ASHS 2024 Conference

Metware Biotechnology Inc.

Learn about advancements in efficient gas exchange research and quality data collection with the CIRAS-4 Portable Photosynthesis System and our partnerships with users to advance precision plant science. In addition, we will share new research collaborations with the NCSU-CEA coalition and our on-site container farm for CEA research. Talk to our research team about working together to further your research. It will be an action-packed 15 minutes. Don’t miss it!

Presenter: Eric Price
Summary: LI-COR is excited to present a new system to measure evapotranspiration in real time. The LI-710 measures actual evapotranspiration—water vapor moving out of the field and into the atmosphere—without the need for crop coefficients. It works over any relatively flat and uniform ground cover at field or ecosystem scale. The LI-710 applies the eddy covariance method to measure vertical wind and water vapor concentration at 10 Hz, then provides fully processed results every 30 minutes. LI-COR Cloud is cloud-based software for an Internet of the Environment (IoE) enabled LI-710—called the Water Node—that provides you with remote access to its data. The IoE Module is on-site hardware that transfers LI-710 data to LI-COR Cloud then ultimately to you for a start-to-finish data management solution.

After a brief introduction about BioChambers, Patrick Friesen (PhD) will talk about using growth chambers to effectively vernalize and cross perennial and biennial kales. The talk will focus on how to leverage the full environmental control growth chambers provide for successful synchronous flowering, sharing key details about growth temperatures, photoperiod, and light (quantity and quality) conditions used. This presentation is based on a successful crossing experiment, which is aimed toward breeding perennial kales that can successfully overwinter in southern Manitoba, Canada.

Sponsoring Professional Interest Groups
Technology: Coordinator Milt McGiffen - milt.mcgiffen@ucr.edu
Teaching Methods: Coordinator, Kathryn Orvis – orvis@purdue.edu
Controlled Environment: Coordinator, Kent Kobayashi - kentko@hawaii.edu

Supporting Professional Interest Groups
Federal Partners: Matthew Mattia - Matthew.Mattia@usda.gov
Plant Biotech: Kedong Da - kda@ncsu.edu
Ornamentals/Landscape and Turf; Youping Sun - youping.sun@usu.edu
Local Food Systems: Charles H. Parrish II - chip.parrish@pm.me

Artificial intelligence and related topics, e.g., robotics, have been a long time coming in agriculture. For decades there have been predictions of intelligent robots replacing humans, and large farms run by a few humans with many autonomous tractors and other devices. But with the now widespread use of artificial intelligence in everyday life,
the moment has arrived. We developed this colloquium by casting a wide net out to all the Professional Interest Group Chairs, and have assembled talks and demonstrations from general topics to specific applications.

Two online meetings were held, where Professional Interest Groups officers and those interested suggested speakers and discussed topics. Further discussions over email helped fill in the details to create this colloquium.

We will have a block of speakers for the diverse topics we present below, as well as panel discussions on how AI is and can be incorporated into various aspects of Horticulture, so that there is ample time for questions and discussion.

Title: Overview of the Colloquium

Speaker: Milt McGiffen, Cooperative Extension Specialist, Department of Botany and Plant Sciences,
University of California, Riverside, CA.

AI in Ornamentals

Title: FloraCount: An App for Rapid Assessment of Pollinator Attractiveness to Annuals and Perennial Plants.

Description: Customers are interested in buying annuals and perennials that support pollinators. Protocols for rapid assessment in flower trail evaluations are not available. We have developed a mobile app that can be used to analyze in real time the users’ observational data and quantitatively rank the relative utility of observed cultivars to pollinator communities. This app takes into account pollinator groups, relevant floral characteristics and landscape.

Presenter: Harland Patch
Assistant Research Professor
Department of Entomology
Penn State University
549 Ag Sciences & Industries Building
University Park, PA 16802

Title: Approach to Biodiversity Protection: Employing AI and IoT Systems for the
Containment of Box Tree Moth Proliferation.

Description: The box tree moth (BTM, Cydalima perspectalis) is an invasive pest first confirmed in Niagara County, New York in 2021. This invasive pest can significantly damage and potentially kill boxwood (Buxus species) plants if left unchecked. This presentation describes our advances in combining deep learning algorithms for enhanced computer vision with IoT-enabled smart traps, to facilitate the early detection and continuous monitoring of BTM populations and to protect the prevalent ornamental boxwood in U.S. landscapes.

Presenter: Yanqiu Yang (she/her)
Ph.D. Graduate Research Assistant
Department of Agricultural and Biological Engineering
Pennsylvania State University
3 Agricultural Engineering Building
University Park, PA 16802

Title: Landscapes from Words: The Future of Landscape Design with AI.

Description: The ongoing text-to-graphic artificial intelligence (AI) revolution has the potential to change the field of Landscape Architecture dramatically. The ability to produce original high-quality graphics, manipulate the viewer's perspective of images, and amend the rendering style through text inputs are significant advancements that will
inform new design process models. These changes can lead to expanded design exploration, improved accessibility for non-designers to contribute to creating visual concepts, enhanced ability to integrate data analysis and visualizations, and streamlined collaboration between clients and project stakeholders using a shared visual language. This talk focuses on two dimensions of change that may result from the rapid evolution of text-to-graphic AI, including (1) faster iterations and exploration of design options and (2) the advancement of methods that result in more inclusive and responsive design. In the classroom, students are just beginning to acknowledge the existence of text-to-graphic AI, which allows them to experiment with text-based design options that allow them to quickly visualize and explore a wide range of site program alternatives. Nevertheless, how do we manage the ethical and creative boundaries within an academic setting? In a research context, methods supporting rapid manipulation of both generated images and existing landscape photography represent advances that allow for greater collaboration surrounding landscape design decisions (Incorporating resilience strategies, protecting vernacular landscape elements that support a sense of place, or representing new design proposals that modify the landscape). These approaches allow stakeholders to gain remarkable advances in influencing the design process through shared visualization development. However, as with any emerging technology, practitioners, educators, and researchers need to respond to the challenges presented by text-to-graphic AI by developing and testing new design process models and public engagement techniques that can improve landscape decision-making and streamline collaboration.

Presenter: Aaron Thompson
Assistant Professor
Department of Horticulture and Landscape Architecture
Purdue University
625 Ag Mall Drive
West Lafayette, IN 47906

Title: Developing Guidelines for Extension’s Use of ChatGPT and Other Generative AI
Tools.

Description: A new technological era marked by the advent of Artificial Intelligence (AI), particularly generative AI and Large Language Models (LLMs) like ChatGPT has necessitated the need to navigate this domain with a compass of ethicality, safety, and effectiveness. Penn State’s experience developing guidelines for Extension’s use of
generative AI tools which will be shared and discussed.

Presenter: Michael Masiuk
Assistant Director – Horticulture Programs
Penn State Extension
342 Agricultural Administration Building
University Park, PA 16802

Panel: 30 minute panel with the above speakers, to allow time for Q&A and discussion.

Growth-promoting Bacteria in Improving the Biophysical Parameters of Cherry Tomatoes (Solanum lycopersicum L.)  - Henrique Oliveira
Promoting Controlled Environment Agriculture Activities At Campus-Wide Events - Kent Kobayashi
Rapid Detection of Herbicide-Resistant Weeds Utilizing Novel Full-Spectrum Imaging and a Hyperparameter-Tuned Convolutional Neural Network (CNN) - Pauline Victoria Estrada
Puʻuhonua Kauluwehi: Maui Wildfire Rapid Response Strategies for Agroecosystem Resilience and Community Well-Being - Nicolette van der Lee
Enhancing Hot Pepper Quality and Yield through Smart Irrigation Strategies - Harmandeep Sharma
Spraying Drone Efficiency: A Comparative Study of Application Rate and Surfactant Addition - Lucas Sales

How can we help students, the public, and stakeholders become familiar and engaged with controlled environment agriculture (CEA) and its benefits? Besides offering undergraduate courses such as TPSS 300 Tropical Production Systems and TPSS 491 Experimental Topics "Controlled Environment Agriculture" we sought other ways to accomplish this. The objective is to describe how we use displays about our CEA lab at campus-wide events to help inform audiences about CEA and its technology. Various events at the University of Hawaii at Manoa (UHM) enable colleges, departments, units, and individual laboratories the opportunity to showcase their programs, curricula, and research. At these campus-wide events, we set up table displays that explain CEA and highlight our CEA research. Our displays exhibit various aspects of the technology used in CEA such as LED (light-emitting diodes) lights, hydroponics, and greenhouse materials. We display high tech acrylic greenhouse coverings and walls, smart glass, photoselective shadecloths, and light spectrum control plastic films to show recent developments in greenhouse coverings. Hydroponic principles are explained through the use of micro-hydroponics, dwarf vegetables grown under LED lights, and hydroponic kits. A display using simulated Martian soils and LEGO® figures shows a Martian landscape with a plastic dome greenhouse with plastic vegetables growing inside. The audience gets to experience a hands-on working miniature grow tent, a replica of actual grow tents, to demonstrate how CEA experiments are conducted using grow tents with manually controlled red, blue, and white LED lights and fans. We have a shadecloth covered PVC pipe box with red and blue photoselective shadecloths and LED light placements on top, sides, and intracanopy to explain light spectrum and light placement. The Lunar/Martian greenhouse model displays an example of how plants could be grown on extraterrestrial bodies such as the moon and Mars. The display shows a cutaway view of a greenhouse installed below the soil surface for protection from radiation. Natural light is supplied with light pipes and artificial light is supplied with LEDs. Our lab’s table displays have been well received by people stopping by our tables. The campus events provide the opportunity for students to assist in staffing the tables and talking about CEA and their research. We also discuss CEA research opportunities provided by the UHM Undergraduate Research Opportunities Program (UROP) and the UHM Hawaii Space Grant Consortium Program.

Every year, farmers around the world lose more than $95 billion from uncontrolled weed infestation. Herbicide-resistant weeds, also known as “superweeds”, are fast becoming a significant part of this weed problem and are a significant threat to crop production and food security. Late detection of resistant weeds leads to increasing economic losses and severe environmental damage. Traditionally, genetic sequencing and herbicide dose-response studies are used to detect herbicide-resistant weeds, but these are expensive and slow processes. To address this problem, an AI-based superweed identifier program (SIP) was developed to quickly and accurately distinguish herbicide-resistant from susceptible chickweed (Stellaria media). A regular camera was converted to capture light wavelengths from 300 to 1,100 nm. These full spectrum images were used to develop a hyperparameter-tuned convolutional neural network (CNN) model utilizing a “train from scratch” approach. This novel approach exploits the subtle differences in the spectral signature of resistant and susceptible chickweed plants as they react differently to herbicide treatments. The SIP was able to identify resistant chickweed to acetolactate synthetase (ALS) inhibitor herbicides as early as 72 hours post treatment at an impressive accuracy of 85%. It has broad applicability due to its ability to distinguish resistant from susceptible chickweed plants regardless of the type of ALS herbicide or dosage rate used. Utilizing the superweed identifier program will allow farmers to make timely interventions and develop more effective and safer weed management practices. This can optimize yield, reduce herbicide use, minimize environmental harm, prevent herbicide-resistant weed proliferation, and improve overall public health.

The Puʻuhonua Kauluwehi project aims to develop a rapid response to the recent Maui wildfires by collaboratively establishing a network of biocultural refuges supporting the cultivation of native plants to accelerate landscape-scale agroecological resilience, food security and community well-being strategies. Puʻuhonua Kauluwehi is a Hawaiian phrase describing regenerative agroecosystem areas that provide shelter for native vegetation, attract native birds and insects, and serve as a source of thriving launching points to revegetate the landscape through community engagement. In Hawaiʻi, establishing biocultural refuges is even more critical as the unique ecosystems of the islands continue to come under threat from invasive species, drought, commercial development, lack of ecosystem management and are more at risk due to the dependence on imported response and aid resources from the mainland as demonstrated by the devastating impact of the Maui wildfires in August 2023. The project’s specific objectives are to: (1) Provide applied research and GIS mapping services that integrate water quality testing, soil testing and native plant and tree cataloging in one accessible database for the growing coalition of local agricultural and conservation organizations responding to the wildfires; (2) Develop strategies to ensure all children, youth, and adults have access to abundant local food during and after wildfire disasters through a network of seed orchard, seed bank, nursery and food hub partners; and (3) Design extension and non-formal community education initiatives to address the health and well-being of children, youth, and adults affected by wildfire disasters through work-based agroecosystem and stewardship training in the Kauluwehi Biocultural Garden for 300 participants. The Puʻuhonua Kauluwehi restoration project, led by University of Hawaii Maui College, will share initial outcomes of launching a technology platform to connect critical nodes of the Maui wildfire response into a thriving network that will serve as a social-ecological incubator for the positive impact of vibrant and culturally authentic landscapes and redefine the value of agroecosystems in Maui’s unique context for disaster recovery.

Hot peppers (Capsicum chinense) are attracting increasing attention due to their rich reservoirs of secondary metabolites, notably capsaicinoids, which are in high demand across various industries such as culinary, cosmetic, and pharmaceutical. Consequently, there has been a surge in the number of new pepper growers emerging throughout the United States. Despite ranking fifth in pepper production, North Carolina’s pepper cultivation remains smaller compared to other states known for hot pepper production. Additionally, the southern U.S. anticipates an increase in extreme weather events such as droughts and floods. Thus, there is a pressing need to identify the most suitable pepper cultivars and implement efficient production management practices tailored to local climatic conditions to maximize both crop production and quality. To address this need, the current study was conducted at Reid Greenhouse, North Carolina Agricultural

Current agricultural practices are facing several challenges because of the use of large and heavy machinery used in the fields. The benefits of covering large areas to meet the time of spraying crops is becoming questionable because the heavy machinery (large self-propelled boom sprayers) also can cause soil compaction and require large amounts of fuel and technical labor to be operated. Moreover, spraying drones are emerging as a pivotal technology in modern agriculture. They serve multiple purposes, from measuring and understanding fields using sensor and camera-captured images to acting as spray applicators for a wide range of products e.g.,including herbicides, pesticides, fungicides, and fertilizers. As a novel technology, spraying drones overcome some of the challenges faced by traditional methods. For instance, they can initiate applications in specific areas that require treatment, thereby avoiding issues like soil compression and unnecessary use of cultivated areas. This enhances precision while reduces losses in the field. However, defining application rate and the impact of adjuvant products is still scarce in previous studies. Therefore, in this study, we analyzed whether the coverage area is influenced by application rates and surfactant addition. The study was conducted in a carrot crop field. Water-sensitive papers were placed on the top leaf and at the bottom of the plants to quantify the coverage area. The measured area comprised a swath of 40 feet and a drone route of 100 feet. Measurements were performed in 9 crop-rows, each row with three hydrosensitive papers spaced in 33 feet apart. A multirotor spraying drone XAG P100Pro with Atomized Nozzles was used to apply spraying rates of 5 and 10 gallons per acre, both with and without surfactant addition. Results showed more coverage area on the top leaf than at the bottom of the plants. Similarly, when 10 gallons per acre were applied, it produced a higher covered area. However, there was a difference when applied 10 gallons with and without adjuvant. By applying adjuvant, the trial proved more efficient in reaching the plants. Conversely, when 5 gallons were applied, the surfactant did not contribute to either the top leaves or bottom part. Therefore, our results are promising and contribute to the enhancement of technology in agricultural production. The insights allow from farms to research centers to improve the spraying drone application, guaranteeing a more sustainable environment.