Abstract:

Remote sensing technologies have become a fundamental component of modern crop management, offering precise, timely, and spatially extensive information for evaluating crop status and field conditions.

This work presents a teaching innovation activity that utilizes Google Earth Engine (GEE) to support the agronomic interpretation of spectral bands and vegetation indices during field plot assessments. The activity aims to familiarize students with the principles of remote sensing—specifically reflectance behavior and vegetation index computation—and to demonstrate how these tools can be used to inform agronomic decision-making through a coding-based analytical environment.

Using a pre-configured GEE script, students can visualize and compare multiple spectral bands and vegetation indices over a selected agricultural plot, enabling visual assessment, temporal analysis, quantitative evaluation, and introductory modeling exercises. This direct interaction with satellite-derived information enhances student comprehension of how biophysical signals relate to crop vigor, stress conditions, and overall field performance.

The primary objective is to provide a hands-on learning experience that enables students to integrate theoretical knowledge of remote sensing with practical interpretation skills, translating spectral and index information into actionable agronomic insights. This approach strengthens competencies such as critical thinking, active learning, and digital literacy, while introducing students to analytical tools widely used in precision agriculture.

Incorporating remote sensing and cloud-based platforms, such as GEE, into agronomy training not only enriches the educational experience but also equips students with essential methodological skills for future professional practice in agricultural sciences, thereby enhancing their technological readiness for data-driven farm environments.
The use of these technologies enhances teaching for students and their professional futures. Preliminary feedback suggests increased engagement, improved confidence in utilizing remote sensing data, and a deeper understanding of how digital tools support agronomic decision-making.

Keywords:

Remote sensing education, Digital learning, Spectral analysis, Cloud-based platforms, Crop monitoring, Data-driven agronomy.