Optimizing the Detection of Soil Nitrogen Levels via Grayscale Conversion: A Full-Factorial Design of Experiment Approach

Abstract

In smart agriculture, the detection the level of soil macronutrients is essential in soil fertility and productivity that correlates to crop yields and fertilizer recommendations. With the advancement of technology, identification of such levels is easily obtained using devices that capture images. The levels of soil macronutrients from the captured images are affected by two factors, i.e., the tilting angle of the test tube and the lighting condition. The device produces images containing three red, green, and blue values, respectively. Using grayscale conversion, these values are then converted into a single value to analyze appropriately. This study aims to determine the optimal combination of the factors to obtain the correct reading of Nitrogen and Phosphorus using a fullfactorial design of experiments with four replications designed by Minitab®. The results are analyzed using Analysis of Variance. The determined factors are the tilting angle and lighting condition. The results depicted that the factors and their interactions are significant. The developed regression model explains 76.43% of variability among factors. The optimal setting for tilting angle is 90°, while the lighting condition should be indoors. Design of Experiment is a valuable statistical tool that promotes optimization and efficient experimentations used by scientists and engineers.