Predicting rice blast disease: machine learning versus process-based models.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: In this study, we compared four models for predicting rice blast disease, two operational process-based models (Yoshino and Water Accounting Rice Model (WARM)) and two approaches based on machine learning algorithms (M5Rules and Recurrent Neural Networks (RNN)), the former inducing a rule-based model and the latter building a neural network. In situ telemetry is important to obtain quality in-field data for predictive models and this was a key aspect of the RICE-GUARD project on which this study is based. According to the authors, this is the first time process-based and machine learning modelling approaches for supporting plant disease management are compared.

Authors

  • David F Nettleton
    IRIS Technology Solutions, Barcelona, Spain.
  • Dimitrios Katsantonis
    Hellenic Agricultural Organization-DEMETER, Institute of Plant Breeding and Genetic Resources, 65, Georgikis Scholis Av. Zeda Building, Entrance 4, 2nd floor, 57001, Thessaloniki, Greece.
  • Argyris Kalaitzidis
    Hellenic Agricultural Organization-DEMETER, Institute of Plant Breeding and Genetic Resources, 65, Georgikis Scholis Av. Zeda Building, Entrance 4, 2nd floor, 57001, Thessaloniki, Greece.
  • Natasa Sarafijanovic-Djukic
    IRIS Advanced Engineering, Parc Mediterrani de la Tecnologia, Avda. Carl Friedrich Gauss nÂș 11, 08860, Castelldefels, Spain.
  • Pau Puigdollers
    GreenPowerMonitor, Av. de Josep Tarradellas, 123-127, 08029, Barcelona, Spain.
  • Roberto Confalonieri
    ESP, Cassandra Lab., UniversitĂ  degli Studi di Milano, Via Celoria, 2, 20133, Milan, Italy.