Neural Network for AI-Driven Prediction of Larval Protein Yield: Establishing the Protein Conversion Index (PCI) for Sustainable Insect Farming

The predictive capabilities of artificial intelligence for predicting protein yield from larval biomass present valuable advancements for sustainable insect farming, an increasingly relevant alternative protein source. This study develops a neural network model to predict protein conversion efficiency based on the nutritional composition of larval feed. The model utilizes a structured two-layer neural network with four neurons in each hidden layer and one output neuron, employing logistic sigmoid functions in the hidden layers and a linear function in the output layer. Training is performed via Bayesian regularization backpropagation to minimize mean squared error, resulting in a high regression coefficient (R = 0.9973) and a low mean-squared error (MSE = 0.0072401), confirming the precision of the model in estimating protein yields. This AI-driven approach serves as a robust tool for predicting larval protein yields, enhancing resource efficiency and promoting sustainability in insect-based protein production.