A Portable in-situ Near-infrared LEDs-based Soil Nitrogen Sensor

Abstract

Monitoring soil Nitrogen content for palm oil cultivation is paramount to produce high-quality palm oil. This study aims to investigate the feasibility of a designed portable near-infrared (NIR) light emitting diodes (LEDs)-based soil Nitrogen in predicting the soil Nitrogen content using NIR light. First, soil samples that collected from a local oil palm plantation were scanned using the developed sensor and followed by a conventional method, i.e. Kjeldahl analysis. A chemometric analysis was applied in this study to develop a predictive model by choosing the best result from an artificial neural network (ANN). The performance of ANN was validated using leave one out cross-validation. Results indicate that ANN with one hundred number of hidden neurons outperformed with a root mean square error of cross-validation of 0.031. This finding suggests that the proposed sensor coupled with ANN is promising to satisfactorily predict soil Nitrogen content.