Generation of a remote sensing methodology for the identification and variable chemical control of weeds with ground equipment in sugarcane

The proposed project intends to generate a method for identifying weeds and develop site-specific weed control prescriptions for sugarcane cultivations in Costa Rica using Remote Sensing techniques. Remotely sensed data will be captured using multispectral camera and LiDAR sensors attached to Remotely Piloted Aircraft Systems (RPAS). Images will be processed using machine learning algorithms to characterize the weed type and how it emerges during the early stages of sugarcane cultivation. Results will be evaluated using field samples. Once the variety of weeds and the emerging patterns identify, site-specific, variable-rate chemical solutions or prescriptions will be developed and fed into ground machines for spraying.

Faculty Supervisor:

Muditha Heenkenda

Student:

Partner:

National University of La Plata

Discipline:

Engineering

Sector:

Environmental Science and Technology; Artificial Intelligence; Agriculture and Food

University:

Lakehead University

Program: