A scene of photographing mandarin trees to forecast production (Image provided by Jeju Province)
JEJU, Aug. 22 (Korea Bizwire) — In a bid to modernize one of South Korea’s most iconic agricultural industries, the Jeju Agricultural Research and Extension Services announced Friday it has formally introduced an artificial intelligence (AI) and 3D modeling system to predict tangerine harvests more accurately.
For decades, yield forecasts for Jeju’s signature citrus crop relied on labor-intensive field surveys. Inspectors visited 320 sample orchards three times a year to count blossoms, measure fruit size and sugar levels, and estimate yields.
But the method was prone to human error, manpower shortages during peak heat, and inconsistencies caused by prematurely harvested fruit.
The new system, developed as part of Jeju’s broader digital agriculture strategy, integrates a decade of field survey data with microclimate information from the Korea Meteorological Administration and vegetation indices derived from satellites and drones.
3D model of a mandarin tree (image provided by Jeju Province)
By applying multiple machine-learning models, researchers can automatically generate predictions that factor in blossom-to-leaf ratios, fruit counts and sizes, planting density, and elevation.
During this month’s mid-season survey, researchers tested the system by photographing citrus trees with smartphones. Within 40 minutes, uploaded images produced 3D models of trees, enabling AI to calculate fruit numbers and dimensions.
“AI-driven forecasting reduces labor intensity, minimizes human error, and raises accuracy,” said Kim Tae-woo, head of the Agricultural Digital Center. “By strengthening predictive reliability through digital transformation, we aim to enhance the competitiveness of Jeju’s citrus industry.”
The rollout reflects a broader national push toward agricultural digitalization, with Jeju’s mandarin oranges—long a staple of South Korean produce exports—now serving as a testbed for cutting-edge farming technologies.
Ashley Song (ashley@koreabizwire.com)
