Jeonbuk National University (JBNU) Department of Smart Farm students have been attracting attention in related academic circles by consecutively presenting results in advanced crop modeling research and the development of AI-based smart farm technologies.

At the recent Spring Conference of the Korean Society for Horticultural Science held in Suwon, Yun Jeong-min, a Master’s student (supervisor: Lee Jun-woo), received an Excellence Poster Presentation Award for the poster titled 'Comparison of 14 Light-Response Models for Estimating the Light Saturation Point of Nun-gaet-ssuk-bujaengi and Haeguk'.

This study compared and analyzed various light-response models to propose a method for more precisely estimating crop light saturation points. The findings are expected to serve as baseline data to improve the precision of light-environment control in greenhouses.

At the Spring Conference of the Korean Society for Biological Environment Control held at Yeonam University, Lee Hyun-gyu, an undergraduate student (supervisor: Lee Jun-woo), won an Excellence Poster Presentation Award for research on 'Estimation of the Crop Coefficient of Romaine Lettuce (Lactuca sativa var. longifolia) Grown in Greenhouse Conditions'.

The study estimated the crop coefficient (Kc) for romaine lettuce using the FAO Penman-Monteith equation and load-cell-based evapotranspiration measurements. It identified a tendency toward higher Kc than the FAO56 standard and demonstrated positive correlations with leaf area, leaf number, and biomass. The results are evaluated as empirical evidence that can be used to establish precise irrigation and water-management standards by growth stage.

At the same conference, Jeon Hye-jin, a Master’s student (supervisor: Kim Tae-gon), received an Excellence Poster Presentation Award for research on 'Development of an Educational Smart Farm Dashboard for Decision Support on Supplemental Lighting Under Low-Light Conditions, Integrated with an LLM-Based Chatbot'.

This study developed an educational platform that combines large language models (LLMs) with real-time environmental data to determine the need for supplemental lighting for leafy vegetables under low-light conditions. Through an RAG-based chatbot, the platform provides stage-specific guidance on environmental management, pest and disease response, and nutrient management, thereby improving both smart farm operational efficiency and user accessibility.

Lee Jun-woo, Chair of the Department of Smart Farm, stated, “Despite challenging research conditions, the students produced meaningful results through sustained research engagement. We will continue to devote efforts to cultivating talent who will lead agricultural innovation based on advanced technologies.”

Meanwhile, the JBNU Department of Smart Farm is actively conducting interdisciplinary research across all areas of smart agriculture — including digital agriculture, crop modeling, environmental control, and automation technologies — and has established itself as a hub for training key talent to drive the advancement of future agriculture.