Neural Network Model for Estimating Total Chlorophyll Laboratory Measurement Based on Chlorophyll Meter (SPAD) Value in Oil Palm Muhdan Syarovy, Rana Farrasati, Iput Pradiko, Winarna,
Indonesia Oil Palm Researh Institute
Abstract
Chlorophyll is one component that is often an indicator of plants experiencing environmental stress. Quantitatively, the value of chlorophyll can be measured using a chlorophyll meter and in the laboratory. Chlorophyll meter measurements can be done quickly, but do not produce actual values like chlorophyll measurements in the laboratory. Meanwhile, measurement of chlorophyll in the laboratory requires special treatment and a long time to get results. This study aims to estimate the chlorophyll content of chlorophyll meter and laboratory measurements using a neural network model. The input that will be used in this study is the age group and SPAD value, while the output is the estimated total chlorophyll in laboratory measurements. The number of datasets used in this research is 1,066 data which is divided into 80% training and 20% test data. The neural network model can predict the chlorophyll content in the laboratory with a mean square error (MSE) and a Mean Absolute Error (MAPE) of 0.0330 and 0.1333 respectively.
