Mr. Zhongzhong Niu, Purdue University, United States
Zhongzhong Niu is a doctoral candidate at Purdue University’s College of Engineering, where he focuses on spatial-spectral analysis for high-dimensional plant images to detect chemical injuries and diseases. He holds a Master’s degree in Agricultural Engineering from Purdue and a Bachelor’s degree in the same field through a joint program between Purdue University and China Agricultural University. With extensive experience as a Research Assistant, Zhongzhong has led cutting-edge machine learning projects for hyperspectral imaging and plant disease detection. His work, supported by prominent organizations such as FMC Corporation and Sumitomo Chemical Co., Ltd., has significantly advanced the application of machine learning in smart agriculture. He has published multiple peer-reviewed articles and secured a U.S. patent for innovations in environmental monitoring technology. His technical expertise includes Python, MATLAB, hyperspectral imaging, cloud computing, and big data analytics, making him a key contributor to modern agricultural practices.
Professional Profile:
Summary of Suitability for Best Researcher Award
Zhongzhong Niu holds a solid educational foundation with a Bachelor’s degree in Agricultural Engineering from a joint program between Purdue University and China Agricultural University. He advanced his studies at Purdue University, obtaining a Master’s degree in Agricultural Engineering and is currently pursuing a Ph.D. in the College of Engineering. His dissertation focuses on “Spatial-Spectral Analysis for High-Dimensional Plant Images for Chemical Injury and Disease Detection,” indicating a deep specialization in hyperspectral imaging and its applications in agriculture.
Education
- Purdue University, West Lafayette, IN
- Doctoral Candidate in College of Engineering
- Dissertation: Spatial-Spectral Analysis for High-Dimensional Plant Images for Chemical Injury and Disease Detection
- Duration: September 2022 – June 2025
- Purdue University, West Lafayette, IN
- Master of Science in Agricultural Engineering
- Duration: September 2019 – August 2022
- Purdue University – China Agricultural University
- Bachelor of Science in Agricultural Engineering
- Duration: September 2015 – May 2019
Professional Experience
- Purdue University, West Lafayette, IN
- Research Assistant
- Duration: August 2020 – Present
- Spearheaded machine learning initiatives for herbicide action analysis and chemical stress detection.
- Utilized Python, MATLAB, PyTorch, and sklearn for model development.
- Employed R for statistical analysis and managed datasets with Hadoop and Spark.
- Research focus includes applying large language models (LLM) in smart agriculture.
- Purdue University, West Lafayette, IN
- Lead Data Scientist (Sponsored by FMC Corporation)
- Duration: January 2022 – Present
- Collaborated on wheat disease management using hyperspectral and multispectral imaging.
- Developed predictive models with Python and MATLAB, improving disease identification.
- Indiana State Government
- Data Scientist
- Duration: January 2021 – January 2023
- Created a high-throughput model for detecting herbicide damage in soybeans using hyperspectral imaging.
- Managed large-scale datasets and improved data processing capabilities.
- Sumitomo Chemical Co., Ltd
- Machine Learning Engineer
- Duration: September 2020 – December 2021
- Led a $3.5M project analyzing herbicide modes of action with hyperspectral imaging and machine learning.
- Managed all research phases and developed models with over 85% accuracy.
- Purdue University, West Lafayette, IN
- Full-Stack Developer
- Duration: September 2019 – September 2020
- Developed mobile and desktop applications for dust concentration detection.
- Secured a U.S. patent for image-processing algorithms and applications.
Publication top Notes:
Early Detection of Dicamba and 2,4-D Herbicide Drifting Injuries on Soybean with a New Spatial–Spectral Algorithm Based on LeafSpec, an Accurate Touch-Based Hyperspectral Leaf Scanner
Hyperspectral Analysis for Discriminating Herbicide Site of Action: A Novel Approach for Accelerating Herbicide Research