The Institute of Industrial Science, the University of Tokyo (hereinafter referred to as ``Todai Institute of Industrial Science'') and Air Water Co., Ltd. (hereinafter referred to as ``Air Water'') have developed technology to predict the appropriate harvest time of agricultural crops and observation technology to detect differences in growth. developed.

 The University of Tokyo IIS and Air Water established the "IoT Sensing Analysis Technology" Social Collaboration Research Department in December 2020, and have been conducting joint research on smart agriculture. This time, we announced a technology that predicts the appropriate harvest time with high accuracy based on the cumulative effective temperature during the growing period of crops. This eliminates the need for large capital investments and allows the optimal harvest time to be determined just by collecting temperature data, which is expected to reduce quality deterioration and harvest losses due to overripeness/immaturity.

 When this "prediction" model was applied to predict the harvest of broccoli using machine learning, the company succeeded in predicting the optimal harvest time of broccoli with an average accuracy of less than 2.5 days from the date of planting.

 Furthermore, we have developed an "observation" technology that assigns individual numbers to crops from aerial images taken using a drone and detects differences in growth (amount and growth rate of crops) for each individual number. Observation technology makes it possible to predict the number and quantity of crops harvested, which is expected to lead to optimization of harvesting equipment, personnel, and collection, leading to improved productivity.

 In the future, in anticipation of simultaneous harvesting due to mechanization, which is expected to advance Japanese agriculture, we will work to further improve the accuracy of ``prediction'' and ``observation'' of the entire field (field) rather than individual individuals. In addition, we are concurrently conducting research and development to improve the accuracy of predicting the appropriate harvest time using weather forecasts, and to have field-driving robots monitor crops on behalf of humans based on information observed and grasped by drones, and to implement social implementation. The company plans to aim for the following.

Paper information:[Journal of Agronomy] RNN-Based Approach for Broccoli Harvest Time Forecast
【Sensors and Materials】Locating Open-field Broccoli Plants with Unmanned Aerial Vehicle Photogrammetry and Object Detection Algorithm: A Practical Prediction Approach

Tokyo University

Established in the 10th year of the Meiji era.A university with the longest history in Japan and at the forefront of Japanese knowledge

The University of Tokyo was established in 1877 (Meiji 10) by integrating the Tokyo Kaisei School and the Tokyo Medical School.Since its establishment, it has developed education and research in a unique way in the world as a leading university in Japan and an academic center for the fusion of East and West cultures.As a result, many human resources have been produced in a wide range of fields, and many research achievements […]

University Journal Online Editorial Department

This is the online editorial department of the university journal.
Articles are written by editorial staff who have a high level of knowledge and interest in universities and education.