This text revealed in collaboration with JUIDA, the Japan UAS Industrial Improvement Affiliation.
Researchers on the College of Tokyo say drone imagery, machine studying, and a development curve mannequin can estimate underground potato yield earlier than harvest.
Researchers on the College of Tokyo Graduate College of Agricultural and Life Sciences and Kubota Company have developed a drone potato yield prediction methodology that estimates underground tuber biomass earlier than harvest. In keeping with the college, the strategy combines drone-based distant sensing, machine studying, and an underground development mannequin to foretell yield in unharvested plots.
The announcement follows current Dronelife protection of Japan’s agriculture drone market, which Tokyo-based Market Analysis Heart forecasts will attain $357.8 million by 2034. The College of Tokyo says its new methodology displays the type of precision agriculture use case driving that development.
How the drone potato yield prediction works
In keeping with the college, fields had been periodically photographed with drones geared up with RGB and multispectral cameras. The group extracted picture options on a plot foundation, together with plant cowl ratio, cover top, coloration indices, and vegetation indices. A machine-learning mannequin was educated on the connection between these options and measured underground biomass obtained by sampling.
For unharvested plots, the researchers estimated tuber biomass by feeding picture options into the machine-learning mannequin. The group then utilized the time-series information to a Gompertz development curve, an S-shaped mathematical mannequin of organic development, to foretell yield at harvest.
The research was led by doctoral pupil Yuto Imachi, Professor Hiroyoshi Iwata, and Affiliate Professor Wei Guo, alongside researchers from Kubota’s Subsequent-Technology Analysis Division and Masahiro Okada of Sarabetsu Prediction Co., Ltd. Pieter M. Blok, then a undertaking assistant professor on the college and now at Eindhoven College of Know-how, additionally contributed.
Two-year area trial outcomes
In keeping with the college, the group carried out the experiment in 2023 and 2024 in fields on the College of Tokyo Discipline Science Heart in Nishi-Tokyo Metropolis. Trials coated a number of remedy plots with various planting density and seed tuber circumstances.
The group achieved a correlation coefficient of 0.8 or greater for tuber biomass estimation and 0.7 or greater for yield prediction utilizing the expansion curve. In keeping with the college, the outcomes verify that yield could be predicted from the pre-harvest stage utilizing above-ground drone information.
Functions for sensible agriculture
The college says potatoes are an vital meals crop worldwide, however assessing yield throughout the rising interval has historically relied on damaging sampling. In keeping with the analysis group, the brand new methodology provides a non-destructive different that captures spatial variation throughout a area.
The group says the growth-curve strategy is predicted to help pre-harvest yield forecasting and optimization of cultivation administration, together with suggesting optimum harvest timing. The analysis was carried out beneath the joint Kubota Todai Lab undertaking.
Extra data is obtainable from the College of Tokyo.
Learn extra:
Ian McNabb is a journalist specializing in drone know-how and life-style content material at Dronelife. He’s based mostly between Boston and NH and, when not writing, enjoys climbing and Boston space sports activities.
