Deep Learning Approach to Estimate the Maize Yield Prediction Using Data From Cameroon: Shifting the Maize Yield Production to the Next Level

State Of Art

In this era, many technologies are capable of predicting the climate in agriculture, one of which is machine learning technology (Aravind et al., 2022). Machine learning technology is one of the automatic lessons intended to enable a machine to have the ability to predict, analyze, and recognize a pattern (Ying et al., 2019). Machine learning has many methods, such as K-means, recurrent neural networks, and artificial neural networks (Jiahuan et al., 2022). Several previous studies have examined the machine learning technology used to predict climate in the agricultural sector. Using recurrent neural network methods, deep learning has been used to predict climate and estimate agricultural products based on Koppen classification. The parameters are precipitation, temperature, sun exposure, farming, and soil management (Novia et al., 2021). Previous research has also studied Machine learning methods for crop yield and climate forecasting with an assessment of the impact of change in agriculture with parameters temperature, precipitation, humidity, and wind speed and with the neural networks semi-parametric as the method used (Andrew et al., 2018).