Central AsianResearch Index

Application of Artificial Neural Network for Wheat Yield Prediction

Применение искусственной нейронной сети для прогнозирования урожайности пшеницы

The results of wheat yield forecasting based on an artificial neural network (ANN) are presented. The use of ANN is due to the use of such non-linear factors as air temperature and precipitation as predictors. The study also used meteorological, agrochemical and phytosanitary factors that have the greatest impact on wheat yield. These factors were used as input variables to the backpropagation neural network. After training the ANN and obtaining predictive data, good results were achieved for wheat yield prediction (p = 0.52, MAPE = 12.02%, RMSE = 3.368). The developed model can be easily adapted to other cultures and locations, and can also be improved by using new data sources

Сведения

Журнал
Trudy Universiteta
Опубликовано
2023 · Т. 3
Язык
Английский
ISSN
1609-1825 · 2710-3382
Издатель
Karaganda Technical University named after Abylkas Saginov