By Jan Johnson, Contributing Writer and Dan Jacobs, Senior Editor, AgriBusiness Global and CropLife
Agriculture started using modeling and forecasting hundreds of years ago, computed and analyzed by the grower’s mind. More fertilizer should equal more yield, until it doesn’t, then it’s time to change the inputs. Herbicides kill certain weeds, until they don’t, then new herbicides are sought out and used.
As the digital agricultural industry increases in pace, the job of improving yields to feed the world’s population is analyzing years of information, data points, and outcomes to create digital models for predicting the weather, climate, water availability, and soil. Growers need to prescribe preventative measures for maintaining yields and quality, rather than corrective action after damage. Digital modeling will provide information for preventative action.
“It is the notion of modeling a farm. The crops, the soil, the water, the fertilizer, the weather, all those things. Farmers are already doing that today to a varying degree. One of the main drivers of agriculture is the soil. We have soil maps for the entire United States. They're not very high resolution, but we do use them as a model of how we expect a crop to perform on a certain piece of ground,” said Rob Tiffany, Founder and CEO of Sustainable Logix, a firm dedicated to driving farm profitability, efficiency and sustainability through continual monitoring, tracking, reporting, and automation.
Tiffany participated in a panel discussion as part of Meister Media’s VISION Conference held in Glendale, AZ, on Jan 17-18, 2023. The session, “Virtual Cropping: Digital Modeling for Precise and Accurate Forecasting” also included Elia Scudiero, Research Agronomist at the University of California-Riverside, and Kathleen Glass, Vice President of Marketing for AquaSpy.
Future gains in agricultural productivity will come from the ability to create predictive models from data that will show what is happening at the micro or macro level of the farm, Tiffany said. “We want to be able to make a change before that crop is stressed, but just before it happens. Not after, because by then, we’ve lost yield or quality.”
Digital modeling works by creating a digital twin of each farm or field, then using that twin to incorporate weather, moisture, and inputs to determine the best possible outcome for that field. The basis for the digital twin comes from actual data collected along a digital thread — data collected throughout the lifecycle of crops.
Every time data is collected from the physical world, it’s fed into the digital twin. The technology to accomplish digital modeling is just beginning to match the concept. The work being done today to lay the foundation for digital twins includes large-scale modeling using sensors and crop data to predict outcomes and drive automation. It also includes strategies and interventions to improve outcomes while reducing costs and risks.
For his part, Scudiero is working to develop the ability to remotely sense the effects of the environment on plants and then automate mitigating treatments. His work earned him the 2020 Young Scholar Award from the Soil & Water Management & Conservation Division of the Soil Science Society of America.
As water becomes increasingly valuable and in short supply, the ability to provide the right amount of water at the right time for the plant to thrive becomes critical. Scudiero is focusing his research on just that topic. Of particular interest is measuring soil salinity and compensating irrigation levels. Too much salt in the soil leads to decreased yield, but up until that level, performance stays the same. Over-irrigating pushes the salt away, as does rainfall. As irrigation is costly, Scudiero wants to provide a model for growers to know how much and when they need to address soil salinity.
“This is a new approach to a very old problem,” Scudiero said. “We know that some fruits are more risk sensitive, so [growers] want to irrigate a little bit more than the crop needs, so that it’s pushing away the salt. These experiments were usually done years ago in the greenhouse and were not representative of real-life conditions. Nowadays, we can do it in the field, very large trials where we actually grow it, observe growing it, and collect the data in the background for our model.”
In the future, as the model is perfected, irrigation might be automated based on plant needs and soil salinity, which have been determined from massive databases generated by large-scale observation.
AquaSpy provides smart soil moisture probes connected to the IoT (Internet of Things). This enables growers to track water and nutrients at several levels underground. That data is transmitted to the cloud where growers can access it in real time. Used in conjunction with above ground technology like FarmQA (a suite of digital tools designed to streamline and improve core agronomy service functions), farmers can proactively manage soil moisture, reducing irrigation, and fertilizer costs.
In addition to benefitting individual growers, technology provided by companies like AquaSpy can provide additional sets of water moisture data points to SCAN (Soil Climate Analysis Network) and USCRN (U.S. Climate Reference Network). This, in turn, should accelerate the development of accurate, predictive models.
So, while digital twins are not here yet, progress on using large amounts of data coupled with analysis by artificial intelligence is quickly moving forward. Existing digital models are most often directed at preventing diseases in high-value specialty crops. For example, BLIGHTCAST is a Syngenta agronomy tool developed to predict late blight on tomatoes and potatoes based on rainfall, relative humidity, and temperature data. It recommends when growers should spray their crops.
FAST (Forecasting Alternaria solani on Tomatoes) uses hourly measurements of leaf wetness and temperature to forecast early blight on tomatoes. It recommends when to spray, and has been so effective, it has been modified for other crops.
“We’re getting to model the pests and the microbe activity under the soil,” said Glass. “So, this is evolution. We have the technology of satellites with more granularity and different wavelengths to gather more data. Then you start to be able to take many factors into account when making predictions in a model.”
Tiffany and Glass agree that farmers are understandably reluctant to believe in the future of digital modeling, because of the many unfulfilled promises made over the years by Silicon Valley types.
“I talk with growers, and they all say, ‘Five years ago, those city slickers, all those kids from Silicon Valley came out here to show us all this IoT and whatever,” Tiffany said. “It turned out to be an expensive science experiment. They didn't always know what they were doing. They were just throwing a lot of new tech at the wall, seeing what would stick. They didn't quite have their act together. Since then, the technology has gotten simpler and easier to use. It's got to be low cost with a business model that makes it affordable for the grower. And we’re working on it. I know we’ll get there, but we have to measure first. Because you can’t improve what you can’t measure.”
