Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{208216,
        author = {Mr.Sachin Soni and Ms.Divyani Joshi},
        title = {Machine Learning in Agriculture: A Comprehensive Survey of Applications, Methods, Challenges, and Future Directions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {4},
        pages = {726-734},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208216},
        abstract = {Agriculture is undergoing a data-driven transformation in response to climate variability, resource constraints, increasing food demand, and the need to improve productivity without proportionally increasing environmental pressure. Machine learning (ML) provides a family of statistical and computational methods that can learn relationships from multisource agricultural data and support prediction, classification, monitoring, and decision-making. 
This survey reviews recent literature on ML and deep learning (DL) in crop yield prediction, disease and pest detection, weed recognition, soil and nutrient management, irrigation, remote sensing, phenotyping, and agricultural automation. A structured literature-review protocol is presented covering database search, screening, quality assessment, evidence extraction, and thematic synthesis. The survey highlights a shift from isolated image-classification models toward multimodal systems that combine IoT, satellite/UAV imagery, weather, soil, and management data. Recent reviews report strong use of Random Forest (RF), gradient boosting, support vector methods, convolutional neural networks (CNNs), and long short-term memory (LSTM) models; however, model accuracy alone is insufficient for safe agricultural recommendations. Key unresolved issues include dataset bias, regional generalization, inconsistent evaluation, uncertainty, explainability, privacy, computational constraints, and limited field validation. 
The paper concludes with a research agenda emphasizing multimodal learning, explainable and causal ML, edge AI, privacy-preserving learning, standardized benchmarks, and farmer-centered deployment.},
        keywords = {agriculture, machine learning, precision agriculture, crop yield prediction, deep learning, computer vision, remote sensing, Internet of Things, smart farming, explainable artificial intelligence.},
        month = {September},
        }