Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68825
Volume:
10 |
11 |
Nov 2026
Pages:
1-11
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of computer science and applications
SCSVMV University.
Department of computer science and applications
SCSVMV University.
Agriculture is an important activity for food production, rural livelihoods and economic development. At the same time, farming systems face several pressures, including changing weather conditions, limited water resources, soil degradation, crop diseases, pests and the need to produce more food with fewer inputs. The growing global population, unpredictable climatic changes, and limited availability of natural resources pose significant challenges in meeting the increasing food demands of the present population. Machine learning (ML) offers methods for analysing agricultural data and supporting decisions about crop, soil and water. The review explains basic ML concepts and learning tasks before discussing applications such as crop-yield prediction, disease and weed detection, crop-quality assessment, animal monitoring, evapotranspiration estimation, soil-property prediction, remote sensing and smart farming. It also considers the growing connection between ML, the Internet of Things (IoT), unmanned aerial vehicles and geospatial data. The reviewed studies indicate increasing research interest in data-driven agriculture and the value of combining information from different sources. However, practical use is affected by data quality, local differences, infrastructure, model interpretation, computing requirements and the need for wider validation. The paper concludes that future work should focus on reliable, affordable and understandable systems that can be adapted to different farming conditions.
KEYWORDS
Machine learning has become an important approach for analysing agricultural data and supporting decisions in crop, livestock, water and soil management. The review considered in this study show that ML has been applied to crop-yield prediction, disease and weed detection, crop-quality assessment, animal behaviour monitoring, evapotranspiration estimation and soil-property prediction. More recent research also gives increasing attention to remote sensing, UAVs, IoT, deep learning and smart farming. The 2018 review by Liakos et al. provides detailed examples of agricultural applications and shows the variety of models used for different tasks. The 2025 review by Botero-Valencia et al. identifies strong growth in research publications and highlights the movement towards integrated and data-driven agricultural systems. Together, these shows the potential of ML to improve monitoring, prediction and resource management. However, successful implementation depends on reliable data, local validation, suitable infrastructure, affordable technology and clear interpretation of model outputs. A model that performs well in one dataset or region may not provide the same results elsewhere. Future research should therefore develop robust, explainable and resource-efficient systems and evaluate them under real farming conditions. Collaboration between computer science and agricultural experts will be essential. ML should be viewed as a decision-support tool that complements agricultural knowledge and helps farmers make informed choices.
[1] A. Sharma, A. Jain, P. Gupta, and V. Chowdary, “Machine learning applications for precision agriculture: A comprehensive review,” IEEE Access, vol. 9, pp. 4843–4873, 2021, doi: 10.1109/ACCESS.2020.3048415. [2] J. Jayalakshmi and M. Savitha Devi, “Predictive model construction for prediction of soil fertility using decision tree machine learning algorithm,” Kongunadu Research Journal, vol. 8, no. 1, pp. 30–35, 2021, doi: 10.26524/krj.2021.5. [3] J. Trontelj and O. Chambers, “Machine learning strategy for soil nutrients prediction using spectroscopic method,” Sensors, vol. 21, no. 12, Art. no. 4208, 2021, doi: 10.3390/s21124208. [4] G. A. Mathew, V. Jotwani, and A. K. Singh, “Soil nutrient status prediction using machine learning algorithms,” Journal of Krishi Vigyan, vol. 12, no. 3, pp. 691–694, 2024, doi: 10.5958/2349-4433.2024.00118.1. [5] O. Folorunso et al., “Exploring machine learning models for soil nutrient properties prediction: A systematic review,” Big Data and Cognitive Computing, vol. 7, no. 2, Art. no. 113, 2023, doi: 10.3390/bdcc7020113. [6] R. Raman and B. J. Chelliah, “Hybrid whale Archimedes optimization-based MLPNN model for soil nutrient classification and pH prediction,” Environmental Science and Pollution Research, vol. 30, no. 50, pp. 109389–109409, 2023, doi: 10.1007/s11356-023-29498-2. [7] R. R. Rao and U. S. Reddy, “Agrimind intelligent deep learning framework for accurate soil fertility prediction,” Scientific Reports, vol. 16, Art. no. 19657, 2026, doi: 10.1038/s41598-026-50366-9. [8] Challa et al., “Prediction of soil moisture using machine learning techniques: A case study of an IoT-based irrigation system in a naturally ventilated polyhouse,” Irrigation and Drainage, vol. 73, no. 3, pp. 1138–1150, 2024, doi: 10.1002/ird.2933. [9] M. M. Sazzad, T. Ahmed, G. Kibria et al., “IoT based soil moisture measurement and type prediction using advanced regression and machine learning models,” Scientific Reports, vol. 15, Art. no. 35730, 2025, doi: 10.1038/s41598-025-19444-2. [10] “IoT-enabled adaptive watering system with ARIMA-based soil moisture prediction for smart agriculture,” IEEE Access, vol. 13, pp. 27714–27728, 2025, doi: 10.1109/ACCESS.2025.3532447.
Publication Date
11/7/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...