The Creator & AI: The Good, The Bad, The Agriculture

The Creator, the AI epic sweeping across movie screens this week,  raises all sorts of questions about the future of humanity in a world where machines just can’t seem to get beyond projecting the extremes of human behavior onto, well, the world. With that in mind, let’s take a look at the influence of artificial intelligence on agriculture, and the implications for a live-able planet.

The Creator: A Visually Stunning Whodunnit

The Creator unspools against the backdrop of a nuclear holocaust. As for who pushed the button, go see the movie and find out.

The studio behind the film is 20th Century Studios (Disney’s 2020 rebrand of the familiar 20th Century Fox house), which is not giving anything away except to tease the idea that someone came up with the brainy plan of ending all wars by ending humanity. As for who did that, go see the movie.

Regardless of who (or what) did do it, the action packed thriller has gotten rave reviews for stunning visuals and use of a relatively simple consumer-grade cinematic camera, the Sony FX3. The relatively small, lightweight camera is available at electronics stores everywhere at the relatively affordable price of around $3,500, so you can run right out and try to replicate some of the shots. Or…go see the movie.

On The Bright Side, AI Is Good For Agriculture

Partly due to its adept use of the lightweight FX3 in visually storytelling, The Creator manages to mine new turf in the never ending war between humans and their creations. Whether or not good or evil will prevail is beyond the scope of this article, but speaking of turf, stakeholders in the agriculture industry are already coming down on the side of artificial intelligence.

One recent example comes from the University of Tokyo, where a research team has been studying how automated drones can deploy AI to optimize crop harvesting.

“If farmers know the ideal time to harvest crop fields, they can reduce waste, which is good for them, for consumers and the environment,” explains Associate Professor Wei Guo, of the school’s Laboratory of Field Phenomics.

“But optimum harvest times are not an easy thing to predict and ideally require detailed knowledge of each plant; such data would be cost and time prohibitive if people were employed to collect it.” Professor Guo cautions.

Guo and his team came up with a solution in the form of inexpensive drones equipped with imaging and analytic software that can identify and catalogue every plant in a field, and predict the growth characteristics of each one.

As explained by Guo, a farmer’s income from a particular crop can fall somewhere between 3.7% and 20.4% if harvesting takes place even just a day before the optimal time, so taking out the guesswork could make a significant difference.

In addition to potentially boosting harvest yields, the system is also a cost-saver.

“The drones carry out the imaging process multiple times and do so without human interaction, meaning the system requires little in terms of labor costs,” the school explains.

That sounds simple enough, but the devil is in the details. The team had to spend a considerable amount of time teaching their machines how to interpret the images, proving once again that human input is the key.

“Collecting the image data itself is relatively trivial, but given the way plants move in the wind and how the light changes with time and the seasons, the image data contains a lot of variation that machines often find hard to compensate for,” the school explains.

More Good News About AI & Agriculture: The Water Angle

Another interesting twist on the theme of AI in agriculture comes from the University of Florida Institute of Food and Agricultural Sciences, where Dr. Sandra Guzmán has been applying to machine learning to help resolve irrigation and hydrology issues related to agriculture.

Guzmán leads the Smart Irrigation and Hydrology program at the school’s Indian River Research and Education Center. She works hands-on with farmers in an epicenter of the state’s citrus industry, helping them to incorporate new technology to increase productivity.

The transition to AI technology may take some time, and farmers can hesitate to invest in new equipment. However, Charles Brown, of the University of Florida Technology Transfer Center, sees a similarity with existing technology. At one time, Brown explains, standard irrigation sensing equipment also seemed futuristic and hard to wrap one’s head around.

“Guzmán can work with producers to get them started with smart irrigation or to help them create the system they need to control irrigation and to generate the data needed for the advanced tools she can provide,” Brown explains.

Guzmán’s signature product, called IrrigMonitor, is described as decision support system software. It collects soil, weather, and other data from a variety of different sensor in the field.

“The software allows the grower to quickly assess the water status of the topsoil layers where most plant roots are located,” Brown explains. “This can guide the grower to irrigate more frequently at lower volumes.”

Among other rising issues, the AI-based system can be deployed to curb the impacts of citrus greening, the common name of the serious citrus disease Huanglongbing, which was first found in Florida as recently as 1998.

More & Better AI For Agriculture

Dr. Guzmán’s work is supported by the US Department of Agriculture as part of a broader AI research program under the wing of the National Institute of Food and Agriculture.

“The AI activities supported through a variety of NIFA programs advance the ability of computer systems to perform tasks that have traditionally required human intelligence, including machine learning, data visualization, natural language processing and interpretation, intelligent decision support systems, autonomous systems, and novel applications of these techniques to agriculture and food production,” USDA explains.

The emphasis on AI may appear to run counter to the regenerative agriculture trend, which draws from centuries of indigenous experience to focus on soil and water conservation. However, to the extent that AI can enhance indigenous knowledge rather than steamroll over long term sustainability, that’s a good thing.

In addition, the practice of growing crops within fields of solar panels — the emerging field of agrivoltaics — is providing new opportunities to deploy AI for optimizing both solar cell conversion efficiency and crop yields (see more CleanTechnica coverage here).

Stay tuned for more on that. Among other projects, in 2021 the UDSA launched a four-year, multi-institution agrivoltaics research program spearheaded by the University of Illinois, aimed at demonstrating how the combo of solar panels and agriculture operations can provide bottom line benefits to farmers.

Follow me tinamcasey on Bluesky, Threads, Post, LinkedIn, and Spoutible.