Machine learning models as an alternative to determine productivity losses caused by weeds.

Journal: Pest management science
Published Date:

Abstract

BACKGROUND: Weed control can be economically viable if implemented at the necessary time to minimize interference. Empirical mathematical models have been used to determine when to start the weed control in many crops. Furthermore, empirical models have a low generalization capacity to understand different scenarios. However, computational development facilitated the implementation of supervised machine learning models, as artificial neural networks (ANNs), capable of understanding complex relationships. The objectives of our work were to evaluate the ability of ANNs to estimate yield losses in onion (model crop) due to weed interference and compare with multiple linear regression (MLR) and empirical models.

Authors

  • Matheus de Freitas Souza
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Alex Lima Monteiro
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Daniel Valadão Silva
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Tatiane Severo Silva
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Stefeson Bezerra de Melo
    Department of Exact, Technological and Human Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Angicos, Brazil.
  • Aurélio Paes Barros Júnior
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Bruno Caio Chaves Fernandes
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.
  • Vander Mendonça
    Department of Agronomic and Forestry Sciences, Universidade Federal Rural do Semi-Árido - UFERSA, Plant Science Center, Mossoró, Brazil.