International Journal of Electrical and Computer Engineering (IJECE) Vol. 15, No. 1, February 2025, pp. 783~791 ISSN: 2088-8708, DOI: 10.11591/ijece.v15i1.pp783-791  783 Journal homepage: http://ijece.iaescore.com Seasonal auto-regressive integrated moving average with bidirectional long short-term memory for coconut yield prediction Niranjan Shadaksharappa Jayanna, Raviprakash Madenur Lingaraju Department of Computer Science and Engineering, Kalpataru Institute of Technology, Tiptur, affiliated to Visvesvaraya Technological University, Belagavi, India Article Info ABSTRACT Article history: Received May 27, 2024 Revised Sep 5, 2024 Accepted Oct 1, 2024 Crop yield prediction helps farmers make informed decisions regarding the optimal timing for crop cultivation, taking into account environmental factors to enhance predictive accuracy and maximize yields. The existing methods require a massive amount of data, which is complex to acquire. To overcome this issue, this paper proposed a seasonal auto-regressive integrated moving average-bidirectional long short-term memory (SARIMA-BiLSTM) for coconut yield prediction. The collected dataset is preprocessed through a label encoder and min-max normalization is employed to change non-numeric features into numerical features and enhance model performance. The preprocessed features are selected through an adaptive strategy-based whale optimization algorithm (AS-WOA) to avoid local optima issues. Then, the selected features are given to the SARIMA-BiLSTM to predict the coconut yields. The proposed SARIMA-BiLSTM is adaptable to handling a widespread of various seasonal patterns and captures spatial features. The SARIMA-BiLSTM performance is estimated through the coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE). SARIMA-BiLSTM attains 0.84 of R2, 0.056 of MAE, 0.081 of MSE, and 0.907 of RMSE which is better when compared to existing techniques like multilayer stacked ensemble, convolutional neural network and deep neural network (CNN-DNN) and autoregressive moving average (ARIMA). Keywords: Bidirectional long short-term memory Coconut yield prediction Label encoder Seasonal auto-regressive integrated moving average Whale optimization algorithm This is an open access article under the CC BY-SA license. Corresponding Author: Niranjan Shadaksharappa Jayanna Department of Computer Science and Engineering, Kalpataru Institute of Technology, affiliated to Visvesvaraya Technological University NH-206, Vidya Nagar, Tiptur, Karnataka 572201, India Email: niranjansj555@gmail.com 1. INTRODUCTION The coconut is a significant crop which plays a crucial role in economies of numerous countries, including India, the Philippines, and Indonesia [1]. Generally, it is known as the tree of heaven, because all parts of the plants are useful and the main source of income for farmers [2]. Worldwide, it is grown in 93 countries in 12 million hectares areas with a yearly production of 59.98 million nuts. India has secured the third position globally, producing an impressive 10.56 million coconuts annually [3], [4]. Accurately predicting coconut yields is crucial in mitigating potential disasters during different stages of crop growth, impacting yield levels significantly. Monitoring consecutive time series data throughout growth periods is essential for effective coconut yield prediction [5], [6]. The yield is a complex which varies through factors