Agricultural Information Research
Online ISSN : 1881-5219
Print ISSN : 0916-9482
ISSN-L : 0916-9482
Current issue
Displaying 1-2 of 2 articles from this issue
Original Paper
  • Wei Cao, Junya Geshi, Kazunobu Okadome, Hideki Ueyama, Kouki Fujioka
    2022 Volume 31 Issue 2 Pages 47-58
    Published: July 01, 2022
    Released on J-STAGE: July 01, 2022

    The time of picking is crucial to the production of green tea: delays reduce quality, but picking early reduces yield. Therefore, it is necessary to pick tea at the optimum time to balance quality and yield. At present, deciding when to pick relies on individual experience. However, climate change could make experience less reliable. Therefore, objective prediction of tea harvest dates will be important, not only for stabilizing the production of high-quality tea, but also for saving labor and management. Here, we report multiple linear regression models automatically constructed for predicting the harvest date of cultivars Yabukita, Sayamakaori, and Okumidori in Japan through the use of meteorological data collected over many years on site. The aim was to limit the mean absolute error of models evaluated by the leave-one-out strategy to within 3 days. All models performed better than simple linear regressions. The techniques developed here will reduce the effort of visual judgment and contribute to the stable production of high-quality tea.

    Download PDF (4205K)
Short Paper
  • Daichi Akiyama, Yutaka Sasaki
    2022 Volume 31 Issue 2 Pages 59-64
    Published: July 01, 2022
    Released on J-STAGE: July 01, 2022

    In 2013, the FAO announced in Insects for Food: Future Prospects for Food and Feed Safety that insects could replace traditional livestock and feed to benefit the global environment, health, and livelihoods. One of the important keywords of “Food Tech & Agri-tech”, which is expected to grow worldwide, is “alternative protein”, which includes vegetable “meat”, cultured meat, vegetable “milk” and “dairy” products, and insect protein. Of these, insect protein is attracting attention for its potential to reduce environmental loads and for its productivity and technical aspects; however, R&D on mass production has only just begun, and many research questions exist, because the technology has not yet been established. Our research focuses on raising crickets on food wastes, smart agri-production, waste heat utilization, production and use of renewable energy, business models, and new market development by venture companies. Here, we describe the construction of a real-time ecological model for mass production of crickets in YOLO v. 5, an AI model. This versatile and expandable model facilitates handling of a large amount of data. For example, we evaluated a newly defined “cricket activity index” to gather information on feeding under 24-h lighting.

    Download PDF (1534K)