Journal article · 2026 · Open access
Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture
Smart Agricultural Technology, 15, 102486 · Published 18 August 2026 · DOI 10.1016/j.atech.2026.102486
In brief
“Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture” is a 2026 journal article by Md Abu Jabed and 3 co-authors, published in Smart Agricultural Technology. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Smart Agricultural Technology.
- Citations
- 0
- References
- 84
- Authors
- 4
Abstract
Accurate crop yield prediction is essential for strengthening food security and supporting evidence-based agricultural planning, particularly in climate-sensitive regions such as Bangladesh. However, reliable modeling remains challenging due to complex interactions among environmental, agronomic, and contextual factors, as well as the limited utilization of heterogeneous data sources. This study develops a multimodal machine learning framework for rice yield prediction in the Chittagong district by integrating structured numerical variables with textual agricultural information. Numerical inputs include soil characteristics, meteorological conditions, and management practices, while textual data from agronomic reports are transformed into structured representations using TF-IDF vectorization. A leakage-free experimental pipeline is implemented, ensuring that all preprocessing steps are fitted exclusively on the training data. The dataset is partitioned into training, validation, and testing sets using a 70%–15%–15% split. A range of machine learning models, including Decision Tree, Random Forest, Support Vector Regressor, Artificial Neural Network, Bagging, and Boosting, are evaluated under numerical-only, text-only, and fused feature settings. To enhance predictive performance, ensemble strategies comprising averaging, stacking, and Optimized Weighted Ensemble (OWE) are further investigated. Experimental results demonstrate that multimodal fusion consistently improves prediction accuracy over single-modality approaches, with the OWE model achieving the best overall performance. A computational cost analysis confirms that, despite higher training overhead, ensemble methods maintain low inference time, supporting their practical applicability. Overall, the proposed framework offers a scalable and robust approach for rice yield prediction in data-limited agricultural environments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jabed, M. A., Murad, M. A. A., Kasmiran, K. A., & Husin, N. A. (2026). Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture. Smart Agricultural Technology, 15, 102486. https://doi.org/10.1016/j.atech.2026.102486
MLA 9
Jabed, Md Abu, et al. “Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture.” Smart Agricultural Technology, vol. 15, 2026, p. 102486. https://doi.org/10.1016/j.atech.2026.102486.
Chicago
Jabed, Md Abu, Masrah Azrifah Azmi Murad, Khairul Azhar Kasmiran, and Nor Azura Husin. 2026. “Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture.” Smart Agricultural Technology 15: 102486. https://doi.org/10.1016/j.atech.2026.102486.
Harvard
Jabed, M. A. et al. (2026) ‘Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture’, Smart Agricultural Technology, 15, p. 102486. doi:10.1016/j.atech.2026.102486.
IEEE
M. A. Jabed, M. A. A. Murad, K. A. Kasmiran, and N. A. Husin, “Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture,” Smart Agricultural Technology, vol. 15, p. 102486, 2026, doi: 10.1016/j.atech.2026.102486.
BibTeX
@article{jabed2026integrating,
title = {{Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture}},
author = {Jabed, Md Abu and Murad, Masrah Azrifah Azmi and Kasmiran, Khairul Azhar and Husin, Nor Azura},
journal = {Smart Agricultural Technology},
year = {2026},
volume = {15},
pages = {102486},
doi = {10.1016/j.atech.2026.102486},
url = {https://doi.org/10.1016/j.atech.2026.102486}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- rice yield prediction
- multimodal fusion
- TF-IDF
- ensemble learning
- stacking
- data leakage
- Chittagong district
- Bangladesh
Work with this paper
Most-cited papers in Agricultural and Biological Sciences
- A Revised Medium for Rapid Growth and Bio Assays with Tobacco Tissue CulturesToshio Murashige, Folke Karl Skoog · Physiologia Plantarum · 1962 · 68,073 citations
- AMPLIFICATION AND DIRECT SEQUENCING OF FUNGAL RIBOSOMAL RNA GENES FOR PHYLOGENETICST. J. White, Thomas D. Bruns, Steven S. Lee and 1 more · Elsevier eBooks · 1990 · 37,197 citations
- Methods for Dietary Fiber, Neutral Detergent Fiber, and Nonstarch Polysaccharides in Relation to Animal NutritionPeter J. Van Soest, James B. Robertson, BERTHA A. LEWIS · Journal of Dairy Science · 1991 · 29,489 citations
- AN EXAMINATION OF THE DEGTJAREFF METHOD FOR DETERMINING SOIL ORGANIC MATTER, AND A PROPOSED MODIFICATION OF THE CHROMIC ACID TITRATION METHODAllan Walkley, Ian Armstrong Black · Soil Science · 1934 · 22,994 citations
- Floral dip: a simplified method for Agrobacterium ‐mediated transformation of Arabidopsis thalianaSteven John Clough, Andrew F. Bent · The Plant Journal · 1998 · 22,047 citations
All highly cited Agricultural and Biological Sciences papers
Questions about this paper
How do I cite this paper in APA style?
Jabed, M. A., Murad, M. A. A., Kasmiran, K. A., & Husin, N. A. (2026). Integrating numerical and textual data for accurate rice yield prediction: A novel ensemble learning framework for regional agriculture. Smart Agricultural Technology, 15, 102486. https://doi.org/10.1016/j.atech.2026.102486
How many times has this paper been cited?
0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Smart Agricultural Technology: sign in and open the PDF from this page.
Who wrote this paper?
Md Abu Jabed, Masrah Azrifah Azmi Murad, Khairul Azhar Kasmiran, Nor Azura Husin.
What is the DOI of this paper?
10.1016/j.atech.2026.102486, permanently at https://doi.org/10.1016/j.atech.2026.102486. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.