Humans have physically reconfigured half of the world’s land to grow just eight staple crops: maize (corn), soy, wheat, rice, cassava, sorghum, sweet potato and potato. They account for the overwhelming majority of calories that individuals world wide devour. As global population rises, there’s pressure to expand production even further.

Many experts argue that further expanding modern industrialized agriculture – which relies heavily on synthetic fertilizer, chemical pesticides and high-yield seeds – isn’t the correct way to feed a growing world population. In their view, this approach isn’t sustainable ecologically or economically, and farmers and scientists alike feel trapped inside this technique.

Corn’s evolution into a world commodity shows how industrialized agriculture has transformed farming.

How can societies develop a food system that meets their needs and can also be more healthy and diverse? It has proved hard to scale up alternative methods, comparable to organic farming, as broadly as industrial agriculture.

In a recent study, we considered this problem from our perspectives as a computer scientist and a crop scientist. We and our colleagues Bryan Runck, Adam Streed, Diane R. Wang and Patrick M. Ewing proposed a technique to rethink how agricultural systems are designed and implemented, using a central idea from computer science – abstraction – that summarizes data and ideas and organizes them computationally, so we are able to analyze and act upon them without having to continuously examine their internal details.

Big output, big impacts

Modern agriculture intensified over just a number of many years within the mid-Twentieth century – a blink of an eye fixed in human history. Technological improvements led the best way, including the event of synthetic fertilizer and statistical methods that improved plant breeding.

These advances made it possible for farms to provide much larger quantities of food, but on the expense of the environment. Large-scale agriculture has helped drive climate change, polluted lakes and bays with nutrient runoff and accelerated species losses by turning natural landscapes into monoculture crop fields.

Many U.S. farmers and agricultural researchers would really like to grow a wider range of crops and use more sustainable farming methods. But it’s hard for them to work out what latest systems could perform well, especially in a changing climate. Lower-impact farming systems often require deep local knowledge, plus an encyclopedic understanding of plants, weather and climate modeling, geology and more.

That’s where our latest approach is available in.

Monoculture farming, like this Iowa soybean field shown during harvest, has contributed to the decline of bees and other pollinators by reducing their food sources.
Joe Raedle/Getty Images

Farms as state spaces

When computer scientists take into consideration complex problems, they often use an idea called a state space. This approach mathematically represents the entire possible ways wherein a system might be configured. Moving through the space entails making selections, and people selections change the state of the system, for higher or worse.

As an example, consider a game of chess with a board and two players. Each configuration of the board at a moment in time is a single state of the sport. When a player makes a move, it shifts the sport to a different state.

The whole game might be described by its “state space” – all possible states the sport may very well be in through valid moves the players make. During the sport, each player is looking for states which are higher for them.

We can consider an agricultural system as a state space in a specific ecosystem. A farm and its layout of plant species at any moment in time represent one state in that state space. The farmer is looking for higher states and attempting to avoid bad ones.

Both humans and nature shift the farm from one state to a different. On any given day, the farmer might do a dozen various things on the land, comparable to tilling, planting, weeding, harvesting or adding fertilizer. Nature causes minor state transitions, comparable to plants growing and rain falling, and rather more dramatic state transitions during natural disasters comparable to floods or wildfires.

Climate change is altering the zones wherein major crops like corn and wheat might be grown, reducing yields in some cases and increasing them in others.

Finding synergies

Viewing an agricultural system as a state space makes it possible to broaden selections for farmers beyond the limited options today’s farming systems offer.

Individual farmers don’t have the time or ability to do trial and error for years on their land. But a computing system can draw on agricultural knowledge from many various environments and schools of thought to play a metaphorical chess game with nature that helps farmers discover the very best options for his or her land.

Conventional agriculture limits farmers to a number of selections of plant species, farming methods and inputs. Our framework makes it possible to contemplate higher-level strategies, comparable to growing multiple crops together or finding management techniques which are best suited to a specific piece of land. Users can search the state space to contemplate what mixture of methods, species and locales could achieve those goals.

For example, if a scientist desires to test five crop rotations – raising planned sequences of crops on the identical fields – that every last 4 years, growing seven plant species, that represents 721 potential rotations. Our approach could use information from long-term ecological research to assist find the very best potential systems to check.

One area where we see great potential is intercropping – growing different plants in a mix or close together. Many combos of specific plants have long been known to grow well together, with each plant helping the others not directly.

The most familiar example is the “three sisters” – maize, squash and beans – developed by Indigenous farmers of the Americas. Corn stalks act as trellises for climbing bean vines, while squash leaves shade the bottom, keeping it moist and stopping weeds from sprouting. Bacteria on the bean plants’ roots provide nitrogen, a necessary nutrient, to all three plants.

Cultures throughout human history have had their very own favored intercropping systems with similar synergies, comparable to tumeric and mango or millet, cowpea and ziziphus, commonly often known as red date. And latest work on agrivoltaics shows that combining solar panels and farming can work surprisingly well: The panels partially shade crops that grow underneath them, and farmers earn extra income by producing renewable energy on their land.

Modeling alternative farm strategies

We are working to show our framework into software that individuals can use to model agriculture as state spaces. The goal is to enable users to contemplate alternative designs based upon their intuition, minimizing the costly trial and error that’s now required to check out latest ideas in farming.

Today’s approaches largely model and pursue optimizations of existing, often unsustainable systems of agriculture. Our framework enables discovery of recent systems of agriculture after which optimization inside those latest systems.

Users also will give you the chance to specify their objectives to a synthetic intelligence-based agent that may perform a search of the farm state space, just as it’d search the state space of a chessboard to choose winning moves.

Modern societies have access to many more plant species and rather more details about how different species and environments interact than they did a century ago. In our view, agricultural systems aren’t doing enough to leverage all that knowledge. Combining it computationally could help make agriculture more productive, healthy and sustainable in a rapidly changing world.

This article was originally published at