Remote Sensing Anomaly Detection in Time-Series Imagery and Application Development in the Agricultural Context

• Grant number: 25/22483-0
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: December 01, 2025
• End date: February 28, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Rubens Augusto Camargo Lamparelli
• Grantee: Fernando Kenzo Imami Fugihara
• Supervisor: Jefersson A dos Santos
• Host Institution: Núcleo Interdisciplinar de Planejamento Energético (NIPE). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Institution abroad: University of Sheffield, England
• Associated to the scholarship: 24/06856-9 - Remote Sensing Images Classification for Plasticulture Studies: Pre-Processing and Datafusion, BP.IC

Abstract

The use of plastic in agriculture has increased significantly in recent years, bringing both benefits and environmental challenges. While agricultural plastics improve crop yields and resource efficiency, they also lead to the accumulation of plastic waste in rural areas. Remote Sensing (RS) data, combined with advanced machine learning and computer vision techniques, provide an effective means to monitor plasticulture dynamics. Therefore, this research internship aims to explore RS anomaly detection (RSAD) techniques in time-series imagery and apply them to agricultural monitoring, particularly in detecting subtle cases that involve spectral changes such as material deterioration and pest-related disturbances Therefore, I'll join researchers at the University of Sheffield to learn RSAD techniques in the agriculture context and then explore whether they can be applied in plasticulture. In parallel, I'll collaborate with researchers at the University of Sheffield and contribute to the PEZEGO pest-management app. The internship will provide hands-on experience in scalable application design, app optimization, and model integration, which can enhance our ongoing application, GeoHuman. The University of Sheffield was chosen due to its internationally recognized expertise in application development, machine learning, computer vision, and remote sensing. This experience will strengthen our project in Brazil by improving the accuracy and scalability of agricultural monitoring systems. Upon my return, I will disseminate the knowledge gained through workshops and collaborative activities with my research group at UNICAMP to foster innovation and capacity building in remote sensing applications. (AU)