Testing the generalization of artificial neural networks with cross-validation and independent-validation in modelling rice tillering dynamics

Neural networks (NN) rely on the inner structure of available data sets rather than on comprehension of the modeled processes between inputs and outputs. Therefore, neural networks have been regarded as highly empirical models with limited extrapolation capability to situations outside the range of the training and validation data sets. In this study, the generalization ability of neural networks in predicting rice tillering dynamics was tested and several techniques inducing the generalization ability of neural networks were compared. We compared the performance of cross-validated neural networks with independent-validated neural networks and found that neural networks were able to extrapolate and predict tillering dynamics if the data were within the range of inputs of the training set. An inadequate training set resulted in overfitting of available data and neural networks that were not generalizable. The training set size required to enable a neural network to generalize and predict rice tillering dynamics was found to be at least 9 times as many training patterns for each weight. When a large number of variables are included in the input vector of a neural network with inadequate amounts of training data, we strongly recommend that the dimension of the input vector is reduced using principle component analysis (PCA), correspondence analysis (CA) or similar techniques to decrease the number of weights before the training procedure to improve the generalization ability of the NN. If the amount of training data still is not sufficient after the dimension of the input vector is reduced, regularization techniques, such as early stopping, jittering, and especially the embedment of estimated results by a theoretical model into the training set, should be used to improve the generalization ability of the neural network. The generalization of neural networks presents a wide spectrum of problems, and the proposed approaches are not confined strictly to modelling rice tillering dynamics but can be applied to other agricultural and ecological systems.

[1]  Israel Broner,et al.  Combining expert systems and neural networks for learning site-specific conditions , 1997 .

[2]  R. Wieland,et al.  The use of neural networks in agroecological modelling , 1995 .

[3]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[4]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .

[5]  T. Foin,et al.  A temperature-based model of direct-, water-seeded rice (Oryza sativa) stand establishment in California , 1998 .

[6]  Michele Scardi,et al.  Advances in neural network modeling of phytoplankton primary production , 2001 .

[7]  S. Jørgensen,et al.  Movement rules for individual-based models of stream fish , 1999 .

[8]  Liangzhi Gao,et al.  A software package for optimizing rice production management based on growth simulation and feedback control , 1996 .

[9]  Györgyi,et al.  Inference of a rule by a neural network with thermal noise. , 1990, Physical review letters.

[10]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[11]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[12]  Tetsuo Morimoto,et al.  AI Approaches to Identification and Control of Total Plant Production - for SPA & SFA to environmental control , 1998 .

[13]  Gretchen G. Moisen,et al.  Comparing five modelling techniques for predicting forest characteristics , 2002 .

[14]  P. Heuberger,et al.  Calibration of process-oriented models , 1995 .

[15]  Russell C. Eberhart,et al.  Neural network PC tools , 1990 .

[16]  P. Voho,et al.  Modular production system concept for a water tap system , 1992 .

[17]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[18]  P. Viotti,et al.  Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia , 2002 .

[19]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[20]  Yan Huang,et al.  Neural network modelling of coastal algal blooms , 2003 .

[21]  Willem Bouten,et al.  Comparison of different modelling strategies for simulating gas exchange of a Douglas-fir forest , 2002 .

[22]  Kenneth A. Sudduth,et al.  Analysis of Spatial Factors Influencing Crop Yield , 2015 .

[23]  Alfred Schultz,et al.  Neural networks in agroecological modelling - stylish application or helpful tool? , 2000 .

[24]  Ligang Zheng,et al.  Estimating ecosystem risks using cross-validated multiple regression and cross-validated holographic neural networks , 1999 .

[25]  Stefano Marsili-Libelli,et al.  Parameter estimation of ecological models , 1992 .

[26]  P. C. Robert,et al.  Grain Yield Stability in Continuous Corn and Corn-Soybean Cropping Systems on a Sandy Landscapes , 1996 .

[27]  Fernando Gustavo Tomasel,et al.  Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models , 1997 .

[28]  Jiang De-long,et al.  The Model of Relations of Rice Tillering to Light and Temperature Conditions , 1982 .