An Intelligent Hybrid Model Using CNN and RNN for Crop Yield Prediction

JUNE, KHOO YAN (2023) An Intelligent Hybrid Model Using CNN and RNN for Crop Yield Prediction. [Final Year Project Report] (Unpublished)

	PDF June Khoo Yan 24pgs.pdf Download (366kB)
	PDF (Please get the password by email to repository@unimas.my, or call ext: 3914/ 3942/ 3933) June Khoo Yan ft.pdf Restricted to Registered users only Download (1MB)

Abstract

AI has been successfully applied in agriculture field in terms of prediction, decision making, crops and soil monitoring and analysing. In this study, an intelligent hybrid model using CNN and RNN for crop yield prediction is proposed. The learning model that proposed is the combination of Convolutional Neural Network (CNN) with Recurrent Neural Network (RNN) models. CNN is a popular learning model used in predicting crop yield due to its high performance in feature extraction. CNN algorithm is used in this study due to its characteristic where it considers a smaller number of parameters in the network, and it has a lower chance of overfitting While RNN acts as a prediction model in this study. RNN has the nature of learning, a feedback network and can encode temporal sequence information. Due to the short time memory behaviour of RNN, RNN network is enhanced with LSTM cells which allows them to perform long-term memory tasks. LSTM presents memory blocks in solving the exploding and vanishing gradient problem rather than the uses of conventional RNN units. Besides, this study will discover the best parameter for crop yield prediction by identifying the correlation between them using python. Lastly, the performance of the hybrid model is evaluate using a few evaluation metrics.

Actions (For repository members only: login required)

View Item