Bioscience Evidence 2025, Vol.15, No.5, 249-259 http://bioscipublisher.com/index.php/be 249 Research Insight Open Access Big Data Analytics in Enhancing Maize Breeding Programs Xian Zhang, Jiamin Wang, Yunchao Huang Hainan Provincial Key Laboratory of Crop Molecular Breeding, Sanya, 572025, Hainan, China Corresponding email: yunchao.huang@hitar.org Bioscience Evidence, 2025, Vol.15, No.5 doi: 10.5376/be.2025.15.0025 Received: 26 Aug., 2025 Accepted: 30 Sep., 2025 Published: 15 Oct., 2025 Copyright © 2025 Zhang et al., This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Preferred citation for this article: Zhang X., Wang J.M., and Huang Y.C., 2025, Big data analytics in enhancing maize breeding programs, Bioscience Evidence, 15(5): 249-259 (doi: 10.5376/be.2025.15.0025) Abstract With the development of high-throughput omics, remote sensing and artificial intelligence, big data is transforming corn breeding. Research shows that the combination of machine learning and multi-omics can better predict and screen the yield and stress resistance of corn, and also accelerate the breeding speed of new varieties. The emergence of unmanned aerial vehicle (UAV) sensors, deep learning, and federated learning has made high-throughput phenotyping, early yield prediction, and multi-party collaborative breeding work easier to achieve. Meanwhile, the multi-genome database of corn and the intelligent analysis platform have also laid the foundation for the integration and sharing of global resources. Of course, this process also poses many challenges, such as different data sources, the complexity of biological issues themselves, and the influence of socio-economic factors. Overall, however, big data has become an important force driving corn breeding to be more intelligent, precise and sustainable. Next, it is necessary to strike a balance between technological innovation and green development and enhance cooperation. Our research objective is to explore how these new methods can be utilized to help corn breeding serve global food security more efficiently. Keywords Corn breeding; Big data analysis; Machine learning; High-throughput phenotype; Intelligent breeding 1 Introduction Corn, as a major global food crop, high-yield, stress-resistant and highly adaptable varieties are of great significance to food security and sustainable agricultural development. Traditional corn breeding methods, such as population selection and hybrid breeding, were of great help to crop improvement in the past. However, these methods have deficiencies in accuracy and efficiency, and have been difficult to meet the increasing demand for food and cope with the complex environmental challenges (Andorf et al., 2019; Bhuiyan et al., 2025). In recent years, high-throughput omics and information technology have developed rapidly, and agriculture has entered the era of big data. Big data contains information in multiple aspects such as genomics, phenotypes and the environment. Algorithms such as artificial intelligence (AI) and machine learning (ML) can be used to analyze and predict the complex relationship between genes and the environment (Nepolean et al., 2018; Najafabadi et al., 2023; Crossa et al., 2024; Farooq et al., 2024; Wu et al., 2024; Zhu et al., 2024). These technologies have made trait prediction in corn breeding more accurate, accelerated the cultivation of new varieties, and also promoted the emergence of intelligent and precise breeding (Jiang et al., 2019; Fritsche-Neto et al., 2021). This study will introduce the progress of big data analysis in corn breeding, with a focus on the integration of multi-omics data and the application of AI and ML in gene mining, phenotypic prediction, and genomic selection. At the same time, the role of these methods in enhancing efficiency, improving decision-making and addressing future challenges will also be discussed. Finally, the existing problems will also be pointed out and the directions for future research will be proposed. Through interdisciplinary cooperation and technological innovation, big data-driven corn breeding is expected to provide support for global food security and sustainable development. 2 The Role of Big Data in Modern Breeding 2.1 Sources of big data in maize research Modern corn breeding cannot do without various types of big data. These data provide a basis for trait prediction and genetic improvement. The main sources include:
RkJQdWJsaXNoZXIy MjQ4ODYzNA==