Prof Ji Zhou leads NIAB’s Data Sciences Department, since his appointment in early 2020. His department focuses on developing multi-scale indoor and in-field plant phenotyping and AI-driven phenotypic analysis using satellite, Agri-Drones, LiDAR, self-developed low-cost remote sensing, Videometer and Opera HCS system. Based on the large-scale and multi-dimensional phenotyping, genotyping and environmental datasets acquired, Ji and his lab develop open-source phenotypic analytic solutions to address yield, quality and disease related challenges using Artificial Intelligence (AI, machine learning and deep learning), computer vision, Internet of Things (IoT) and big data analytics for UK’s key agricultural and horticultural crops such as wheat, Brassica, strawberry, lettuce and orchard fruits (e.g. apple).
Some impactful work from his lab includes high-throughput 3D crop mapping using LiDAR (CropQuant-3D), low-cost distributed or mobile phenotyping platforms (CropQuant, CropSight and Leaf-GP), large-scale aerial crop analytic software (AirMeasurer and AirSurf), automated AI-based seed screening system (SeedGerm), and cellular trait analytic packages (PDQuant, CalloseMeasurer and StomataMeasurer). Ji’s department collaborates closely with leading research groups in the UK, Japan and China (e.g. the University of Cambridge, the John Innes Centre, the Kyoto University and the Chinese Academy of Sciences), through which joint research efforts are made to assess plant performance in the context of global climate change, as well as the quantification of genetic gain, trait stability, yield prediction and genotyping-to-phenotyping linkage from larger populations and across different sites. Also, Ji built a close relationship with leading industrial companies such as Bayer Crop Science, Syngenta and China Seeds.
Prior to joininf NIAB, he was a project leader at Earlham, a joint research fellow between JIC and TGAC; and, a post-doctoral research fellow at The Sainsbury Laboratory (TSL), all of which were based at Norwich Research Park. He also worked in industry for nearly a decade, initially as a bilingual IT professional in Shanghai, then a systems analyst and a project consultant at the Aviva group, Norwich UK. Since his PhD in computer science at the University of East Anglia (UEA) in 2011, Ji has published over 25 research articles on top journals such as Nature, Nature Plants, Plant Cell, New Phytologist and Plant Physiology, 3 book chapters, and 3 IEEE/ACM conference proceedings, many of which Ji was a corresponding or leading author. From 2016 onwards, his research has been cited over 1,700 times, with an i10-index over 21. Ji’s academic work has also led to successful patentable inventions, e.g. UKIPO patent (GB 2553631), which were granted and licensed. He holds a full professorship at the China-UK Crop Phenomics Research Center, Nanjing Agricultural University (NAU, a leading agricultural and crop research university in China), an honorary senior lecturer at UEA, and an associate editor for reputable journals such as the Crop Journal, Plant Phenomics and Horticulture Research.
Recent publications (* corresponding author)
- Yang W*, Doonan J, Hawkesford M, Pridmore T, Zhou J* (2021). State-of-the-Art Technology and Applications in Crop Phenomics. Frontiers in Plant Science, 12.
- Zhu Y, Sun G, Ding G, et al., Ober E, Zhou J* (2021). Large-scale field phenotyping using backpack LiDAR and CropQuant-3D to measure structural responses in wheat. Plant Physiology, July: kiab324.
- Colmer J, O’Neill C, Wells R, et al., Penfield S*, Zhou J* (2020). SeedGerm: a cost-effective phenotyping platform for automated seed imaging and machine-learning based phenotypic analysis of crop seed germination. New Phytologist, 228(2): 778-793.
- Bauer A, Bostrom A, et al., Kirwan J, Zhou J* (2019). Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: a case study of lettuce production. Horticulture Research, 6(1):1-12.
- Alkhudaydi T*, Reynolds D, Griffiths S, Zhou J*, De La Iglesia B (2019). An exploration of deep learning based phenotypic analysis to detect spike regions in field conditions for UK bread wheat. Plant Phenomics, (736876): 1-17.