A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks

Most popular emergence prediction models require species-specific population-based parameters to modulate thermal/hydrothermal accumulation. Such parameters are frequently unknown and difficult to estimate. Moreover, such models also rely on hardly available and difficult to estimate soil site-speci...

Full description

Bibliographic Details
Main Authors: Chantre Balacca, Guillermo Ruben, Vigna, Mario Raul, Renzi Pugni, Juan Pablo, Blanco, Anibal Manuel
Format: Artículo
Language:Inglés
Published: 2018
Subjects:
Online Access:https://www.sciencedirect.com/science/article/pii/S1537511017306335
http://hdl.handle.net/20.500.12123/2333
https://doi.org/10.1016/j.biosystemseng.2018.03.014
_version_ 1855483035741323264
author Chantre Balacca, Guillermo Ruben
Vigna, Mario Raul
Renzi Pugni, Juan Pablo
Blanco, Anibal Manuel
author_browse Blanco, Anibal Manuel
Chantre Balacca, Guillermo Ruben
Renzi Pugni, Juan Pablo
Vigna, Mario Raul
author_facet Chantre Balacca, Guillermo Ruben
Vigna, Mario Raul
Renzi Pugni, Juan Pablo
Blanco, Anibal Manuel
author_sort Chantre Balacca, Guillermo Ruben
collection INTA Digital
description Most popular emergence prediction models require species-specific population-based parameters to modulate thermal/hydrothermal accumulation. Such parameters are frequently unknown and difficult to estimate. Moreover, such models also rely on hardly available and difficult to estimate soil site-specific microclimate conditions, which in turn depend on soil heterogeneity at a field spatial level. On the other hand, modern agriculture benefits from easily available real-time information, in particular on-line meteorological data generated by forecasts and automatic local weather stations. In this context, Artificial Neural Networks (ANN) provide a flexible option for the development of prediction models, especially to study species which show a highly distributed emergence pattern along the year. In this work, an ANN approach based on easily obtainable meteorological data (daily minimum and maximum temperatures; daily precipitation) is proposed for weed emergence prediction. Relative Daily Emergence (RDE), expressed as a proportion of the total emergence, was the adopted output variable. Field emergence data recorded on a weekly basis were used to generate RDE patterns through linear interpolation. Results for three study cases from the Semiarid Pampean Region of Argentina (Lolium multiflorum, Avena fatua and Vicia villosa), which show irregular and time-distributed field emergence patterns, are reported. In all cases, ANN model selection was based on the Root Mean Square Error of the test set which showed better consistency than other typical Information Theory performance metrics. The combination of large ANN with a Bayesian Regularization Algorithm generated satisfactory estimations based on the RMSE values for independent Cumulative Emergence data.
format Artículo
id INTA2333
institution Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina)
language Inglés
publishDate 2018
publishDateRange 2018
publishDateSort 2018
record_format dspace
spelling INTA23332019-06-05T18:15:00Z A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks Chantre Balacca, Guillermo Ruben Vigna, Mario Raul Renzi Pugni, Juan Pablo Blanco, Anibal Manuel Malezas Emergencia Modelos Inteligencia Artificial Weeds Emergence Models Artificial Intelligence Redes Neuronales Artificiales Modelos de Predicción Most popular emergence prediction models require species-specific population-based parameters to modulate thermal/hydrothermal accumulation. Such parameters are frequently unknown and difficult to estimate. Moreover, such models also rely on hardly available and difficult to estimate soil site-specific microclimate conditions, which in turn depend on soil heterogeneity at a field spatial level. On the other hand, modern agriculture benefits from easily available real-time information, in particular on-line meteorological data generated by forecasts and automatic local weather stations. In this context, Artificial Neural Networks (ANN) provide a flexible option for the development of prediction models, especially to study species which show a highly distributed emergence pattern along the year. In this work, an ANN approach based on easily obtainable meteorological data (daily minimum and maximum temperatures; daily precipitation) is proposed for weed emergence prediction. Relative Daily Emergence (RDE), expressed as a proportion of the total emergence, was the adopted output variable. Field emergence data recorded on a weekly basis were used to generate RDE patterns through linear interpolation. Results for three study cases from the Semiarid Pampean Region of Argentina (Lolium multiflorum, Avena fatua and Vicia villosa), which show irregular and time-distributed field emergence patterns, are reported. In all cases, ANN model selection was based on the Root Mean Square Error of the test set which showed better consistency than other typical Information Theory performance metrics. The combination of large ANN with a Bayesian Regularization Algorithm generated satisfactory estimations based on the RMSE values for independent Cumulative Emergence data. EEA Bordenave EEA Hilario Ascasubi Fil: Chantre Balacca, Guillermo Ruben. Universidad Nacional del Sur. Departamento de Agronomía; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Centro de Recursos Naturales Renovables de la Zona Semiarida. Universidad Nacional del Sur. Centro de Recursos Naturales Renovables de la Zona Semiarida; Argentina Fil: Vigna, Mario Raúl. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Bordenave; Argentina Fil: Renzi Pugni, Juan Pablo. Universidad Nacional del Sur. Departamento de Agronomía; Argentina. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Hilario Ascasubi; Argentina. Fil: Blanco, Aníbal M. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Planta Piloto de Ingeniería Química. Universidad Nacional del Sur. Planta Piloto de Ingeniería Química; Argentina 2018-05-04T18:33:39Z 2018-05-04T18:33:39Z 2018-06 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://www.sciencedirect.com/science/article/pii/S1537511017306335 http://hdl.handle.net/20.500.12123/2333 1537-5110 https://doi.org/10.1016/j.biosystemseng.2018.03.014 eng info:eu-repo/semantics/restrictedAccess application/pdf Biosystems engineering 170 : 51-60. (June 2018)
spellingShingle Malezas
Emergencia
Modelos
Inteligencia Artificial
Weeds
Emergence
Models
Artificial Intelligence
Redes Neuronales Artificiales
Modelos de Predicción
Chantre Balacca, Guillermo Ruben
Vigna, Mario Raul
Renzi Pugni, Juan Pablo
Blanco, Anibal Manuel
A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title_full A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title_fullStr A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title_full_unstemmed A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title_short A flexible and practical approach for real-time weed emergence prediction based on Artificial Neural Networks
title_sort flexible and practical approach for real time weed emergence prediction based on artificial neural networks
topic Malezas
Emergencia
Modelos
Inteligencia Artificial
Weeds
Emergence
Models
Artificial Intelligence
Redes Neuronales Artificiales
Modelos de Predicción
url https://www.sciencedirect.com/science/article/pii/S1537511017306335
http://hdl.handle.net/20.500.12123/2333
https://doi.org/10.1016/j.biosystemseng.2018.03.014
work_keys_str_mv AT chantrebalaccaguillermoruben aflexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT vignamarioraul aflexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT renzipugnijuanpablo aflexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT blancoanibalmanuel aflexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT chantrebalaccaguillermoruben flexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT vignamarioraul flexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT renzipugnijuanpablo flexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks
AT blancoanibalmanuel flexibleandpracticalapproachforrealtimeweedemergencepredictionbasedonartificialneuralnetworks