MPB_2024v15n5

Molecular Plant Breeding 2024, Vol.15, No.5, 233-246 http://genbreedpublisher.com/index.php/mpb 242 valuable data on crop phenotypes (Danilevicz et al., 2021). However, the resolution and accuracy of these sensors can be further improved to better capture subtle phenotypic variations associated with disease resistance. Another potential advancement lies in the integration of more sophisticated data analysis tools. Machine learning and artificial intelligence (AI) have already shown promise in processing large datasets generated by HTP platforms (Shakoor et al., 2017; Tayade et al., 2022). Future developments could focus on refining these algorithms to improve their predictive accuracy and scalability. For instance, the use of deep learning techniques could enhance the ability to identify and quantify disease symptoms from complex image data, thereby providing more accurate assessments of disease resistance (Smith et al., 2021). The scalability of HTP systems can be enhanced by developing more robust and user-friendly data management infrastructures. Efficient data storage, retrieval, and analysis are critical for handling the vast amounts of data generated by HTP platforms. Advances in cloud computing and big data technologies could play a pivotal role in this regard, enabling researchers to scale up their phenotyping efforts without being constrained by data management challenges (Araus and Cairns, 2014). 8.2 Integration of artificial intelligence and robotics in fully automated phenotyping systems The integration of AI and robotics into HTP systems represents a transformative step towards fully automated phenotyping. AI can be employed to automate the analysis of phenotypic data, reducing the need for manual intervention and increasing the throughput of phenotyping processes. For example, AI algorithms can be trained to recognize specific disease symptoms in wheat, allowing for rapid and accurate disease resistance screening (Juliana et al., 2018; Tayade et al., 2022). Robotics can further enhance the automation of HTP systems by enabling the deployment of phenotyping platforms in diverse field conditions. Unmanned aerial systems (UAS) or drones equipped with advanced sensors can be used to collect high-resolution phenotypic data across large field plots, providing a non-invasive and efficient means of monitoring crop health (Singh et al., 2019). Ground-based robotic platforms can also be utilized to navigate through field plots, capturing detailed phenotypic data at the plant level (Ninomiya, 2022). The combination of AI and robotics can lead to the development of fully automated phenotyping systems that operate continuously and autonomously. Such systems could significantly reduce the labor and time required for phenotyping, allowing researchers to screen larger populations of wheat for disease resistance traits. Additionally, the integration of AI and robotics can improve the consistency and repeatability of phenotyping measurements, leading to more reliable data for breeding programs (Goggin et al., 2015). 8.3 The role of international collaborations in advancing HTP applications for wheat breeding International collaborations play a crucial role in advancing the applications of HTP for wheat breeding. Collaborative efforts can facilitate the sharing of resources, expertise, and data, thereby accelerating the development and deployment of HTP technologies. For instance, the establishment of global phenotyping networks can enable researchers to access diverse germplasm collections and phenotyping platforms, fostering the exchange of knowledge and best practices (Danilevicz et al., 2021). Collaborations between research institutions, industry partners, and governmental organizations can also drive the standardization of HTP protocols and data formats. Standardization is essential for ensuring the comparability and interoperability of phenotypic data across different studies and regions. By working together, stakeholders can develop common guidelines and frameworks for HTP, promoting the widespread adoption of these technologies in wheat breeding programs (Araus and Cairns, 2014). Furthermore, international collaborations can support the development of training programs and capacity-building initiatives. Training researchers and breeders in the use of HTP technologies and data analysis tools is critical for maximizing the impact of these innovations. Collaborative training programs can help build a skilled workforce capable of leveraging HTP for disease resistance screening and other breeding objectives (Shakoor et al., 2017).

RkJQdWJsaXNoZXIy MjQ4ODYzMg==