Optimizing Herbicide Use in Fodder Crops with Low-Cost Remote Sensing and Variable Rate Technology

Conceição, Luís Alcino; Silva, Luís; Dias, Susana; Maçãs, Benvindo; Sousa, Adélia M. O.; Fiorentino, Costanza; D’Antonio, Paola; Barbosa, Sofia; Faugno, Salvatore

http://hdl.handle.net/10362/184655

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
Concei_o_L._A._et_al._2025_..pdf		3.93 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Conceição, Luís Alcino

Resumo(s)

The current Common Agriculture Policy (CAP) foresees a reduction of 50% in the use of herbicides by 2030. This study investigates the potential of integrating remote sensing with a low-cost RGB sensor and variable-rate technology (VRT) to optimize herbicide application in a ryegrass (Lolium multiflorum Lam.) fodder crop. The trial was conducted on three 7.5-hectare plots, comparing a variable-rate application (VRA) of herbicide guided by a prescription map generated from segmented digital images, with a fixed-rate application (FRA) and a control (no herbicide applied). The weed population and crop biomass were assessed to evaluate the efficiency of the proposed method. Results revealed that the VRA method reduced herbicide usage by 30% (0.22 l ha−1) compared to the FRA method, while maintaining comparable crop production. These findings demonstrate that smart weed management techniques can contribute to the CAP’s sustainability goals by reducing chemical inputs and promoting efficient crop production. Future research will focus on improving weed recognition accuracy and expanding this methodology to other cropping systems.

Descrição

Funding Information: The APC was funded by national funds through the Fundação para a Ciência e a Tecnologia, I.P. (Portuguese Foundation for Science and Technology) via the project UIDB/05064/2020 (VALORIZA—Research Centre for Endogenous Resource Valorization); by national funds from Fundação para a Ciência e a Tecnologia (FCT), Portugal, through the research unit UIDP/04035/2020 (GeoBioTec); and by the GEEBovMit Project—LA 3.3-PRR-C05-i03-I-000027-LA3.3—Mitigation of GHG emissions in beef cattle production—pastures, forages, and natural additives. Publisher Copyright: © 2025 by the authors.

Palavras-chave

Low-cost sensor Machine learning Mediterranean climate RGB Spatial analysis General Materials Science Instrumentation General Engineering Process Chemistry and Technology Computer Science Applications Fluid Flow and Transfer Processes