Stacking ensemble machine learning model for smart drip irrigation-based nutrient prediction in oil palm seedlings
Sunanto1, 2, Wan Suryani Wan Awang2, Fatma Susilawati Mohamad2 and Mohd Khalid Awang2
Faculty Informatics and Computing,University Sultan Zainal Abidin, Besut Campus,Terengganu,Indonesia2
Corresponding Author : Sunanto
Recieved : 01-January-2025; Revised : 22-October-2025; Accepted : 19-November-2025
Abstract
This study explores the application of precision agriculture, which leverages modern computer-based technologies to enhance agricultural yields by predicting the needs for fertilizers, soil acidity, water, disease management, and overall production improvements. Precision agriculture typically employs a variety of sensors, actuators, and control systems to monitor and optimize agricultural practices. However, the high cost of these technologies has limited their accessibility to farmers in developing and underdeveloped countries. To address this challenge, machine-learning techniques are proposed as a cost-effective alternative, utilizing data generated from precision agriculture systems to create predictive models. These models can forecast requirements for fertilizers, nutrients, and water in smart drip irrigation systems, thereby optimizing resource use. This study focuses on developing a stacking ensemble machine learning model to predict the fertilizer, soil acidity, and water needs of oil palm seedlings. The proposed model integrates various base algorithms such as k-nearest neighbours (KNN), decision tree (DT), support vector machine (SVM), and linear discriminant analysis (LDA). The performance of these models is evaluated using a confusion matrix, receiver operating characteristic (ROC), and area under the curve (AUC) curve metrics. Results indicate that the extra trees (ET) meta-model achieved the highest accuracy at NPK_Drip 95%, pH_Drip 93% and Water_Drip 97%, followed by random forest (RF) and logistic regression (LR) with comparable performances.
Keywords
Precision agriculture, Machine learning, Stacking ensemble model, Smart drip irrigation, Oil palm seedlings.
Cite this article
Sunanto, Awang WSW, Mohamad FS, Awang MK. Stacking ensemble machine learning model for smart drip irrigation-based nutrient prediction in oil palm seedlings. International Journal of Advanced Technology and Engineering Exploration. 2025;12(132):1700-1721. DOI : 10.19101/IJATEE.2025.121220048