A comparative study between nonlinear regression and artificial neural network approaches for modelling wild oat (Avena fatua) field emergence

CHANTRE, GUILLERMO RUBÉN; BLANCO, ANÍBAL; FORCELLA, FRANK; VAN ACKER, RENE C.; SABBATINI, MARIO RICARDO; GONZÁLEZ-ANDÚJAR, JOSÉ LUIS

JOURNAL OF AGRICULTURAL SCIENCE

CAMBRIDGE UNIV PRESS

Lugar: Cambridge; Año: 2014 vol. 152 p. 254 - 262

0021-8596

Non-linear regression techniques are used widely to fit weed field emergence patterns to soil microclimatic indices using S-type functions. Artificial neural networks (ANNs) present interesting and alternative features for such modelling purposes. In the present work, a univariate hydrothermal-time based Weibull model and a bivariate (hydro-time and thermal-time) artificial neural network were developed to study wild oat emergence under non-moisture restriction conditions using data from different locations worldwide. Results indicated a higher accuracy of the neural network in comparison to the non-linear regression approach due to the improved descriptive capacity of thermal-time and the hydro-time as independent explanatory variables. The bivariate ANN model outperformed the conventional Weibull approach, in terms of RMSE of the test set, by 70.8 %. These outcomes suggest the potential applicability of the proposed modelling approach in the design of weed management decision support systems.