Journal of Agriculture and Livestock Farming

ABSTRACT

The global population is rapidly increasing and is expected to exceed 9 billion by 2050, resulting in significant challenges for agriculture due to factors such as industrialization, reduced farmland, and biotic and abiotic stresses. To address these challenges and ensure future sustainability, the agriculture system needs to become more productive, efficient, and resilient. Artificial intelligence (AI) and machine learning (ML) have emerged as powerful tools to transform the agricultural sector. Agricultural productivity is greatly influenced by biotic and abiotic stresses, and developing climate-smart crops through conventional breeding techniques is time-consuming and challenging. Plant phenotyping, which involves measuring specific plant features related to function, is crucial in breeding for target traits. However, traditional phenotyping methods are laborious, error-prone, and less accurate, particularly under stress conditions. To overcome these limitations, researchers have focused on developing high-throughput phenotyping technologies. State-of-the-art imaging techniques, such as light detection and ranging (LIDAR), remote sensing, and RGB imaging, combined with autonomous carriers like unmanned aerial vehicles (UAVs) and ground robots, enable real-time and high-throughput phenotyping of morphological, physiological, and stress-related traits. ML tools can compartmentalize big data, identify related traits, classify them, quantify their expression, and predict their function within the plant system. AI and ML offer multidisciplinary approaches for analyzing big data accumulated over time, leading to the discovery of patterns and systematic data of interest, such as stress phenotypes. Using these technologies, researchers worldwide can expedite agricultural research and develop climate-smart crops. The future of AI and ML in agriculture is promising, as they can lead to new scientific discoveries and help overcome the challenges of limited resources in food production.

Article History

KEYWORDS

1. Stress phenotyping
2. Artificial intelligence
3. Machine learning
4. Climate-smart crops