Manish Kumar Patel

Biography

I am a motivated and innovative graduate with an aptitude for problem-solving and with emphasis on details. I have been working in the domain of Remote Sensing of Vegetation and am keen to explore its further advancements particularly integrating hyper/multi-spectral, chlorophyll fluorescence, and LiDAR data.
Currently, I am working as a Postdoctoral research scientist in CSIRO, Australia. I am developing a computer vision, deep learning and drone-remote sensing based disease phenotyping solution.
I have been awarded a joint PhD from the Group of Eight (Go8, comprises Australia’s leading research-intensive universities) research program between the prestigious University of Melbourne and the University of Sydney in 2022. My research objective was to optimize the use of nitrogen fertiliser over the crop field by using remote sensing data. I am also currently serving as a manager of the Melbourne Unmanned Aircraft System Integration Platform (MUASIP).
Prior to joining PhD, I did a master degree, Master of Technology (M.Tech) in ‘Geo-informatics and Natural Resources Engineering’ from Centre of Studies in Resources Engineering (CSRE), Indian Institute of Technology Bombay (IIT Bombay), Mumbai, India.
My research work focuses on developing remote sensing models, harnessing the information obtained through field spectroradiometer data for canopy nitrogen and biomass prediction. These models are driven by the radiometric responses of crop canopies for distinct (independent of other extraneous factors such as biomass, LAI, phenological conditions and seasons) chlorophyll/nitrogen signals in the optical range. Machine learning and deep learning models are also being used to increase the remote sensing model's efficiency under contrasting growth and crop conditions. Scaling up from proximal to low altitude to satellite level modes is an included objective that is advantageous for the continent level vegetation nitrogen mapping and monitoring. As the vegetation is itself highly complex and dynamic in space, season and time and this makes this field more attractive and challenging simultaneously.