Predicting oil palm yield using a comprehensive agronomy dataset and 17 machine learning and deep learning models

• Published in: Ecological informatics 2024-07, Vol.81, p.102595, Article 102595
• Main Authors: Jamshidi, Ehsan Jolous, Yusup, Yusri, Hooy, Chee Wooi, Kamaruddin, Mohamad Anuar, Mat Hassan, Hasnuri, Muhammad, Syahidah Akmal, Mohd Shafri, Helmi Zulhaidi, Then, Kek Hoe, Norizan, Mohd Shahkhirat, Tan, Choon Chek
• Format: Article
• Language: English
• Subjects: Agriculture; agronomy; crop management; data collection; decision support systems; Deep learning; Elaeis guineensis; industry; Machine learning; Oil palm; plant age; soil composition; supply chain; sustainable agriculture; yield forecasting; Yield prediction
• ISSN: 1574-9541
• DOI: 10.1016/j.ecoinf.2024.102595

The rising global demand for oil palm emphasizes the importance of accurate oil palm yield predictions. This predictive capability is critical for effective crop management, supply chain optimization, and sustainable farming practices. However, the oil palm sector faces challenges in yield projection, stressing a noteworthy gap in the application and evaluation of modern machine learning and deep learning technologies. Our study addressed this gap by systematically evaluating 17 machine and deep learning models in predicting oil palm yield, incorporating various agronomic parameters, e.g., soil composition, climatic conditions, plant age, and farming techniques. This holistic approach enhances the application of machine and deep learning in agriculture. Using the feature selection technique and a maximum depth of 32 and 1000 estimators, the Extra Trees Regressor exhibited positive performance, i.e., MSE = 860.36 and an R2 = 0.65, and stands out among the 17 models evaluated. Our findings also showed that incorporating a comprehensive agronomic dataset is critical to accurate yield prediction. Hence, this model and approach have the potential to be a robust decision-making tool for agronomists and farmers in the oil palm industry, setting the stage for future innovations in sustainable agriculture practices. •A comprehensive evaluation of 17 ML and DL models on a robust agronomy dataset for predicting oil palm yield.•The Extra Trees Regressor emerged as the top-performing model, with an MSE of 860.36 and an R2 value of 0.65.•Emphasized the importance of integrating detailed agronomic data to enhance yield prediction accuracy and reliability.•Provides insights into the effectiveness of various ML and DL models, offering a decision-making tool for agronomists and farmers.