Optimal Approach for Supply Chain Market-Based Harvesting Time Forecasting

Machine Learning (ML) has been utilized in agriculture to enhance agricultural productivity and reduce environmental impact. This study introduces a new technique for predicting the optimal crop harvesting time using a novel Buffalo-based Sequence Neural Prediction Mechanism (BSNPM). At first, the historical hydroponic data is gathered and trained into the system. The proposed technique is then used to predict the optimal harvesting time for crops based on the highest yield rate and market demand. This technique helps producers make informed decisions by identifying the optimal conditions for lettuce yield and market demand. The MATLAB environment is used to implement the proposed BSNPM model. To analyze the efficacy of the proposed method, some significant performance metrics include accuracy, Precision, recall, error rate, and computation time. The results demonstrate that the proposed method effectively predicts the best harvesting time for the hydroponic crop.