Bioscience Evidence 2025, Vol.15, No.5, 249-259 http://bioscipublisher.com/index.php/be 255 Figure 3 A roadmap of artificial intelligence (AI)-enabled plant breeding (Adopted from Farooq et al., 2024) 7.2 Scalability As data becomes larger and more complex, big data analysis in corn breeding requires better scalability. Cloud computing, distributed storage and high-performance computing platforms will become the basis for processing large-scale data (Xu et al., 2022; Govaichelvan et al., 2023; Zhu et al., 2024). Data sharing and joint analysis among different institutions and regions (such as federated learning) are expected to break data silos and enable models to be better applied globally (Zhao et al., 2021). Meanwhile, improving the algorithm, automating feature screening and an efficient data cleaning process will also enhance the efficiency and practicality of the analysis (Wu et al., 2024). In the future, the popularization of low-cost genotyping and high-throughput phenotypic technologies will lower the threshold, enabling breeding projects of different scales and resource conditions to use big data methods. 7.3 Towards sustainable maize production Big data combined with artificial intelligence-driven smart breeding (emphasizing the use of computers and algorithms to improve breeding) is providing new support for sustainable corn production. By more accurately predicting and optimizing the interaction between genotypes and the environment, new varieties with high yield, strong stress resistance and higher resource utilization rate can be bred, thereby enhancing food security and environmental adaptability (Xu et al., 2022; Farooq et al., 2024; Liu et al., 2025). Meanwhile, digital decision support systems and intelligent management platforms also play a role in precision agriculture, such as more scientific management of fertilizer and water, prevention and control of pests and diseases, and reduction of carbon emissions. All these can promote the development of green agriculture (emphasizing ecological protection and low-carbon development) (Wolfert et al., 2017; Lassoued et al., 2021). Furthermore, the open and shared breeding platform and the sound data governance system will further promote international cooperation and technological innovation, and provide assistance in addressing the challenges brought about by climate change and population growth (Zhu et al., 2024). 8 Conclusion With the help of big data analysis in combination with machine learning and artificial intelligence (common methods in intelligent breeding), the prediction process of corn breeding has become faster and more accurate. After combining data from different sources such as genomics, phenotypic information and environmental conditions, the algorithm can automatically select key features and improve the model, thereby making the
RkJQdWJsaXNoZXIy MjQ4ODYzNA==