A machine learning-based smart crop yield prediction for selecting the best crop under specific climate and soil conditions
Plant Science Today · 21.07.2026
DOI: 10.14719/pst.13575 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plant Science Today, online erschienen am 21.07.2026. Verfasst von M D Rhowel. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate crop yield prediction and appropriate crop selection are essential for improving agricultural productivity and sustainability under varying soil and climate conditions. This study developed and evaluated a machine learning (ML)–based crop yield prediction framework to support crop selection for maize, rice, wheat and barley, using agricultural data comparable to conditions in Infanta, Pangasinan, Philippines. A dataset containing soil, climate and farm management variables was analysed using deep neural network (DNN), convolutional neural network–long short-term memory (CNN-LSTM), random forest (RF) and support vector regression (SVR) models. Model performance was evaluated using the coefficient of determination (R²), mean absolute error (MAE) and root mean square error (RMSE) metrics. Results showed that the RF model achieved the highest predictive accuracy (R² = 0.98), while the CNN-LSTM model produced the lowest prediction errors, demonstrating a strong capability to capture temporal climate variability. Predicted yield ranges indicated that maize and rice exhibited higher yield potential under favourable soil moisture conditions, whereas wheat and barley were more suitable for upland and moderately fertile soils. Crop suitability mapping and uncertainty analysis further supported site-specific crop recommendations. The results confirm that ML–based decision support systems can effectively guide crop selection and promote sustainable, data-driven agricultural planning.
Zitieren
APA
Rhowel, M. D. (2026). A machine learning-based smart crop yield prediction for selecting the best crop under specific climate and soil conditions. Plant Science Today. https://doi.org/10.14719/pst.13575
Vancouver
Rhowel MD. A machine learning-based smart crop yield prediction for selecting the best crop under specific climate and soil conditions. Plant Science Today. 2026. doi:10.14719/pst.13575
BibTeX
@article{Rhowel2026,
author = {Rhowel, M D},
title = {A machine learning-based smart crop yield prediction for selecting the best crop under specific climate and soil conditions},
journal = {Plant Science Today},
year = {2026},
doi = {10.14719/pst.13575}
}
EUVIMED