Bionote
Tianyi Jia received his bachelor’s degree in surveying and mapping engineering from Northeastern University, China, and his master’s degree in the same field from the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, China. He is currently pursuing his Ph.D. degree in the Laboratory of Geo-information Science and Remote Sensing at Wageningen University & Research, the Netherlands. He is primarily interested in uncrewed aerial vehicle (UAV)-borne remote sensing for agricultural applications, with a particular focus on crop disease identification, and multi-modality image fusion.
Presentation Abstract
Potato is a major food consumed all over the world, yet nearly 40% of potato crops are lost to diseases caused by fungi, bacteria, viruses, and pests. Two of the most damaging pathogens are Potato Virus Y (PVY) and vascular wilt disease (blackleg), which, if left unchecked, can lead to significant yield loss. This study explored the effectiveness of combing dimensionality-reduced images, vegetation indices imagery, and specific hyperspectral bands with RGB imagery to improve disease detection using deep learning models. The results demonstrate that the fusion of RGB images with vegetation indices can significantly improve the disease detection accuracy compared to single-modality inputs, highlighting the value of multi-source data integration for precision agriculture.
Co-Researcher (Supervisors): Lammert Kooistra, Gert Kootstra, Gerrit Polder, Magdalena Smigaj, and Rick van de Zedde