Moisture prediction from simple micrometeorological data.

ABSTRACT Four linear regression methods and a generalized regression neural network (GRNN) were evaluated for estimation of moisture occurrence and duration at the flag leaf level of wheat. Moisture on a flat-plate resistance sensor was predicted by time, temperature, relative humidity, wind speed, solar radiation, and precipitation provided by an automated weather station. Dew onset was estimated by a classification regression tree model. The models were developed using micrometeorological data measured from 1993 to 1995 and tested on data from 1996 and 1997. The GRNN outperformed the linear regression methods in predicting moisture occurrence with and without dew estimation as well as in predicting duration of moisture periods. Average absolute error for prediction of moisture occurrence by GRNN was at least 31% smaller than that obtained by the linear regression methods. Moreover, the GRNN correctly predicted 92.7% of the moisture duration periods critical to disease development in the test data, while the best linear method correctly predicted only 86.6% for the same data. Temporal error distribution in prediction of moisture periods was more highly concentrated around the correct value for the GRNN than linear regression methods. Neural network technology is a promising tool for reasonably precise and accurate moisture monitoring in plant disease management.

[1]  T. Gillespie,et al.  Estimating dew duration. II. Utilizing standard weather station data , 1981 .

[2]  W. Massy.  Principal Components Regression in Exploratory Statistical Research , 1965 .

[3]  L. Francl.  Challenge of bioassay plants in a monitored outdoor environment , 1995 .

[4]  Uwe Hartmann,et al.  Mapping neural network derived from the parzen window estimator , 1992, Neural Networks.

[5]  Hrishikesh D. Vinod,et al.  Application of New Ridge Regression Methods to a Study of Bell System Scale Economies , 1976 .

[6]  Ronald Marsh,et al.  Conjugate gradient and approximate Newton methods for an optimal probabilistic neural network for food color classification , 1998 .

[7]  Terry J. Gillespie,et al.  Estimating dew duration. I. Utilizing micrometeorological data , 1981 .

[8]  T. Gillespie,et al.  SENSING DURATION OF LEAF MOISTURE RETENTION USING ELECTRICAL IMPEDANCE GRIDS , 1978 .

[9]  Thomas M. Loughin,et al.  Development and Validation of an Empirical Model to Estimate the Duration of Dew Periods , 1994 .

[10]  A. E. Hoerl,et al.  Ridge regression:some simulations , 1975 .

[11]  J. Friedman,et al.  A Statistical View of Some Chemometrics Regression Tools , 1993 .

[12]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[13]  T. Gillespie,et al.  Modeling Leaf Wetness in Relation to Plant Disease Epidemiology , 1992 .

[14]  Eric D. Salin,et al.  Improved Calibration for Inductively Coupled Plasma-Atomic Emission Spectrometry Using Generalized Regression Neural Networks , 1995 .

[15]  Terje V. Karstang,et al.  Prediction of molecular weight and density of distillation fractions from gas chromatographic—mass spectrometric detection and multivariate calibration , 1988 .

[16]  E. Nadaraya.  On Non-Parametric Estimates of Density Functions and Regression Curves , 1965 .

[17]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[18]  S. Coakley,et al.  Forecasting Dew Duration at Pendleton, Oregon, Using Simple Weather Observations , 1978 .

[19]  R. E. Pitblado,et al.  Using operational weather data to schedule fungicide sprays on tomatoes in Southern Ontario, Canada , 1993 .

[20]  Adaptation of a dew estimation scheme to a new crop and site , 1984 .

[21]  Suranjan Panigrahi,et al.  Artificial neural network models of wheat leaf wetness , 1997 .

[22]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.