Artificial Neural Network Model for Shallot Disease Severity Prediction Using Drone Multispectral Imagery

Shallot plant diseases can reduce yields by up to 50% of total land area. Currently, shallot plant disease identification relies on direct observation, which is less effective and efficient due to varying intensities of disease and large cultivation areas. This study aims to develop a predictive model for shallot disease severity using multispectral drone imagery, apply Artificial Neural Network (ANN) algorithm to analyze multispectral band data, and evaluate the model's performance. The study used ANN algorithm with multi-layer perceptron regressor, involving following stages such as dataset acquisition, dataset stitching, dataset filtering and feature extraction, model development, and model evaluation. Multispectral data were taken using DJI Mavic 3 Multispectral drone, resulting 696 images per bands that were stitched into orthophoto map. The filtering process of plant objects yielded better model training results compared to unfiltered data. The optimal ANN model structure was identified as 4-6-2-1, with R² value of 0.9194 and MAE value of 0.0618. Model testing results demonstrated that using four input bands (G, R, RE, NIR) provided the best performance with R² value of 0.9194, followed by combination of two bands (R, RE) with R² value of 0.8883. This indicated that the R and RE bands were most strongly correlated with shallot disease severity. Keywords: Drone, Multi-layer perceptron, Multispectral imagery, Plant disease, Shallot.