totally safe."

There are multiple techniques, many possible product categories, with many possible safety outcomes. The safety relies on regulation by U.S. agencies which are mostly compromised by regulatory capture in a market with trillion dollar IP potential.

It is not insane anti-science to question the deployment of GMO products into the food chain and ecosystem.

[fsflover]

See my link above with scientific references. In the same way you can add poison (or herbicides) in non-GMO crops. It does not prove anything.

See also: https://xkcd.com/641/.

[consumer451]

I agree with your sentiment, but I fail to see how it applies to what I was replying to.

[xchaotic]

"By the year 2025, 63% of the world’s population will be living in cities" I wonder if Covid will revise those trends. Where I live (rural), there's plenty of unused land that needs a lot let contortions to farm (cheaper) but is indeed further away from the mouths to be fed in cities. How is the math behind urban farms vs simply shipping food into the city?

[davehcker]

True, but I can't really predict the outcome due to covid. Just saw Dubai post-covid-onset, and to my eyes, nothing has changed much from food-supply-chain side.

I personally believe that permaculture would actually be the best solution overall, but our modern economy's pace and expectations would always keep such methods at bay. But at the same time, for leafy produce, and herbs, I think proper vertical farming would not only make it more affordable but also sustainable too. For the math, the rough estimates are production per m^2 (2-4kg on ground vs 70-400kg indoor farm), 10% lettuce in solid won't see the dining table i.e. they'd die, here there's no loss, off-season non-perennial produce, no problem for a vertical farm, the expenses on operations change too. Overall, if done properly, a very high-tech vertical farm should be able to break even in 2-3 yrs, even assuming a sales at no premium (which is very easy given the high-quality) i.e. at the shipped food i.e. the status-quo. But once people get used to the high-quality, and wholesalers get to enjoy the short supply chain due to indoor farms, I think the remote once will face a fierce competition, at least for select crops.

[fakedang]

> Just saw Dubai post-covid-onset, and to my eyes, nothing has changed much from food-supply-chain side.

Forget Dubai, it's natural that a city in the desert that relies on tourism way too much will keep itself open. Government even mandated schools to open (no one's sending their kids, except the really desperate parents), mandated malls to stay open and cancel temperature checks, mandated employers to open up offices. They just recently closed up and put in all restrictions once again (although not European levels).

I think a lot of countries will see shifts from major cities to cheaper cities (as long as they are safer and have basic services). The only reason people (like my parents) are still staying in Dubai is because it has gotten cheaper - rents are falling, home prices are falling, there is a visible glut, and it's a buyer's market right now.

[marcosdumay]

> I wonder if Covid will revise those trends.

I imagine COVID may possibly have an impact on our megacities trend (even though it had many dying signals already), but I don't believe it may push people into rural areas. Rural life isn't for everybody.

[DennisP]

Rural areas are getting slammed pretty hard by covid. I don't think that will put the brakes on urbanization all that much.

[xchaotic]

perhaps you're looking at US? Generally I see a trend of people moving back to the countryside as remote work is by default now. London, UK is pretty empty too - all the restaurants and offices closed - means all the food that used to be consumed inside the city is now eaten somewhere in the commuter belt. That's a major shift...

[blaser-waffle]

That's do to a comparatively lower rate of mask usage and fewer medical resources.

[CodeGlitch]

I think the advantage is more in the use of far less water and virtually no pesticides - 2 things which will become more important as the climate changes.

[rorykoehler]

There are other considerations at play. We need to rewild nature and minimise human footprint if we want to keep the world livable.

[roel_v]

I've worked on this in the past too (not as rigorous as it sounds you are). My main problem: how do we define our optimum function, and how do we quantify the variables going into it? How do you do it? I assume you're not sitting there and tasting, comparing and scoring 25 salad samples every 3 days...

[dr_kiszonka]

What a great project! I was wondering if the details of your home set-up are available anywhere online?

[Triv888]

Is the hardware and software used open?

[catmanjan]

Very interesting, I have a small traditional farm - have you done any work with staple crops?

[mads]

I have been interested in this for a long time and also had a small setup in my apartment. I have been interested in getting back into this lately. What kind of mini farm setup do you have there? How big?

[davehcker]

Right now (re-starting almost the fourth time), my goal is to get consistent 1. images 2. co2, ec, ph, temperature, humidity, light intensity/quality readings. Anyone putting in money (besides me) hesitated until now because they couldn't see what was in my head. So I'm remaking the setup with data-collection in mind first. It's almost shameful to confess that it is an 8 bed farm only :/ And this will be the setup for next 2 months. Once you've a 1200 plant bed (which is only 10 metre^2 with four layers), I think you will be able to demonstrate the efficiencies with the available data. ps: You can get a harvest every 19 days, roughly.

Computer vision is a big chunk here, and me being no expert, I'm trying to have the hardware setup right so I'd have to do little on the software side of data processing.

If you're doing on your own, and don't want to spend a lot, I'd just say that almost everything can be done with off the shelf boards and sensors.

[nolite]

How mature is this field? I get the impression that all the existing companies doing this have cracked a secret. Can a hacker-type really make significant headway in this space still? (I'm really really interested in this)

[Nathanael_M]

I love this! Is there somewhere where I could follow your project? Have you experimented at all comparing flavours? Could I purchase some of your herbs anywhere? This is super exciting to me.

[WrtCdEvrydy]

> I have a mini-farm setup in my appt

Now this could be interesting...

[cbames89]

Sounds like you care quite a bit. Although perhaps here you're defining success as monetary as opposed to adding reliable knowledge.

[5560675260]

Sorry for bothering if you already know this, but a lot of resources on your site point to localhost:8000 and fonts are just missing.

[msaharia]

Would you be publishing your research or data or both? Would you be interested in sharing it privately? I would love to know more!

[stuntkite]

I like this project and I like you. Thank you for sharing! I'll be sure to keep and eye on it and possibly contribute.