Classification of hyperspectral data and neural networks to differentiate between typical leaves of wheat and those deficient in nitrogen, phosphorus, potassium and calcium

Authors: Ayala-Silva, Tomas; BEYL, CAULA - ALABAMA A&M UNIV; Heath, Robert

Submitted to: International Journal of Biological Sciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/21/2006
Publication Date: 9/25/2006
Citation: Ayala Silva, T., Beyl, C., Heath, R.R. 2006. Classification of hyperspectral data and neural networks to differentiate between typical leaves of wheat and those deficient in nitrogen, phosphorus, potassium and calcium. International Journal of Biological Sciences.

Interpretive Summary: A quick identification of deficiency of nutrients using spectral features would be useful in farming and in other nutrient demanding farming systems such as those proposed for NASA space missions. A Multilayer Perceptron (MLP) neural network and backpropagation algorithm was used to distinguish between normal leaves of wheat (Triticum aestivum L.) and those deficient in nitrogen, phosphorus, potassium and calcium using hyperspectral data. The network consisted of three layers with spectral reflectance of the leaves in wavelengths from 401 nm to 770 nm as the input layer and the mineral concentrations as the output layer. Based upon the values of actual nutrient concentrations (mg/L), plants were classified as either lacking or normal. Wheat plants were grown for '100 days under hydroponic and greenhouse (vermiculate) conditions in the growth chamber. A complete nutrient solution with selected minerals removed to induce specific nutrient deficiencies was used. Control plants received a complete nutrient solution. The MLP model was trained and tested successfully within 1000 epochs. The backpropagation algorithm functioned well with the following results: classification model; N 90.9%, P 100%, K 90%, and Ca 100% and the regression model ; N 93.0%, P 87.2%, K 91.9%, and Ca 97.4%. This confirms the potential of using spectral data together with either a classification or regression neural network model to ensure quick identification of deficiencies. Key words: Deficiency, neural network, reflectance, hyperspectral data, minerals

Technical Abstract: A fast identification of insufficiency of nutrients using spectral features would be a useful instrument in farming and in other nutrient demanding agricultural systems such as those proposed for long period space missions. A Multilayer Perceptron (MLP) neural network and backpropagation algorithm was used to differentiate between normal leaves of wheat (Triticum aestivum L.) and those deficient in nitrogen (N) , phosphorus (P) , potassium (K), and calcium (Ca) using hyperspectral data. The network consisted of three layers with spectral reflectance of the leaves in wavelengths from 401 nm to 770 nm as the input layer and the nutrient concentrations as the output layer. Based upon the values of actual nutrient concentrations (mg/L), plants were classified as either deficient or standard. Wheat plants were grown for '100 days under both hydroponic conditions in the greenhouse and vermiculate media in a growth chamber using Hoagland's complete nutrient solution with selected minerals detached to induce specific nutrient deficiencies. Check plants received complete nutrient solutions. The MLP model was trained and tested successfully within 1000 epochs as the MSE of the sample-training curve approached zero. The backpropagation algorithm functioned well with the following accuracies for the classification model: N 90.9%, P 100%, K 90%, and Ca 100%. Using the regression model, the following accuracies were obtained: N 93.0%, P 87.2%, K 91.9%, and Ca 97.4%. This affirms the potential of using spectral data coupled with either a classification or regression neural network models to quickly categorize leaves deficient in these four major minerals consequently that remedial applications of those nutrients can be made before the yield is drastically affected. Key words: Deficiency, neural network, reflectance, hyperspectral data, nutrients.