The role of big data and machine learning methods in precision agriculture

Publication date: 21-11-2025
Extent: 22 pages

Contributions by: Dhahi Al-Shammari, Si Yang Han, Patrick Filippi, Nikolas Hoskin, Sally Poole, Niranjan S. Wimalathunge, Jie Wang, and Thomas F. A. Bishop, The University of Sydney, Australia

Chapter synopsis:

The concept of precision agriculture (PA) refers to the observation, impact assessment, and timely strategic responses to fine-scale variations in the causal components of agricultural production. Big data and machine learning (ML) play integral roles in this paradigm by providing detailed insights into various farming processes. In PA, data from remote sensing platforms and weather forecasts are collected and analysed to monitor crop health and soil conditions, enabling farmers to make informed decisions. Examples of ML techniques and potential sources of big data are discussed in this chapter. Furthermore, three case studies examine the potential of big data and ML models within the PA cropping systems. The three case studies illustrated the practical integration of ML in processing this data, leading to enhanced decision-making. With the advancement of data collection techniques and machine learning methods, agricultural decision-making and overall productivity can be improved significantly.

DOI: 10.19103/AS.2025.152.07