Data Aggregation and Analysis in Precision Agriculture

Description

This course will present the background knowledge, methods, and tools for data aggregation and analysis of the massive amounts of qualitative and quantitative (spatial) data regarding conditions in the field coming from precision agriculture monitoring technologies. Data-collecting hardware and monitoring technologies are gathering massive amounts of data regarding the conditions of crops and their environment, but they cannot on their own support the management of crops and the critical decisions required to enhance crop yields, minimize the use of resources, and protect the environment.

Data collecting technologies including distal and proximal remote sensing, agricultural drones, soil sensors, Global Navigation Satellite Systems (GNSS), yield monitoring devices, and weather stations provide in principle geospatial data (or location-based data). Therefore, geoinformatics, geographical information systems (GIS), spatial analysis, spatial statistics, and geostatistics lie in the core of Data Aggregation and Analysis in Precision Agriculture to allow managing spatial variability. The course will introduce the students in the fundamental principles of geoinformatics and GIS. The students will receive basic knowledge in spatial analysis, spatial statistics, and geostatistics that are required for the exploration, explanation, and interpretation of spatial data.

This course will offer a mixture of lectures, discussions, demonstrations and hands-on exercises on specific case studies and real world applications.

Learning objectives

Students will learn how to use geoinformatics in precision agriculture, water and land resources evaluation, protection and management, crop monitoring and management, as well as environmental monitoring and protection. They will learn the main geospatial analysis techniques and the principles of spatial statistics, and geostatistics. They will also get familiar with the GIS technologies and tools on analyzing, distributing, and visualizing geo-spatial data and will be introduced in spatial data modeling.

Exams, marking and student assessment

Assignments: 40%, Laboratory and practical learning evaluation: 30%, Written exams: 30%

Proposed reference material

Scientific papers, given by the lecturers