Researchers from the University of Illinois have proposed a method to measure farmers’ willingness to adopt digital tools for sustainable production.
Agricultural producers are faced with a dual challenge, increasing output for a growing world population whilst reducing negative impacts on the environment. Digital tools and Artificial Intelligence (AI) can assist sustainable production, but farmers must weigh opportunities and risks when deciding whether to embrace such tools.
In a new paper, titled ‘Digital transformation for a sustainable agriculture in the United States: Opportunities and challenges,’ researchers from the University of Illinois have proposed a method to measure farmers’ willingness to adopt digital agricultural tools.
The study explores a variety of sustainability challenges for US agriculture and why it is difficult to address those challenges with conventional technologies.
The paper was published in the journal Agricultural Economics.
Adopting digital tools in agriculture
“Digital and AI technologies can play a role in moving us to a more sustainable future, but there are barriers to usage,” explained Madhu Khanna, Professor in Agricultural and Consumer Economics (ACE) and Director of the Institute for Sustainability, Energy and Environment (iSEE) at the University of Illinois.
“Farmers are typically cautious of adopting new technology until the benefits have been well demonstrated and uncertainties have been reduced, and they see their neighbours and other peers adopting.”
The paper’s authors are all part of the Center for Digital Agriculture (CDA) and the USDA National Institute of Food and Agriculture/National Science Foundation’s AIFARMS Institute at the University of Illinois. These projects aim to promote the application of Artificial Intelligence toward a future of sustainable farming.
Benefits of digital agriculture
Digital tools can offer site-specific management guidelines and compile large amounts of information, allowing production efficiency to increase and reducing environmental harm. Tools such as precision irrigation systems can monitor crop and soil conditions to ensure site-specific watering. Information about crop health and soil fertility can be provided by AI to help adjust input application rates and reduce nitrogen runoff.
Digital tools can also help address farm labour shortages. Small robots that can move under the canopy can facilitate seeding, diagnostics, site-specific fertilisation, and mechanical weeding to reduce pesticide usage. Soil health can also be improved by under-canopy robots as they can seed cover crops between rows.
Barriers to technology uptake
Although these innovative tools offer benefits such as lower costs and improved yield, upfront investments are required, and farmers must acquire new skills and knowledge to operate them. Many digital tools are still in the early development stages, and results may not be instantaneous. The team found that there are limited reward programmes for farmers’ uptake of these tools, and they are often not enough to cover the cost of adoption.
“Existing research suggests that in addition to economic factors, behavioural factors play a big role in technology adoption. Even though something may look profitable, there are often hidden costs or hidden barriers, such as concerns about the risk or how long it might take to get the payback. It’s important to consider all of those behavioural factors as we’re thinking about the implementation of these new technologies,” Khanna stated.
Predicting willingness to adopt digital agriculture practices
Instead of focusing on technology adoption that has already occurred like in previous studies, Khanna’s team developed a new approach to predict willingness to adopt the digital tools, based on dynamic analysis.
“We recommend combining survey-based methods with spatial and temporal computer simulation methods where we can model the effect of adoption decisions on the ecosystem. This allows us to capture the feedback loop between decisions today and environmental outcomes tomorrow, which then affects subsequent decisions,” said Shadi Atallah, Associate Professor in ACE and co-author of the paper.
“For example, managing herbicide resistance in the long run by using robots for non-chemical weeding illustrates how costs and benefits are dynamic. Outcomes are influenced by the decisions farmers make, and also the decisions their neighbours are making.”
The researchers presented farmers with choice cards that outline a variety of scenarios, such as, what the neighbours are doing, the level of weeds, and the cost of the technology. For the survey, each participant was given a subset of cards presenting different combinations. The data from the survey is then combined with agent-based modelling, which captures individual differences at the farmer level, rather than the population level. The dynamic effects of farmers’ decisions over time are then modelled by computer simulations.
“In a nutshell, we’re advocating to move away from static analysis to more spatially dynamic analysis of adoption, and we conduct computational experiments on how policy will affect the adoption of technologies for a more sustainable agriculture,” concluded Atallah.
The researchers are currently conducting a survey of new technology adoption for cover crops with a random sample of farmers.