Abstract
A neural network was developed to predict the effect of phosphorus on spring wheat yields. The focus is on the neural network, including its structure, parameters, training methods and results related to phosphorus effects on spring wheat yields. An algorithm for developing a neural network model is also presented. The study was conducted to address the critical need for developing a neural network to predict the effect of phosphorus on spring wheat yields in the Republic of Kazakhstan. For data analysis, input data were used that cover the period from 2012 to 2022, including climatic indicators, regional features and phosphorus application. The target variable is spring wheat yield. To ensure the accuracy of the study, the data were preprocessed and standardized, and an outlier and variance analysis was performed. The developed neural network was trained and tested to obtain the best results. The mean squared error was used as a metric for evaluating the quality of forecasting. Additionally, indicators such as mean absolute error and coefficient of determination were considered. The results of the study showed an MSE of 7.12, indicating that the model agrees well with the data and makes accurate predictions, which also suggests its practical relevance. The correlation analysis of the features showed that phosphorus application and spring wheat yield have a positive relationship. These results can be very useful for agriculture and farming enterprises, as they allow optimizing phosphorus application to the soil and increasing wheat yields