Chapter Five - Use of artificial intelligence in soybean breeding and production

Abstract

Artificial intelligence (AI) in soybean research has revolutionized various crop improvement and production aspects. This review provides predominant areas that have seen the use of AI. AI applications in phenomics have enabled collecting and analyzing high-dimensional data in soybean plants, from below- to above-ground traits, predicting phenotypes, and identifying complex patterns. In genomics, AI has improved genomic selection accuracy and identified genomic regions associated with traits of interest, such as resistance to biotic and abiotic stresses. AI has also been extensively used in detecting and managing biotic and abiotic plant stresses using RGB, multispectral, and thermal imagery from ground-based and aerial platforms. Additionally, AI has shown significant potential in yield prediction, incorporating factors such as vegetation indices, weather data, and soil properties. This review explains the concept of cyber-agricultural systems (CAS) that integrates AI, advanced sensing, computational modeling, and scalable cyberinfrastructure to optimize soybean production, enhance resource management, reduce environmental impact, and improve farm efficiency. We explain the use of CAS in crop improvement as well. We provide an exhaustive listing of challenges and future direction in the integration of AI in soybean production and crop improvement, including multi-modal and layered sensing, data availability and quality, computational modeling, AI models and tools, Cyberinfrastructure, Explainability and interpretability of AI models, AI-related impacts on privacy, ethics, and policy, Impact on Smallholder Farmers, Digital Twin, Large Soybean Datasets for community usage, and Immersive environments.

Plant phenotyping relevance

大豆育種・生産におけるAIの総説であり、植物フェノミクス、画像センシング、表現型予測を主要な対象として扱っているため、フェノタイピング方法レビューに該当する。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.