Autonomous, indoor farming gives a boost to crops
The glass-encased cabinet looks like a display meant to hold reasonably priced watches, or drugstore beauty creams shipped from France. But instead of this stagnant merchandise, each of its five shelves is overgrown with leaves — moss-soft pea sprouts, spikes of Lolla rosa lettuces, pale bok choy, dark kale, purple basil or red-veined sorrel or green wisps of dill. The glass structure isn’t a cabinet, but rather a “micro farm.”
The gadget is on display at the Richmond, Virginia headquarters of Babylon Micro-Farms, a company that aims to make indoor farming in the U.S. more accessible and sustainable. Babylon’s soilless hydroponic growing system, which feeds plants via nutrient-enriched water, allows chefs on cruise ships, cafeterias and elsewhere to provide home-grown produce to patrons, just seconds after it’s harvested. Currently, there are over 200 functioning systems, either sold or leased to customers, and more of them are on the way.
The chef-farmers choose from among 45 types of herb and leafy-greens seeds, plop them into grow trays, and a few weeks later they pick and serve. While success is predicated on at least a small amount of these humans’ care, the systems are autonomously surveilled round-the-clock from Babylon’s base of operations. And artificial intelligence is helping to run the show.
Babylon piloted the use of specialized cameras that take pictures in different spectrums to gather some less-obvious visual data about plants’ wellbeing and alert people if something seems off.
Imagine consistently perfect greens and tomatoes and strawberries, grown hyper-locally, using less water, without chemicals or environmental contaminants. This is the hefty promise of controlled environment agriculture (CEA) — basically, indoor farms that can be hydroponic, aeroponic (plant roots are suspended and fed through misting), or aquaponic (where fish play a role in fertilizing vegetables). But whether they grow 4,160 leafy-green servings per year, like one Babylon farm, or millions of servings, like some of the large, centralized facilities starting to supply supermarkets across the U.S., they seek to minimize failure as much as possible.
Babylon’s soilless hydroponic growing system
Courtesy Babylon Micro-Farms
Here, AI is starting to play a pivotal role. CEA growers use it to help “make sense of what’s happening” to the plants in their care, says Scott Lowman, vice president of applied research at the Institute for Advanced Learning and Research (IALR) in Virginia, a state that’s investing heavily in CEA companies. And although these companies say they’re not aiming for a future with zero human employees, AI is certainly poised to take a lot of human farming intervention out of the equation — for better and worse.
Most of these companies are compiling their own data sets to identify anything that might block the success of their systems. Babylon had already integrated sensor data into its farms to measure heat and humidity, the nutrient content of water, and the amount of light plants receive. Last year, they got a National Science Foundation grant that allowed them to pilot the use of specialized cameras that take pictures in different spectrums to gather some less-obvious visual data about plants’ wellbeing and alert people if something seems off. “Will this plant be healthy tomorrow? Are there things…that the human eye can't see that the plant starts expressing?” says Amandeep Ratte, the company’s head of data science. “If our system can say, Hey, this plant is unhealthy, we can reach out to [users] preemptively about what they’re doing wrong, or is there a disease at the farm?” Ratte says. The earlier the better, to avoid crop failures.
Natural light accounts for 70 percent of Greenswell Growers’ energy use on a sunny day.
Courtesy Greenswell Growers
IALR’s Lowman says that other CEA companies are developing their AI systems to account for the different crops they grow — lettuces come in all shapes and sizes, after all, and each has different growing needs than, for example, tomatoes. The ways they run their operations differs also. Babylon is unusual in its decentralized structure. But centralized growing systems with one main location have variabilities, too. AeroFarms, which recently declared bankruptcy but will continue to run its 140,000-square foot vertical operation in Danville, Virginia, is entirely enclosed and reliant on the intense violet glow of grow lights to produce microgreens.
Different companies have different data needs. What data is essential to AeroFarms isn’t quite the same as for Greenswell Growers located in Goochland County, Virginia. Raising four kinds of lettuce in a 77,000-square-foot automated hydroponic greenhouse, the vagaries of naturally available light, which accounts for 70 percent of Greenswell’s energy use on a sunny day, affect operations. Their tech needs to account for “outside weather impacts,” says president Carl Gupton. “What adjustments do we have to make inside of the greenhouse to offset what's going on outside environmentally, to give that plant optimal conditions? When it's 85 percent humidity outside, the system needs to do X, Y and Z to get the conditions that we want inside.”
AI will help identify diseases, as well as when a plant is thirsty or overly hydrated, when it needs more or less calcium, phosphorous, nitrogen.
Nevertheless, every CEA system has the same core needs — consistent yield of high quality crops to keep up year-round supply to customers. Additionally, “Everybody’s got the same set of problems,” Gupton says. Pests may come into a facility with seeds. A disease called pythium, one of the most common in CEA, can damage plant roots. “Then you have root disease pressures that can also come internally — a change in [growing] substrate can change the way the plant performs,” Gupton says.
AI will help identify diseases, as well as when a plant is thirsty or overly hydrated, when it needs more or less calcium, phosphorous, nitrogen. So, while companies amass their own hyper-specific data sets, Lowman foresees a time within the next decade “when there will be some type of [open-source] database that has the most common types of plant stress identified” that growers will be able to tap into. Such databases will “create a community and move the science forward,” says Lowman.
In fact, IALR is working on assembling images for just such a database now. On so-called “smart tables” inside an Institute lab, a team is growing greens and subjects them to various stressors. Then, they’re administering treatments while taking images of every plant every 15 minutes, says Lowman. Some experiments generate 80,000 images; the challenge lies in analyzing and annotating the vast trove of them, marking each one to reflect outcome—for example increasing the phosphate delivery and the plant’s response to it. Eventually, they’ll be fed into AI systems to help them learn.
For all the enthusiasm surrounding this technology, it’s not without downsides. Training just one AI system can emit over 250,000 pounds of carbon dioxide, according to MIT Technology Review. AI could also be used “to enhance environmental benefit for CEA and optimize [its] energy consumption,” says Rozita Dara, a computer science professor at the University of Guelph in Canada, specializing in AI and data governance, “but we first need to collect data to measure [it].”
The chef-farmers can choose from 45 types of herb and leafy-greens seeds.
Courtesy Babylon Micro-Farms
Any system connected to the Internet of Things is also vulnerable to hacking; if CEA grows to the point where “there are many of these similar farms, and you're depending on feeding a population based on those, it would be quite scary,” Dara says. And there are privacy concerns, too, in systems where imaging is happening constantly. It’s partly for this reason, says Babylon’s Ratte, that the company’s in-farm cameras all “face down into the trays, so the only thing [visible] is pictures of plants.”
Tweaks to improve AI for CEA are happening all the time. Greenswell made its first harvest in 2022 and now has annual data points they can use to start making more intelligent choices about how to feed, water, and supply light to plants, says Gupton. Ratte says he’s confident Babylon’s system can already “get our customers reliable harvests. But in terms of how far we have to go, it's a different problem,” he says. For example, if AI could detect whether the farm is mostly empty—meaning the farm’s user hasn’t planted a new crop of greens—it can alert Babylon to check “what's going on with engagement with this user?” Ratte says. “Do they need more training? Did the main person responsible for the farm quit?”
Lowman says more automation is coming, offering greater ability for systems to identify problems and mitigate them on the spot. “We still have to develop datasets that are specific, so you can have a very clear control plan, [because] artificial intelligence is only as smart as what we tell it, and in plant science, there's so much variation,” he says. He believes AI’s next level will be “looking at those first early days of plant growth: when the seed germinates, how fast it germinates, what it looks like when it germinates.” Imaging all that and pairing it with AI, “can be a really powerful tool, for sure.”
Everyone Should Hear My COVID Vaccine Experience
On December 18th, 2020, I received my first dose of the Pfizer mRNA vaccine against SARS-CoV-2. On January 9th, 2021, I received my second. I am now a CDC-card-carrying, fully vaccinated person.
The build-up to the first dose was momentous. I was scheduled for the first dose of the morning. Our vaccine clinic was abuzz with excitement and hope, and some media folks were there to capture the moment. A couple of fellow emergency physicians were in the same cohort of recipients as I; we exchanged virtual high-fives and took a picture of socially distanced hugs. It was, after all, the closest thing we'd had to a celebration in months.
I walked in the vaccine administration room with anticipation – it was tough to believe this moment was truly, finally here. I got a little video of my getting the shot, took my obligate vaccine selfie, waited in the observation area for 15 minutes to ensure I didn't have a reaction, and then proudly joined 1000s of fellow healthcare workers across the country in posting #ThisIsMyShot on social media. "Here we go, America!"
The first shot, though, didn't actually do all that much for me. It hurt less than a flu shot (which, by the way, doesn't hurt much). I had virtually no side effects. I also knew that it did not yet protect me. The Pfizer (and Moderna) data show very clearly that although the immune response starts to grow 10-12 days after the first shot, one doesn't reach full protection against COVID-19 until much later.
So when, two days after my first shot, I headed back to work in the emergency department, I kept wondering "Will this be the day that I get sick? Wouldn't that be ironic!" Although I never go without an N95 during patient care, it just takes one slip – scratching one's eyes, eating lunch in a break room that an infected colleague had just been in – to get ill. Ten months into this pandemic, it is so easy to get fatigued, to make a small error just one time.
Indeed, I had a few colleagues fall ill in between their first and second shots; one was hospitalized. This was not surprising, but still sad, given how close they had come to escaping infection.
Scientifically speaking, one doesn't need to feel bad to develop an immune response. Emotionally, though, I welcomed the symptoms as proof positive that I would be protected.
This time period felt a little like we had our learner's permit for driving: we were on our way to being safe, but not quite there yet.
I also watched, with dismay, our failures as a nation at timely distribution of the vaccine. On December 18th, despite the logistical snafus that many of us had started to highlight, it was still somewhat believable that we would at least distribute (if not actually administer) 20 million doses by the New Year. But by December 31, my worst fears about the feds' lack of planning had been realized. Only 14 million doses had gone to states, and fewer than 3 million had been administered. Within the public health and medical community, we began to debate how to handle the shortages and slow vaccination rates: should we change prioritization schemes? Get rid of the second dose, in contradiction to what our FDA had approved?
Let me be clear: I really, really, really wanted my second dose. It is what is supported by the data. After living this long at risk, it felt frankly unfair that I might not get fully protected. I waited with trepidation, afraid that policies would shift before I got it in my arm.
At last, my date for my second shot arrived.
This shot was a little less momentous on the outside. The vaccine clinic was much more crowded, as we were now administering first doses to more people, as well as providing the second dose to many. There were no high fives, no media, and I took no selfies. I finished my observation period without trouble (as did everyone else vaccinated the same day, as is typical for these vaccines). I walked out the door planning to spend a nice afternoon outdoors with my kids.
Within 15 minutes, though, the very common side effects – reported by 80% of people my age after the second dose – began to appear. First I got a headache (like 52% of people my age), then body aches (37%), fatigue (59%), and chills (35%). I felt "foggy", like I was fighting something. Like 45% of trial participants who had received the actual vaccine, I took acetaminophen and ibuprofen to stave off the symptoms. There is some minimal evidence from other vaccines that pre-treatment with these anti-inflammatories may reduce antibodies, but given that half of trial participants took these medications, there's no reason to make yourself suffer if you develop side effects. Forty-eight hours later, just in time for my next shift, the side effects magically cleared. Scientifically speaking, one doesn't need to feel bad to develop an immune response. Emotionally, though, I welcomed the symptoms as proof positive that I would be protected.
My reaction was truly typical. Although the media hype focuses on major negative reactions, they are – statistically speaking – tremendously rare: fewer than 11/million people who received the Pfizer vaccine, and 3/million who received the Moderna vaccine, developed anaphylaxis; of these, all were treated, and all are fine. Compare this with the fact that approximately 1200/million Americans have died of this virus. I'll choose the minor, temporary, utterly treatable side effects any day.
Now, more than 14 days after my second dose, the data says that my chance of getting really sick is, truly, infinitesimally low. I don't have to worry that each shift will put me into the hospital. I feel emotionally lighter, and a little bit like I have a secret super-power.
But I also know that we are not yet home free.
I may have my personal equivalent of Harry Potter's invisibility cloak – but we don't yet know whether it protects those around me, at all. As Dr. Fauci himself has written, while community spread is high, there is still a chance that I could be a carrier of infection to others. So I still wear my N95 at work, I still mask in public, and I still shower as soon as I get home from a shift and put my scrubs right in the washing machine to protect my husband and children. I also won't see my parents indoors until they, too, have been vaccinated.
At the end of the day, these vaccines are both amazing and life-changing, and not. My colleagues are getting sick less often, now that many of us are a week or more out from our second dose. I can do things (albeit still masked) that would simply not have been safe a month ago. These are small miracles, for which I am thankful. But like so many things in life, they would be better if shared with others. Only when my community is mostly vaccinated, will I breathe easy again.
My deepest hope is that we all have – and take - the chance to get our shots, soon. Because although the symbolism and effect of the vaccine is high, the experience itself was … not that big a deal.
New Hope for Organ Transplantation: Life Without Anti-Rejection Drugs
Rob Waddell dreaded getting a kidney transplant. He suffers from a genetic condition called polycystic kidney disease that causes the uncontrolled growth of cysts that gradually choke off kidney function. The inherited defect has haunted his family for generations, killing his great grandmother, grandmother, and numerous cousins, aunts and uncles.
But he saw how difficult it was for his mother and sister, who also suffer from this condition, to live with the side effects of the drugs they needed to take to prevent organ rejection, which can cause diabetes, high blood pressure and cancer, and even kidney failure because of their toxicity. Many of his relatives followed the same course, says Waddell: "They were all on dialysis, then a transplant and ended up usually dying from cancers caused by the medications."
When the Louisville native and father of four hit 40, his kidneys barely functioned and the only alternative was either a transplant or the slow death of dialysis. But in 2009, when Waddell heard about an experimental procedure that could eliminate the need for taking antirejection drugs, he jumped at the chance to be their first patient. Devised by scientists at the University of Louisville and Northwestern University, the innovative approach entails mixing stem cells from the live kidney donor with that of the recipient to create a hybrid immune system, known as a chimera, that would trick the immune system and prevent it from attacking the implanted kidney.
The procedure itself was done at Northwestern Memorial Hospital in Chicago, using a live kidney donated by a neighbor of Waddell's, who camped out in Chicago during his recovery. Prior to surgery, Waddell underwent a conditioning treatment that consisted of low dose radiation and chemotherapy to weaken his own immune system and make room for the infusion of stem cells.
"The low intensity chemo and radiation conditioning regimen create just enough space for the donor stem cells to gain a foothold in the bone marrow and the donor's immune system takes over," says Dr. Joseph Levanthal, the transplant surgeon who performed the operation and director of kidney and pancreas transplantation at Northwestern University Feinberg School of Medicine. "That way the recipient develops an immune system that doesn't see the donor organ as foreign."
"As a surgeon, I saw what my patients had to go through—taking 25 pills a day, dying at an early age from heart disease, or having a 35% chance of dying every year on dialysis."
A week later, Waddell had the kidney transplant. The following day, he was infused with a complex cellular cocktail that included blood-forming stem cells derived from his donor's bone marrow mixed what are called tolerance inducing facilitator cells (FCs); these cells help the foreign stem cells get established in the recipient's bone marrow.
Over the course of the following year, he was slowly weaned off of antirejection medications—a precaution in case the procedure didn't work—and remarkably, hasn't needed them since. "I felt better than I had in decades because my kidneys [had been] degrading," recalls Waddell, now 54 and a CPA for a global beverage company. And what's even better is that this new approach offers hope for one of his sons who has also inherited the disorder.
Kidney transplants are the most frequent organ transplants in the world and more than 23,000 of these procedures were done in the United States in 2019, according to the United Network for Organ Sharing. Of this, about 7,000 operations are done annually using live organ donors; the remainder use organs from people who are deceased. Right now, this revolutionary new approach—as well as a similar strategy formulated by Stanford University scientists--is in the final phase of clinical trials. Ultimately, this research may pave the way towards realizing the holy grail of organ transplantation: preventing organ rejection by creating a tolerant state in which the recipient's immune system is compatible with the donor, which would eliminate the need for a lifetime of medications.
"As a surgeon, I saw what my patients had to go through—taking 25 pills a day, dying at an early age from heart disease, or having a 35% chance of dying every year on dialysis," says Dr. Suzanne Ildstad, a transplant surgeon and director of the Institute for Cellular Therapeutics at the University of Louisville, whose discovery of facilitator cells were the basis for this therapeutic platform. Ildstad, who has spent more than two decades searching for a better way, says, "This is something I have worked for my entire life."
The Louisville group uses a combination of chemo and radiation to replace the recipient's immune and blood forming cells with that of the donor. In contrast, the Stanford protocol involves harvesting the donor's blood stem cells and T-cells, which are the foot soldiers of the immune system that fight off infections and would normally orchestrate the rejection of the transplanted organ. Their transplant recipients undergo a milder form of "conditioning" that only radiates discrete parts of the body and selectively targets the recipient's T-cells, creating room for both sets of T-cells, a strategy these researchers believe has a better safety profile and less of a chance of rejection.
"We try to achieve immune tolerance by a true chimerism," says Dr. Samuel Strober, a professor of medicine for immunology and rheumatology at Stanford University and a leader of this research team. "The recipients immune system cells are maintained but mixed in the blood with that of the donor."
Studies suggest both approaches work. In a 2018 clinical trial conducted by Talaris Therapeutics, a Louisville-based biotech founded by Ildstad, 26 of 37 (70%) of the live donor kidney transplant recipients no longer need immunosuppressants. Last fall, Talaris began the final phase of clinical tests that will eventually encompass more than 120 such patients.
The Stanford group's cell-based immunotherapy, which is called MDR-101 and is sponsored by the South San Francisco biotech, Medeor Therapeutics, has had similar results in patients who received organs from live donors who were either well matched, such as one from siblings, meaning they were immunologically identical, or partially matched; Talaris uses unrelated donors where there is only a partial match.
In their 2020 clinical trial of 51 patients, 29 were fully matched and 22 were a partial match; 22 of the fully matched recipients didn't need antirejection drugs and ten of the partial matches were able to stop taking some of these medications without rejection. "With our fully matched, roughly 80% have been completely off drugs up to 14 years later," says Strober, "and reducing the number of drugs from three to one [in the partial matches] means you have far fewer side effects. The goal is to get them off of all drugs."
But these protocols are limited to a small number of patients—living donor kidney recipients. As a consequence, both teams are experimenting with ways to broaden their approach so they can use cadaver organs from deceased donors, with human tests planned in the coming year. Here's how that would work: after the other organs are removed from a deceased donor, stem cells are harvested from the donor's vertebrae in the spinal column and then frozen for storage.
"We do the transplant and give the patient a chance to recover and maintain them on drugs," says Ildstad. "Then we do the tolerance conditioning at a later stage."
If this strategy is successful, it would be a genuine game changer, and open the door to using these protocols for transplanting other cadaver organs, including the heart, lungs and liver. While the overall procedure is complex and costly, in the long run it's less expensive than repeated transplant surgeries, the cost of medications and hospitalizations for complications caused by the drugs, or thrice weekly dialysis treatments, says Ildstad.
And she adds, you can't put a price tag on the vast improvement in quality of life.