‘Farm of the future’ project marries microbiology and machine learning

Science Daily – looking into how farms of the future will feed a projected 9.8 billion people by 2050 – reports on a “smart farm” project which marries microbiology and machine learning. The aim is to reduce the need for chemical fertilisers and enhance soil carbon uptake, thus improving the long-term viability of the land while increasing crop yields.

The report features a farm in Arkansas, growing soybeans, corn and rice, that is aiming to be the most scientifically advanced farm in the world.

Soil samples are run through powerful machines to have their microbes genetically sequenced, drones are flying overhead taking hyperspectral images of the crops, and soon supercomputers will be crunching the massive volumes of data collected.

Scientists at the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab), working with the University of Arkansas and Glennoe Farms, hope this project, which brings together molecular biology, biogeochemistry, environmental sensing technologies, and machine learning, will revolutionise agriculture and create sustainable farming practices that benefit both the environment and farms.

If successful, the scientists envision being able to reduce the need for chemical fertilisers and enhance soil carbon uptake, thus improving the long-term viability of the land, while at the same time increasing crop yields.

Understanding the role of microbes in the health of the soil is a major focus of the research.

“Microbes are a critical component of soil health and productivity,” said scientist Ben Brown.

“By understanding how microbes work and modifying the environments where they function, we can eventually engineer microbial communities to enhance soil productivity. What’s more, Berkeley Lab’s research is showing that healthy soils are more resilient to system shocks such as climate change, drought, and insects.”

A key challenge for advancing these goals is the recognition of the significant spatial variability of soil properties within a single field and between fields.

The “AR1K Smart Farm” project has brought together a range of expertise to focus on a 1,000-acre farm near Stuttgart, Arkansas, as a test bed.

The project is co-led by Haruko Wainwright, an expert in environmental monitoring and estimation methodologies in Berkeley Lab’s Earth and Environmental Sciences Area, and Ben Brown, an expert in machine learning and microbial analysis in the Biosciences Area.

Science Daily notes the world’s population is forecast by the United Nations to grow to 9.8 billion by 2050. Feeding these people will require raising food production by more than 70 per cent.

Yet industrialised farming practices have depleted a majority of the USA’s agricultural land of active carbon and a balanced microbial ecosystem. This is reflected in measurements of organic matter that average only 1 to 2 per cent in most farmland, compared to historic levels of around 10 per cent.

“Our farmers are dependent on a heavy prescription of genetically modified seeds, fertiliser, chemical herbicides, and pesticides to render a profitable crop,” said Jay McEntire, manager of Glennoe Farms.

“For the farmer this dependency raises their input costs and increases their economic risk. For the landowner depleted soils and chemical regimes represent risks for both economic and environmental sustainability.”

Building on Berkeley Lab’s ENIGMA and Microbes to Biomes initiatives, the project scientists aim to develop and evaluate microbial amendments, which can be thought of as “probiotics for soil,” to replace the carbon, phosphorus, and other nutrients that have been lost.

As Science Daily points out, repeated use of bulk fertilisers and chemicals over the years have depleted the soils and caused other environmental damage, creating a vicious cycle that makes the current model of industrial agriculture potentially unsustainable — and increasingly expensive as more and more chemical and bulk salt-based fertiliser additives are required each year.

What’s more, the world’s supply of phosphorus is limited.

But Berkeley Lab is pursuing a microbial solution.

“The good news is, there are lots and lots of microbes that have enzymes called phytases that are capable of resolubilizing inorganic phosphorus,” which is essentially the “leftovers” in the ground after plants take up what they need from the rock phosphorus, says Brown.

While the concept of microbial amendments is not new — commercial products are on the market — a predictive understanding of how the soil microbiome interacts with and affects plant growth is lacking.

“There are millions of species of microbes per cubic centimeter of soil,” Brown said.

“As you approach the plant root and its interior tissues, you go from millions to dozens. So plants do an exceptional job of farming their microbiomes. They release materials, including antimicrobial compounds, to selectively kill undesirable microbes, and they release food to incentivise beneficial microbes. It’s a highly symbiotic and enormously complex interaction, and we understand almost nothing about it.”

The challenge will be in figuring out the cause-and-effect relationships between the microbial amendments and plant growth.

“You’re trying to connect events at timescales relevant to molecules to events that occur over the course of a six-month growing season,” said Brown. “You’re trying to bridge something like 18 orders of magnitude across spatiotemporal scales. That is seriously nontrivial.”

Hyperspectral sensors on the drones will be able to detect light reflectance from the plants and see hundreds of channels of spectra, from the visible to near infrared.

“The human eye has only three channels — red, green, and blue,” said Wainwright. “You can see if a leaf looks yellow or green. But with hundreds of channels you can measure carbon and nitrogen content, and you can tell a lot about plant health, plant disease, or leaf chemistry, all of which affect crop yield.”

In addition, surface geophysical techniques are used to map soil electrical properties in 3-D, which greatly controls soil microbial activities.

Machine learning is the tool that will tie all the data together.

“The team science approach pioneered at Berkeley Lab is being put to use to integrate all the information within the machine learning context,” said Wainwright. “Our ultimate goal is to provide actionable intelligence to the farming community.”

Currently farmers have no such information, even though services and products have sprung up providing various “big data” solutions.

“All the private companies have a big incentive to lock their own data sets, so they can’t be used in conjunction with other data sets,” Wainwright said. “That’s where the public sector, like Berkeley Lab, can step in. We’re not incentivised by profit.”

The scientific challenge is formidable but not insurmountable.

“We think it’s a tractable problem, and we’re hoping to prove it in the next year,” Brown said.

The Berkeley Lab team is collaborating with the University of Arkansas with support from Laboratory Directed Research and Development funding and collaboration with Glennoe Farms, the landowners, and M2Capital Partners LLC.

Source: Science Daily. 


Our precious soil – are we treating it like dirt?


Registrations are being accepted here for  a discussion on soil and soil policy at Lincoln University involving broadcaster Kim Hill and a group of expert panellists.

The question at issue: are we letting our most precious resource slip through our fingers?

The panellists who will draw on their extensive expertise to discuss this question are:

• Trish Fraser: Plant & Food Research

• Ants Roberts: Ravensdown

• Mike Hedley: Massey University

• Andy MacFarlane: Farmer/Company Director

Event Details

Date: Thursday 22 March

Time: 7.30pm, doors open 6.30pm

Venue: Stewart Building, Lincoln University (no. 62 or C3 on the campus map)

Cost: $5 koha. Refreshments and nibbles provided. (Alcoholic beverages will be provided from a cash bar.)

Biographies of the panellists can be found here.

Earthworm count is encouraged in efforts to improve farm productivity

Bala Tikkisetty, a sustainable agriculture advisor at Waikato Regional Council, has gone out to bat for the humble earthworm in an article distributed to news media.

He explains that soils without enough of the right type of earthworms are usually poorly structured and tend to develop a turf mat or thatch of slowly decomposing peat-like material at the surface. Old dung and dead plant material lie about the surface. These factors can naturally inhibit pasture and crop production.

Lower producing grasses are often more evident than ryegrass on these types of soils as well. Pasture growth is slow to start in spring and stops early in autumn.

Plant nutrients tend to remain locked in the organic layer and there is poor absorption of applied fertiliser.

Plants roots in such soils are relatively shallow and pastures are therefore susceptible to drought.

And, as indicated earlier, water runs off this type of pasture more easily rather than being absorbed into the soil, increasing water quality problems.

To help avoid these types of problems, soils should have a good diversity of relevant earthworm species.

The most common introduced earthworm in New Zealand is Aporrectodea calignosa, a topsoil dweller, Tikkisetty says.

This earthworm grows up to 90mm long and may vary in colour from grey to pink or cream.

Another common introduced earthworm is Lumbricus rubellus, a surface dweller. Often found under cow pats, this earthworm will grow up to 150mm long. It is reddish-brown or reddish-purple with a pale underside and flattened tail. Aporrectodea longa live in burrows as deep as 2-3m below the surface.

Earthworm functional groups are: Epigeic earthworms (i.e. Lumbricus rubellus) feed on organic matter on the soil surface and do not form permanent burrows; Endogeic earthworms (i.e.Aporrectodea caliginosa) ingest topsoil and its associated organic matter, forming semi-permanent burrows; Anecic earthworms (i.e. Aporrectodea longa) draw organic matter from the soil surface into their deep, permanent burrows to feed on.

The article includes this illustration from AgResearch.


The article is designed to encourage an earthworm count to  let farmers know if they have enough of the right type.

Counts should preferably be done late winter to early spring when soil moisture and temperature conditions are ideal. Counts can be done by taking out a 20cm cube of soil with a spade. Aim to have an earthworm number of between 30 and 35 in that cube.


Life under the surface can be studied via systems using microchips

Researchers at Lund University in Sweden have developed new systems to study the life of microorganisms in the ground. Without any digging, the researchers can use microchips to see and analyse an invisible world that is filled with more species than any other ecosystem.

In one spoonful of soil there are more microorganisms (fungi and bacteria) than there are people on Earth. But it is an impenetrable world for researchers.

“Our soil chips could revolutionise how we study microbiological processes in the ground. Finally, we can follow what actually happens down the ground under a microscope in real-time,” says Edith Hammer, associate senior lecturer the Department of Biology in Lund.

For a long time, experiments using petri dishes and real soil have been the traditional way of exploring life in the ground.

What the researchers have done is create models of soil structures and ecosystems in microchips. With these, the researchers can study the life that takes place in the labyrinth systems of the soil — systems which they are now able to build on the same scale as the microorganisms themselves.

Using a technology called microfluidics, the researchers can produce relatively realistic soil models. The models are made of a silicone polymer and simulate the structure of the soil with components of organic and inorganic material, mazelike passageways, water and unevenly distributed nutrients on which the microorganisms feed.

“Our systems are transparent — this is probably what fascinates people the most. It allows us to look directly at all processes and behaviours in the ground. We see how the microorganisms move, search for food, choose where they are going and how they compete with each other, but also cooperate,” says Edith Hammer.

“The microorganisms are ecosystem engineers. We see how they change their environment by creating or blocking passageways with their cells. The bacteria in the soil tunnel system have to fight hard against the forces of water to move at all,” she says.

The researchers are confident the method will increase knowledge of the structures in the soil and the importance of the organisms living there. Eventually, this will lead to better recommendations for how to use soil in a sustainable way that preserves the ground’s functions.

The new microchips were developed in collaboration between biologists and engineers at the faculties of science and engineering in Lund, together with their colleagues in Amsterdam.

PGP review may result in greater focus on soil and water issues

The Primary Growth Partnership may continue under the Labour-led Government but with a greater focus on soil and water issues.

Agriculture Minister Damien O’Connor told AgScience:

“I have indicated there will be a review of PGP.  Millions have been invested across different sectors and of course there is good that will have come from it. But identifying that is not so easy.

“So we’ve got to make sure that wherever taxpayers are spending money across the rural and agricultural sectors, they are getting good value for that money because just as farmers expect to use their money wisely, so does government.

“And we’ve got to make sure that we don’t drop the ball.”

O’Connor said there was a need for a greater understanding of the value of soil and all aspects of its protection and development.

Similarly, with water science “there’s a  hell of a lot for us still  to learn”.

Not enough investment had been put into those areas.

On the role of state grants for research and development, O’Connor said the Government hadn’t committed to any approach, other than to boost the Sustainable Farming Fund, “which we think has been a very successful approach – we like small smart initiatives.”

With the PGP, large amounts of money often had been invested for business-as-usual projects

“We are going to balance those,” O’Connor said.

“Firstly, we will have a review and look at the system .

“I know PGP has improved over time in terms of oversight and accountability, but the question still remains what is the best way to spend taxpayers money for the future of agriculture.”

Without a vision and strategic plan “we’re not quite sure if we are spending that money in the right direction”.


Decomposing leaves are shown to be a source of nitrous oxide

Michigan State University scientists have pinpointed a new source of nitrous oxide, a greenhouse gas that’s more potent than carbon dioxide.

The culprit?

Tiny bits of decomposing leaves in soil, according to account of the research released by the univerity (HERE).

The discovery, featured in the current issue of Nature Geoscience, could help refine nitrous oxide emission predictions as well as guide future agriculture and soil management practices.

“Most nitrous oxide is produced within teaspoon-sized volumes of soil, and these so-called hot spots can emit a lot of nitrous oxide quickly,” said Sasha Kravchenko, MSU plant, soil and microbial scientist and lead author of the study.

“But the reason for occurrence of these hot spots has mystified soil microbiologists since it was discovered several decades ago.”

Part of the vexation was due, in part, to scientists looking at larger spatial scales. It’s difficult to study and label an entire field as a source of greenhouse gas emissions when the source is grams of soil harboring decomposing leaves.

Changing the view from binoculars to microscopes will help improve N2O emission predictions, which traditionally are about 50 percent accurate, at best. Nitrous oxide’s global warming potential is 300 times greater than carbon dioxide, and emissions are largely driven by agricultural practices.

“This work sheds new light on what drives emissions of nitrous oxide from productive farmlands,” said John Schade, a programme director for the National Science Foundation’s Long-Term Ecological Research program, which co-funded the research with NSF’s earth sciences division.

“We need studies like this to guide the creation of sustainable agricultural practices necessary to feed a growing human population with minimal environmental impact.”

To unlock the secrets of these N2O hotspots, Kravchenko and her team took soil samples from MSU’s Kellogg Biological Station Long-term Ecological Research site.

Then in partnership with scientists from the University of Chicago at Argonne National Laboratory, they examined the samples at Argonne’s synchrotron scanning facilities, a much more powerful version of a medical CT scanner. The powerful X-ray scanner penetrated the soil and allowed the team to accurately characterize the environments where N2O is produced and emitted.

“We found that hotspot emissions happen only when large soil pores are present,” Kravchenko said. “The leaf particles act as tiny sponges in soil, soaking up water from large pores to create a micro-habitat perfect for the bacteria that produce nitrous oxide.”

Not as much N2O is produced in areas where smaller pores are present. Small pores, such as in clay soils, hold water more tightly so that it can’t be soaked up by the leaf particles. Without additional moisture, the bacteria aren’t able to produce as much nitrous oxide. Small pores also make it harder for the gas produced to leave the soil before being consumed by other bacteria.

“This study looked at the geometry of pores in soils as a key variable that affects how nitrogen moves through those soils,” said Enriqueta Barrera, program director in NSF’s earth sciences division. “Knowing this information will lead to new ways of reducing the emission of nitrous oxide from agricultural soils.”

More specifically, future research will review which plant leaves contribute to higher N2O emissions. Plants with more nitrogen in their leaves, such as soybeans, will more than likely give off more N2O as their leaves decompose. Researchers also will look at leaf and root characteristics and see how they influence emissions.

Soil scientist goes myth-busting about feeding the world with fewer chemicals

Three big myths that impede our ability to restore degraded soils and feed the world using fewer chemicals are tackled in an essay in The Conversation, an online publication covering the latest research.

The essay, written by David R. Montgomery, has been reprinted in Scientific American (HERE).

Montogmery is a Professor of Earth and Space Sciences at the University of Washington in Seattle, where he is a member of the Quaternary Research Center. Wikipedia

One of the biggest modern myths about agriculture he now confronts is that organic farming is inherently sustainable,

It can be, but it isn’t necessarily.

Montgomery then addresses other issues which he says must be recognised to restore degraded soils to feed the world using fewer agrochemicals.

He embarked on a six-month trip to visit farms around the world to research his forthcoming book, “Growing a Revolution: Bringing Our Soil Back to Life.

The innovative farmers he met showed him that regenerative farming practices can restore the world’s agricultural soils.

In both the developed and developing worlds, these farmers rapidly rebuilt the fertility of their degraded soil, which then allowed them to maintain high yields using far less fertiliser and fewer pesticides.

Their experiences, and the results that I saw on their farms in North and South Dakota, Ohio, Pennsylvania, Ghana and Costa Rica, offer compelling evidence that the key to sustaining highly productive agriculture lies in rebuilding healthy, fertile soil.

But the journey also led Montgomery to question three pillars of conventional wisdom about today’s industrialised agrochemical agriculture:


Not so. He cites a recent UN Food and Agriculture Organization (report which says family farms produce over three-quarters of the world’s food. The FAO also estimates that almost three-quarters of all farms worldwide are smaller than one hectare – about 2.5 acres, or the size of a typical city block.

Of course the world needs commercial agriculture, unless we all want to live on and work our own farms. But are large industrial farms really the best, let alone the only, way forward?


While mechanisation can provide cost and labor efficiencies on large farms, bigger farms do not necessarily produce more food. Large farms excel at producing a lot of a particular crop – like corn or wheat – but small diversified farms produce more food and more kinds of food per hectare overall.


The most extensive yield comparison to date, a 2015 meta-analysis of 115 studies, found that organic production averaged almost 20 per cent less than conventionally grown crops, a finding similar to those of prior studies.

But the basis for claims that organic agriculture can’t feed the world depend as much on specific farming methods as on the type of farm.

Moreover about a quarter of all food produced worldwide is never eaten. Each year the United States alone throws out 133 billion pounds of food, more than enough to feed the nearly 50 million Americans who regularly face hunger.

So even taken at face value, the oft-cited yield gap between conventional and organic farming is smaller than the amount of food we routinely throw away.

In the upshot, Montgomery says he no longer sees debates about the future of agriculture as simply conventional versus organic.

He now sees adopting farming practices that build soil health as the key to a stable and resilient agriculture.

And the farmers he visited had cracked this code, adapting no-till methods, cover cropping and complex rotations to their particular soil, environmental and socioeconomic conditions.

Whether they were organic or still used some fertilizers and pesticides, the farms I visited that adopted this transformational suite of practices all reported harvests that consistently matched or exceeded those from neighboring conventional farms after a short transition period.

Another message was as simple as it was clear: Farmers who restored their soil used fewer inputs to produce higher yields, which translated into higher profits.