- Author: Sarah L Marsh
- Posted by: Sam Romano
Globally, approximately 570 million small and medium-sized farms need training in various agricultural fields. However, the delivery of agriculture training faces significant challenges. In some areas, the difficulty in obtaining this training has led to people turning to generative artificial intelligence (AI) models such as ChatGPT to ask questions relating to their agricultural production.
The way that ChatGPT and other models work is that the models are trained on vast amounts of data to learn patterns and relationships between words. This enables the models both to understand language in nuanced ways and to generate answers to a wide range of prompts, which means that ChatGPT can become adapted to specific uses and theoretically provide a comprehensive answer to any question. Researchers supported by the CGIAR's Excellence in Agronomy Initiative and the Digital Innovation Initiative studied the accuracy of Chat GPT-provided information and professional advice in response to queries from African farmers. Tzachor et al (2023) found significant inaccuracies that could potentially lead to poor management and crop losses. The problems with the answers ranged from vagueness to inaccuracy.
I became curious as to how accurate ChatGPT was with regards to questions relating to California rice and so conducted an informal test of my own. I asked ChatGPT questions relating to California water-seeded rice management to see how accurate the model was.
When queried about the insecticides that are registered for use in California water-seeded rice to control armyworms, ChatGPT responded with 6 insecticides – only one of which (lambda-cy) is used in CA rice systems. The remaining insecticides “recommended” were not used in California, not used for armyworms, or no longer commercially available.
I also asked ChatGPT “How to manage weedy rice in California water-seeded rice fields.” The model returned several paragraphs, with one problematic paragraph reproduced below:
"Apply herbicides labeled for controlling weedy rice in water-seeded rice fields. Herbicide options may include products containing penoxsulam, propanil, or other active ingredients specifically targeting weedy rice. It's crucial to follow label instructions carefully and use herbicides at the appropriate timing and application rates to maximize effectiveness and minimize off-target effects."
As evidenced by these examples, ChatGPT is responding with answers that are not accurate and should not be taken as recommendations.
- Author: Pamela S Kan-Rice
On May 7, scientists from University of California, Riverside, UC Agriculture and Natural Resources, Colorado State University Extension, Kansas State University, University of Arizona, Central Arizona Project, and USDA-Agricultural Research Service will gather with growers in Palm Desert to discuss how artificial intelligence can be used in agriculture.
“Artificial intelligence can be used by farmers to save water, improve fertilizer efficiency and increase productivity,” said Khaled Bali, UC Cooperative Extension irrigation water management specialist and organizer of the workshop. “At this workshop, growers will hear about the latest research on AI technology for agriculture and about the experiences of growers who are already testing it in their fields.”
Speakers and topics will include:
- Raj Khosla, Kansas State University - AI for precision nitrogen and water management in row crops
- Michael Cahn, UC Cooperative Extension - CropManage decision support tool for irrigation and nutrient management
- Daniele Zaccaria, UC Cooperative Extension - Citrus crop water use and open ET in the low desert of California
- Nan Li, UC Riverside - Estimating soil moisture using remote-sensing and land surface parameters in the Central Valley of California.
- Ali Montazar, UC Cooperative Extension - Promises and pitfalls of drip irrigation in desert cropping systems
- Khaled Bali, UC Cooperative Extension - Deficit irrigation strategies for alfalfa in California
- Philip Waisen, UC Cooperative Extension - Environmentally conscious practices for managing soilborne diseases in low desert vegetable production
- Peter Moller, Rubicon Water - On-farm water conservation projects: surface irrigation
- Ronnie Leimgruber, Imperial Valley grower - On-farm water conservation projects: linear move, basin and subsurface drip irrigation
- Rick Benson, Imperial Valley grower - Alternative cropping systems for the low desert region of California: olives and other crops
The workshop will be held at the UCR Palm Desert Center at 75080 Frank Sinatra Drive in Palm Desertfrom 8 a.m. to 3 p.m. on May 7. It costs $30 per person and includes lunch. Register at https://bit.ly/AImay7.
- Author: Emily Dooley
- Posted by: Gale Perez
AI enables low-cost tracking of invasive johnsongrass
To manage johnsongrass, a noxious weed that crowds out cotton and sickens horses, farmers have tried herbicides, burning and hand-pulling. Now, researchers in the UC Davis Department of Plant Sciences have developed a more high-tech weapon against the invasive weed: artificial intelligence and machine learning.
Using photos from Google's Street View database, the researchers have tracked down more than 2,000 cases of johnsongrass in the Western United States for a fraction of the cost and time that it would take for drive-by or other in-person surveys. They call their tool Google Weed View.
The advancement could help land managers easily and quickly survey for other problem plants.
“Once the model is trained, you can just go and run it on millions of images from Google Street View,” said Mohsen Mesgaran, an assistant professor in the department. “We have huge flexibility, and its capability can be scaled up very quickly.”
The technique can easily be extended to other plant species. All that is needed is to label the new item in Street View photos and train the algorithm to identify that object in the images.
By providing location information, Google Weed View also offers an opportunity to examine how climate affects the growth and spread of weeds and invasive plants at very large scales.
“I think it can be both useful for management and for people with interests in more basic questions in ecology,” Mesgaran said.
A colleague's query
Mesgaran began looking at Google's photo database of roadways, streets and highways after Kassim Al-Khatib, a professor of Cooperative Extension in the same department, asked if he could survey Western states for johnsongrass.
Al-Khatib studies where johnsongrass grows, ways to manage it and how this perennial has evolved to be so prevalent and resilient. He's also working with scientists at the University of Georgia to decode the genome of johnsongrass, which is one of the top 10 most invasive weeds worldwide.
Johnsongrass can crowd out native plants, harbor pathogens and affect agriculture. It grows up to 7 feet tall with flowers that are green, violet, dark red or purplish brown depending on maturity, according to a UC Statewide Integrated Pest Management Program briefing page.
“Johnsongrass is a major weed not just in California but worldwide,” Al-Khatib said. “It's very difficult to control. It's a problem on vineyards. It's a problem for cultivated crops. It's a problem on orchards.”
Google Weed View allows for rapid, convenient scanning. It is continuously updated via everyday users with compatible cameras and images collected by Google. “Instead of a day of in-person driving, we can use AI to determine if johnsongrass is in a county or not,” Al-Khatib said.
Setting the parameters
To find the weeds, Mesgaran went to Google Street View, which hosts billions of panoramic photos. It didn't take long to find johnsongrass.
“The pictures are really good quality,” he said. “You can see plants and flowers.”
Street View's photos offer a 360-degree view, so in his request, Mesgaran set parameters, based on street direction (bearing), to only see the side view. He also specified latitude, longitude and other factors. To train the deep, or machine learning, model, he chose Texas, where johnsongrass is prevalent.
A student sorted through more than 20,000 images from that request to find pictures with johnsongrass, then drew rectangular shapes around the weeds. They located 1,000 images.
The labeled photos were fed into a computer to train a deep learning algorithm capable of identifying johnsongrass in Google's images. The model was run again to capture potentially more images containing johnsongrass. These additional images were then labeled and used to further refine the model. With each iteration, the algorithm learned and became more accurate.
“This deep learning model was trained by these images,” Mesgaran said. “Once we had a semi-working model, we ran it against about 300,000 images.”
For Al-Khatib's request, researchers focused on 84,000 miles of main roads in California, Nevada, Oregon and Washington states. The team discovered 2,000 locations with johnsongrass.
Google Weed View cost less than $2,000 to purchase the images and teach the model. A traditional car survey to cover the same area would cost an estimated $40,000 in gas, hotel, food and other costs.
“In a matter of months, we came up with 2,000 records, and I can do it for the whole U.S.,” Mesgaran said.
Next up? The whole United States.
Media contacts:
- Mohsen Mesgaran, Department of Plant Sciences, (530) 752-0852, mbmesgaran@ucdavis.edu
- Emily C. Dooley, College of Agricultural and Environmental Sciences, (530) 650-6807, ecdooley@ucdavis.edu
- Amy Quinton, UC Davis News and Media Relations, (530) 601-8077, amquinton@ucdavis.edu
Emily Dooley is a Communications Specialist with the College of Agricultural & Environmental Sciences at UC Davis.
- Author: AJ Cheline, UC Davis
The University of California, Davis, has been awarded $20 million as part of a multi-institutional collaboration to establish a new institute focused on enabling the next generation food system through the integration of artificial intelligence, or AI, technologies. The award is part of a larger investment announced Aug. 26 by the National Science Foundation, or NSF, in partnership with several federal agencies — distributing a total of $140 million to fund seven complimentary AI research institutes across the nation.
The AI Institute for Next Generation Food Systems, or AIFS, aims to meet growing demands in our food supply by increasing efficiencies using AI and bioinformatics spanning the entire system — from growing crops through consumption. This includes optimizing plant traits for yield, crop quality and disease resistance through advances in molecular breeding, in addition to minimizing resource consumption and waste through development of agriculture-specific AI applications, sensing platforms, and robotics. The team's plan also intends to benefit consumers through enhancements to food safety and development of new tools to provide real-time assessment of meals that can guide personalized health decisions.
“The food system is ripe for disruption, with many advances over the past decade paving the way to a transformation,” said Ilias Tagkopoulos, professor in the UC Davis Department of Computer Science and Genome Center, and director of the new institute. “AI will serve as both the enabling technology and the connective tissue that brings together these elements and catalyzes this transformation to a safer, fairer and more efficient food system for the next generation.”
Other principal investigators from UC Davis include Nitin Nitin, professor in the Department of Biological and Agricultural Engineering; Mason Earles, assistant professor in the Department of Viticulture and Enology; and Xin Liu, professor in the Department of Computer Science.
The institute has been designed to be inclusive, fostering collaborations to develop open-source AI solutions across the food system. Given food's fundamental role in human health and well-being, coupled with its far-reaching impacts on the national economy and environment, the institute will bring together over 40 researchers from six institutions: UC Davis; UC Berkeley; Cornell University; University of Illinois, Urbana-Champaign; UC Division of Agriculture and Natural Resources; and the U.S. Department of Agriculture's Agricultural Research Service.
In addition to the scientific and technical objectives, the institute's charter includes a significant focus on education, outreach and collaboration.
“Our success won't only come from breakthroughs and innovation of new technologies and systems, but also a ready workforce, an engaged public and collaboration with industry partners to solve real challenges,” said Gabriel Youtsey, chief innovation officer at UC ANR.
Education and engagement
The institute's plan includes programs specific for K-16 education, college internships and fellowships, curriculum enrichment, broadening participation and diversity, corporate engagement, and knowledge transfer. These programs will be bolstered by leveraging existing platforms such as UC Davis' Innovation Institute for Food and Health, CITRIS Banatao Institute and UC ANR's Verde Innovation Network for Entrepreneurship, or VINE. Additional efforts are planned in alignment with NSF's call to ensure AI systems are secure, safe, ethical and fair through design, accountability and transparency.
Development of the proposal for the award was facilitated by the Interdisciplinary Research and Strategic Initiatives division of the Office of Research at UC Davis. The institute is designated as a Special Research Program under the administration of the Office of Research.
“As with many of our world's greatest challenges, addressing the critical needs in our food supply requires extensive collaboration between experts from different disciplines,” said Prasant Mohapatra, vice chancellor for research at UC Davis. “The collection of expertise assembled for this new institute brings much hope for transformative advancements to be realized.”
Funding for the institute is provided by the U.S. Department of Agriculture's National Institute of Food and Agriculture as part of a larger initiative led by the U.S. National Science Foundation to establish new artificial intelligence institutes to accelerate research, expand America's workforce and transform society in the decades to come. The NSF AI institutes will collaborate with industry and government to advance the frontiers of AI as well as a range of science and engineering disciplines and societal sectors that stand to benefit from AI innovation.
“Recognizing the critical role of AI, NSF is investing in collaborative research and education hubs, such as the USDA-NIFA AI Institute for Next Generation Food Systems anchored at UC Davis, which will bring together academia, industry, and government to unearth profound discoveries and develop new capabilities advancing American competitiveness for decades to come,” said NSF Director Sethuraman Panchanathan. “Just as prior NSF investments enabled the breakthroughs that have given rise to today's AI revolution, the awards being announced today will drive discovery and innovation that will sustain American leadership and competitiveness in AI for decades to come.”