Spatial analyzes to enable the Circular Economy in Plasticulture

• Grant number: 24/06854-6
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: June 01, 2024
• End date: June 30, 2025
• Field of knowledge: Interdisciplinary Subjects
• Agreement: BRASKEM
• Principal Investigator: Rubens Augusto Camargo Lamparelli
• Grantee: Marlon Fernandes de Souza
• Host Institution: Núcleo Interdisciplinar de Planejamento Energético (NIPE). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Company: Universidade Estadual de Campinas (UNICAMP). Núcleo Interdisciplinar de Planejamento Energético (NIPE)
• Associated research grant: 21/05251-8 - Proposal for the creation of the Plasticulture Engineering Centre, AP.PCPE

Abstract

Plasticulture has been changing agricultural landscapes into something more industrial, mainly in the interface between rural and urban areas. It can generate some negative environmental effects despite its benefits for crop growth. Thus, the working group of Reverse Logistics and Circular Economy of the Plasticulture Engineering Center (CEP) is researching solutions to support the circularity in this vital food chain. The group decided to start structuring data about plasticulture due to the significant information gap. We will apply Artificial Intelligence (AI) in Remote Sensing (RS) images to identify Plastic-Mulched Farmlands (PMF) and Plastic Greenhouses (PGH), exploring computer vision techniques with machine learning (ML) algorithms. The ML advance has ushered in a new era of image big data analytics, and deep learning (DL) approaches have been at the forefront of these efforts. Performance on many RS tasks using large-scale satellite data has improved significantly. Remote detection can map the plastic structures used in agriculture, to locate and estimate the quantity of Agricultural Plastic Waste (APW) generated. Additionally, a geographic information system (GIS) is appropriate for organizing and showing this dataset. The GIS enables showing the plasticulture's accurate location and the vicinity context. So, the combination of RS and GIS allows evaluation of the existing infrastructure and the proposition of reverse logistics systems. The APW information enables verifying if the residues could be recycled using the close infrastructure or if new infrastructure is demanded. Therefore, the primary goal of this post-doctoral project is to generate datasets, models, and methods to support the circularity in the plasticulture chain. (AU)