Abstract
The food prices are on the rise globally and this fact increases the importance of the agriculture sector. Considering the significance of the agriculture, the nowcasting of the agricultural revenue and the agricultural land of Türkiye are considered in this work. The agricultural revenue and the agricultural land data are taken from the official sources followed by their seasonal-trend analysis. The seasonality and nonlinearity of the agricultural revenue and the agricultural land are then carefully investigated. As the next step, a multilayer perceptron network is developed in Python programming language for the modelling and nowcasting the agricultural revenue and the land data. The developed multilayer perceptron network is built as an autoregressive network structure enabling the utilization of the previous values of the data as inputs. The 75% of the data is taken as the training data and the developed network is trained for the revenue and the land data separately. Then, the remaining 25% of the data is used as the test data. As the next step, the actual agricultural revenue and the agricultural land data are plotted together with the results of the developed autoregressive multilayer perceptron network. The plots indicate an accurate modelling and nowcasting. In addition, the performance metrics of the developed model such as the root mean square error, mean absolute error, mean absolute percentage error and the coefficient of determination are also calculated. The values of these performance metrics verify the accuracy of the developed autoregressive multilayer perceptron network for the modelling and nowcasting of the agricultural revenue and the agricultural land data. It is argued that the nowcasting of the agricultural revenue is an important concept for the estimation of the food prices therefore the developed model will be helpful for the food prices planners.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.