Using multispectral imagery to extract a pure spectral canopy signature for predicting peanut maturity

Abstract An Unmanned Autonomous Octocopter equipped with a multispectral camera was used to take imagery of peanut plant cover at different stages of maturity. Vegetation indexes (Normalized Difference Vegetation Index, Transformed Difference Vegetation Index, Modified Soil Adjusted Vegetation Index, Modified Chlorophyll Absorption Ratio Index and the Modified Triangular Vegetation Index) were stacked and used to mask out the peanut canopy cover from background soil, shadows and any other surficial materials. Masked peanut canopy was used to develop a peanut maturity-spectral reflectance prediction model. The model was built using partial least squares. Comparison between the model- predicted and real values showed that the model does not give an accurate estimate of maturity up to 60 days after planting, but the accuracy of the model increases with time. This may since the difference between chlorophyll a and become more significant in mature peanuts more than immature ones. The overall assessment of the model indicates that the model needs to be calibrated for more precise prediction of the peanut maturity. This could be achieved by expanding the peanut maturity, versus peanut leaf spectra, database by taking data more frequently, especially close to harvest. Data collection should be started two months after planting when the ratios between chlorophyll a and b become more detectable in the leaf reflectance spectra.

[1]  David L. Jordan,et al.  Peanut Response to Planting Date and Potential of Canopy Reflectance as an Indicator of Pod Maturation , 2008 .

[2]  M. A. Shahin,et al.  Fuzzy logic model for predicting peanut maturity. , 2000 .

[3]  J. Hatfield,et al.  Remote sensing estimators of potential and actual crop yield , 1983 .

[4]  J. C. Price,et al.  Leaf area index estimation from visible and near-infrared reflectance data , 1995 .

[5]  Gary E. Varvel,et al.  Use of Remote-Sensing Imagery to Estimate Corn Grain Yield , 2001 .

[6]  C. Daughtry,et al.  Remote Sensing Leaf Chlorophyll Content Using a Visible Band Index , 2011 .

[7]  Kevin P. Price,et al.  Predicting Soybean Relative Maturity and Seed Yield Using Canopy Reflectance , 2016 .

[8]  M. D. Evans,et al.  Maturity Detection in Peanuts (Arachis Hypogaea L.) Using Machine Vision , 1993 .

[9]  W. Collins,et al.  Remote sensing of crop type and maturity , 1978 .

[10]  J. L. Araus,et al.  Usefulness of spectral reflectance indices as durum wheat yield predictors under contrasting Mediterranean conditions , 2003 .

[11]  Ernest W. Tollner,et al.  PREDICTING PEANUT MATURITY WITH MAGNETIC RESONANCE , 1998 .

[12]  A. J. Richardson,et al.  Vegetation indices in crop assessments , 1991 .

[13]  C. Konzak,et al.  Relationship between Grain Yield and Remotely‐Sensed Data in Wheat Breeding Experiments , 1993 .

[14]  John H. Prueger,et al.  Value of Using Different Vegetative Indices to Quantify Agricultural Crop Characteristics at Different Growth Stages under Varying Management Practices , 2010, Remote. Sens..

[15]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[16]  Christopher L. Butts,et al.  Determination of Maturity and Degree Day Indices and their Success in Predicting Peanut Maturity1 , 2006 .

[17]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[18]  D. G. Sullivan,et al.  Canopy Characteristics and their Ability to Predict Peanut Maturity , 2008 .

[19]  Gustavo A. Slafer,et al.  Can wheat yield be assessed by early measurements of Normalized Difference Vegetation Index , 2007 .

[20]  Moon S. Kim,et al.  Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance , 2000 .