Digital platform for forecasting and harvest in arabica coffee crops

• Grant number: 22/05594-5
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Duration: October 01, 2022 - September 30, 2024
• Field of knowledge: Agronomical Sciences - Agronomy - Crop Science
• Principal Investigator: Diego Moure Oliveira
• Grantee: Diego Moure Oliveira
• Host Company: Eleve Pesquisa e Desenvolvimento Ltda
• CNAE: Pesquisa e desenvolvimento experimental em ciências físicas e naturais
• City: Ribeirão Preto
• Pesquisadores principais: Guilherme Jorge Gomes de Sousa ; Joyce Mayra Volpini Almeida Dias
• Associated researchers: Andresa Aparecida Berretta e Silva ; Carlos Pamplona Rehder ; JORGE LUIS SILVA KAVICKI
• Associated scholarship(s): 22/14497-3 - Use of artificial intelligence to monitor the yiled of arabica coffee crops, BP.TT

Abstract

For the coffee grower to be able to do good business with the sale of his coffee, some pre-harvest steps are key, among them, (I) knowing when to harvest the coffee and (II) having a good estimate of production in the fields some time before start harvesting. The first step is extremely important, especially for coffee growers looking to improve their coffee drink scores; and harvesting with many fruits in the immature stage (green) can compromise this quality and consequently devalue the price of coffee. The second stage is crucial for the coffee grower to be able to optimize and plan the management of producing areas and farm finances. In the last harvest, more than 48 million bags of Arabica coffee were produced in the country on more than 1.75 million hectares; therefore, the search for new technologies that aim to improve the coffee production sector is especially interesting. In this sense, during phase 1 (PIPE-FAPESP n 2020/05864-7) a feasibility study of a digital tool was proposed, with image analysis through artificial intelligence for harvest prediction and harvest estimation, the promising results, in the identification of grains and maturity level, which can be found in the phase 1 report attached to this proposal, justify the present proposal for phase 2. During phase 2, it is proposed that this model and tool be incorporated into an accessible digital platform and intuitive, and strategically tested for commercial purposes. In addition to informing general data on productivity and fruit maturation stages, the technology will be able to provide detailed data on productivity and maturation, since the collection points will be georeferenced. Ten farms present in the main Arabica coffee producing regions will be monitored during the project years in three different moments of the coffee production cycle, (I) beginning of fruiting; (II) advanced fruiting, and (III) medium maturation. The collected data will allow to refine the artificial intelligence tool and integrate the platform to be developed for validation and later commercialization for three pre-harvest activities, (I) crop estimation; (II) crop monitoring and (III) identification of the maturation stages of the fruits. (AU)