INTEGRATION OF SENSORS IN SUSTAINABLE NUTRIENT MANAGEMENT IN SUGARCANE: DEVELOPING TOOLS FOR DIGITAL AGRICULTURE

• Grant number: 24/10366-7
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2025
• End date: July 31, 2028
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Peterson Ricardo Fiorio
• Grantee: Peterson Ricardo Fiorio
• Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil
• City of the host institution: Piracicaba
• Associated researchers: Ana Cláudia dos Santos Luciano ; André Freitas Colaço ; Christopher Michael Usher Neale ; Daniel Garbellini Duft ; Joe David Luck ; José Alexandre Melo Demattê ; Mathias Christina ; Roberto Fray da Silva ; Rodnei Rizzo
• Associated scholarship(s): 25/18423-2 - Proposed Methodological Approach for Estimating Sugarcane Productivity by Integrating Spectral and Biometric Data Acquired with UAV, BP.MS; 25/25210-5 - Prediction of Nitrogen content in sugarcane using Hyperspectral data: Comparison of predictive models, BP.IC; 25/15610-6 - INTEGRATION OF SENSORS IN SUSTAINABLE NUTRIENT MANAGEMENT IN SUGARCANE: DEVELOPING TOOLS FOR DIGITAL AGRICULTURE, BP.DR

Abstract

Fertilization based on nitrogen (N), phosphorus (P), and potassium (K) is one of the fundamental agricultural practices for the development of sugarcane, influencing productivity and technological quality. Currently, the main technique for nutrient quantification is soil and plant tissue analysis, which is impractical on a large scale, has high costs, and uses chemical products. In this context, we propose to develop integrated technologies employing laboratory and airborne spectral sensors to optimize the prediction and spatialization of the nutritional condition of sugarcane. The first collections and analyses will be conducted in an experiment installed at the Centro de Tecnologia Canavieira (CTC), Piracicaba - SP, with five sugarcane varieties and four NPK fertilizations. Spectral data will be collected from leaves in the laboratory (FieldSpec spectroradiometer), canopy (Remotely Piloted Aircraft - RPA), and agronomic data will be collected at different phenological stages: 60, 120, 180, and 240 days after cutting - DAC, over two production cycles. Subsequently, the following will be evaluated: i) adjustments of the intensity of reflectance of the multispectral bands based on the laboratory hyperspectral foliar signature; ii) adding variables related to plant-nutrient interactions to the models for fresh leaves; iii) exploring the potential of spectral models for processed samples (dried and ground) of sugarcane, covering different varieties; and iv) testing the transferability of the models across vegetative stages, in different regions. These innovations offer benefits to both producers and the industry, including reduced time for collecting nutritional information about the crop, decreased costs associated with chemical analyses, and reduced use of chemical reagents in nutrient quantification. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

ALEXANDRE, MARTA LAURA DE SOUZA; LIMA, IZABELLE DE LIMA; NILSSON, MATHEUS STERZO; RIZZO, RODNEI; SILVA, CARLOS AUGUSTO ALVES CARDOSO; FIORIO, PETERSON RICARDO. Sugarcane (Saccharum officinarum) Productivity Estimation Using Multispectral Sensors in RPAs, Biometric Variables, and Vegetation Indices. AGRONOMY-BASEL, v. 15, n. 9, p. 20-pg., 2025-09-08. (24/10366-7)