ASHS 2025 Conference

The number of empty houses in South Korea is expected to surge due to rapid population decline. The problem is being overcame through remodeling and leasing in other countries. However, those businesses are not productive and sustainable. Considering climate change and the decline in the agricultural population, we would suggest a project to use empty houses for agricultural purposes. Smartfarm technology allows us to grow crops anywhere, thus farming in the apartments is possible. In particular, since most apartments in South Korea are complexed, large-scale cultivation is possible. We expect economic effect (sales revenue, local food market, job creation, real estate value, distribution process), social effect (connection between cities and rural areas, food security, local communities) and environmental effect (carbon reduction, sustainability, urban green space) from this project. Taking advantage of the characteristics, we believe that it is necessary to proactively conduct a study on a smart value chain system that connects cultivation, storage, retail, and restaurants.

Strawberry harvesting is a labor-intensive task that requires careful, selective picking to avoid damaging delicate fruit. To address labor shortages and enhance harvesting efficiency, we propose an AI-enhanced soft robotic system capable of autonomous and selective strawberry harvesting. Specifically, the system incorporates advanced computer vision algorithms, leveraging the Grounding DINO model, to detect and localize ripe strawberries with high accuracy. A compliant soft robotic gripper, guided by real-time perception, then gently harvests only the target fruits, minimizing potential damage to adjacent berries and plants. Experimental results demonstrate that the system achieves a ripe strawberry detection accuracy of 88% and a harvesting success rate of 66.67%. This integrated approach offers a scalable, precise, and labor-efficient solution for modern strawberry production.

Seed germination may be affected by various abiotic and biotic stressors, resulting in significantly reduced crop yields and resource use efficiency, thus posing challenges to food production for the growing global population. Therefore, several studies have focused on employing diverse mechanical and chemical treatments to improve seed germination. Non-thermal plasma (NTP) is an emerging technology for enhancing seed germination and plant growth. This study evaluated the effects of NTP on the germination properties of borage (Borago officinalis L.) seeds. Plasma was generated using a custom-made surface-barrier-discharge (SBD) device, operating at a frequency of 5 kHz and voltage of 1.3 kVpp. Seeds were exposed to plasma for 0.5, 1, and 2 minutes, whereas untreated seeds served as the control. Each treatment was replicated three times, with each replication divided into two subunits, containing 25 seeds per experimental unit. Germination was monitored under controlled conditions (20 °C temperature, 16 hours photoperiod, 200 µmol/m2/s PAR radiation provided by fluorescent lights and 74% relative humidity) in a PGR-15 Conviron plant growth chamber for 10 days. Germination was assessed daily, and key germination parameters were analyzed, including final germination percentage (GP), mean germination time (MGT), mean germination rate (MGR), coefficient of variation of germination time (CVt), germination index (GI), and time to 50% germination (t50). Plasma treatment for 0.5 and 1 minute significantly (p < 0.05) increased germination percentage (GP) (52 ± 5.37% and 50.67 ± 2.46%, respectively) compared to the control (34.67 ± 3.96%). MGT decreased in all plasma-treated groups, with the shortest MGT (3.94 ± 0.13 days) observed for 0.5 minutes compared to 4.91 ± 0.29 days for the control, suggesting faster germination. Plasma treatment significantly enhanced MGR, with shorter exposure time leading to accelerated germination. All plasma-treated groups reached 50% germination faster than the control, suggesting improved seed vigor. The GI of plasma-treated seeds was consistently higher than the control, indicating greater germination uniformity. These findings highlight the potential of non-thermal plasma treatment to enhance key factors for improved yield and crop resource use efficiency.

Agrivoltaic systems, which integrate photovoltaic (PV) panels with agricultural production, offer potential benefits for sustainable land use but remain underexplored in many regions. A needs assessment survey conducted among stakeholders on the Navajo Nation identified both an interest in agrivoltaics and a lack of understanding regarding its implementation and impacts. In response, a pilot study was established to evaluate the effects of PV panel shading on microclimatic conditions and radish (Raphanus sativus) productivity in a controlled small-scale agrivoltaic system. This study aimed to generate preliminary data to inform future agrivoltaic research and applications. The experiment utilized open-bottomed grow boxes filled with a 2:1 mixture of commercially available peat-perlite growing medium and organic mushroom compost, placed over field soil. Radish seeds were sown under four different PV panel treatments and a full-sunlight control, with environmental parameters—including air temperature and light intensity—monitored throughout a 46-day growth period. At harvest, crop yield and soil characteristics, including nutrient content, electrical conductivity, pH, and heavy metal concentrations, were analyzed. Morphological parameters such as total root biomass and the proportion of marketable roots (≥16 mm in diameter) were also assessed. Results indicated that PV panel shading reduced radish productivity, with shaded treatments exhibiting lower root biomass and yield compared to the full-sunlight control. These findings suggest that shading effects from PV panels may negatively impact radish growth under fall seasonal conditions. This study provides critical baseline data for optimizing agrivoltaic system designs based on crop selection and environmental conditions, contributing to broader research on sustainable agricultural practices in arid and semi-arid regions.

Major U.S. apple producing regions include Washington, Michigan, and New York for an aggregate of 10 billion pounds of apples/year. While most apple orchards in the Western region feature irrigation systems, large portions of acreage in the Midwest and Eastern regions rely on rainfall and are sensitive to lengthy dry periods during the growing season. These dry periods have been shown to cause fruit drop and drastically reduce fruit size. Apple rootstocks represent the interface between soil and scion and are a critical component of water relations in orchards. Understanding rootstock response to drought is a key component of securing apple production in vulnerable regions. In this study, we utilized a large format aeroponics system (LFAS) with integrated sensors for light, root moisture, and caliper to conduct an exploratory experiment on the utility of the LFAS to study rootstock behavior during drought in real time. The LFAS contained 12 trees of 6 rootstock genotypes grafted with ‘Honeycrisp’. Each tree was suspended into the LFAS with a collar and the roots sprayed with a pH-balanced nutrient solution at intervals of 30” on/1’30” off. Trees were grown from June-November in a heated greenhouse (24oC) with supplemental lighting. We selected three rootstocks (G.890, G.935, G.969) to monitor before, during, and after drought using LiCor-600 porometer readings. Prior to treatment, we selected four newly expanded leaves at the top of the tree and two mature leaves in the mid-section, labelling them N1-N4 (newer leaves) and O1-O2 (older leaves). Baseline porometer readings were collected at 4:30 AM and then at 12:00 PM under full sun and supplemental light. Subsequently, solution misting was shut down from 12:00 PM to 4:00 PM on November 11th, 2022. In aeroponics, solution film provided by misting and reserve moisture in the roots are all that is available for evapotranspiration. As a result, the drought treatment was almost instant. Roots appeared dry and both apical sections of the trees and mature leaves wilted. After 2 weeks, leaf damage was recorded. Post-drought, N1-N4 and O1-O2 leaves were measured again with the porometer, as well as two “Drought Damaged” leaves (DD1-DD2). Statistical analysis indicated significant Drought*Genotype effects (p < .0001). Dendrometer readings showed the differential response to drought of each rootstock in real time. This experiment demonstrated that aeroponics is a viable method for assessing drought tolerance of rootstock-scion combinations, and showed drought tolerance of the rootstocks was G.935 > G.890 > G.969.

Modern agricultural systems, notably hydroponics, utilize digital technologies and precision farming techniques for automated, sensor-driven cultivation. These systems apply real-time environmental monitoring to enhance plant growth parameters and operational efficiency. Nevertheless, sensor inaccuracies can undermine data integrity due to malfunctions or environmental influences. Thus, this is required to obtain comprehensive environmental analysis and precise data management protocols to maintain system integrity. This study assessed the sensors' reliability by evaluating algal coverage metrics in hydroponic tomato cultivation. A total of one hundred seventeen sensors designed to measure pH, temperature, humidity, and electrical conductivity (EC) were deployed within a greenhouse environment. Following a duration of three months, only 39 sensors were classified into two separate categories: 22 demonstrating considerable algal coverage (≥90%) and 17 exhibiting minimal coverage (~10%). Sensors characterized by high algal coverage recorded substantially increased substrate humidity (85.6% vs. 41.9%) and EC values (774 µS/cm vs. 331 µS/cm) in contrast to their counterparts with lowered algae coverage. However, tomato yields did not significantly change between the two categories, indicating that the plants accommodate the changing environmental conditions. These results suggest that algal coverage may serve as an indirect metric for evaluating localized environmental parameters—particularly humidity and EC levels—and may also hold potential value in assessing the reliability of sensor data.

UAV Remote Sensing for Western Mayhaw Flower Intensity Assessment Presenting Author: Austin Fruge’ Co-Authors: Dr. Cengiz Koparan, Dr. Donald M Johnson, Dr. Amanda McWhirt Abstract. Western Mayhaw (Crataegus opaca) is an emerging economically important fruit in the genus Crataegus due to increased consumption, expanded marketing, and improved cultivars. Further research is needed to expand technology-driven management strategies and investigate its potential as an economical crop for rural and urban landowners in the Southeastern United States. The current methodology for estimating flowering intensity assessment in Western mayhaws is performed with visual observation in the field. However, this methodology is time-consuming, labor-intensive, and subjective. Given the need for a precise methodology for flowering intensity monitoring in Western mayhaws, we developed an open-source image-based phenotyping workflow from Unmanned Aerial Vehicle (UAV) captured images. A subset of Western mayhaw selections were evaluated for blooming intensity during the spring of 2025 in a private orchard near El Dorado, Arkansas. RGB images of Western mayhaw trees during the early flowering stage were collected using a DJI Mavic 3 Enterprise UAV mounted with an RGB digital camera. Each image was processed using an open-source image processing software to estimate the number of flowers. To evaluate the accuracy of this method, the flowering intensity was evaluated through visual flower counting and a visual scale, and compared to image-based flower estimation. Flowering intensity estimated with image segmentation showed a strong correlation with visual flower counting (r= 0.858, p < 0.001), indicating that an increase in visual flower count can be explained with segmented pixel count for any random image. Flower estimation with image segmentation is accurate and provides a standard method, however, it could be time-consuming due to the large image dataset. A semi-automated or fully automated image processing workflow could be developed to increase the efficiency of image processing.