Introduction of Python and Machine Learning in Phytopathology​​​​​

​​Broadcast Date: November 9, 2022​​

A recording will be posted in 5-7 business days.​

Workshop ​Summary

Python is a powerful open-source programming language known for its easy-access libraries and framework built for machine learning modeling tasks. With the advancements in plant phenotyping technologies in the past few years, the application of machine learning models in phytopathology for plant disease symptom detection and severity estimation has gained increasing interest. This proposed workshop aims to introduce python language and its environment to plant pathologists and hands-on activities on data manipulation, statistical analysis, and visualization. In addition, this workshop will also introduce machine learning packages and techniques for conducting classification modeling work using datasets from published phytopathological research. This workshop aims to assist plant pathologists in the initial learning curve of a new programming language and motivate them to explore and use python to excel in their research.

Learning Objectives

  • This workshop will provide an overview of python for data science application 
  • Introduction to python language and environment 
  • Hands-on activity on data analysis and visualization will be conducted 
  • Machine learning packages in python will be introduced 
  • Participants will involve in hands-on activity on building classification and predictive machine learning model from a published Phytopathological research


Dr. Muhammad Mohsin Raza
University of Exeter

Dr. Muhammad Mohsin ​Raza is a Postdoctoral Fellow in Data Science and Environment at The Joint Centre for Excellence in Environmental Intelligence (JCEEI) at the University of Exeter and The Alan Turing Institute in London. Dr. Raza holds a Ph.D. in Plant Pathology specializing in yield loss modeling and disease detection based on remote sensing from Iowa State University (ISU). He also has an ISU graduate certificate in Geographic Information System (GIS). In his current position, he is integrating crop and disease models with remote sensing, climate re-analysis data, and climate projections. At JCEEI, he is developing innovative approaches to understanding abiotic and biotic pressures on crop production under climate change.

Dr. Xing Wei
Purdue University

Dr. Xing Wei is a postdoctoral research assistant in the Department of Agricultural and Biological Engineering at Purdue University. He obtained his Ph.D. in Plant Pathology from Virginia Tech, where he investigated different sensor-based methods for soilborne plant disease detection and management in peanuts. In his current role at Purdue, he works on image analysis and machine learning modeling in several plant phenotyping projects to detect both abiotic and biotic stresses in various tree and crop systems. He is passionate about integrating new sensor technologies into agricultural research and production.