Crop yield forecasting using neural networks trained on the basis of agrometeorological and agrochemical data

Abstract

In this study, a neural network model was developed and investigated for predicting crop yields based on data on weather conditions, the use of fertilizers and the content of basic nutrients in the soil (nitrogen, phosphorus and potassium). The research is based on the use of a multilayer perceptron architecture with Rely activation functions for hidden layers and linear activation for the output layer. The evaluation of the model quality was carried out using the mean square error (MSE), which was 0.5783 in the test sample, demonstrating high accuracy of predictions. Visualization of the results included analysis of scatter plots, residuals, histograms of residuals and comparison of distributions of actual and predicted values. The results obtained confirm the effectiveness of the proposed model for yield forecasting tasks, which makes it a valuable tool for optimizing agricultural production.