Remote sensing systems
University of Manitoba
Department of Plant Science
Digital Agronomy & Weeds Lab
Advancing sustainable agriculture through precision technology and data-driven research
About the Lab
Bridging traditional weed science with digital agriculture
The Digital Agronomy and Weeds Lab (DAWL) at the University of Manitoba focuses on advancing sustainable crop production through precision agriculture and data-driven weed management.
Our research integrates remote sensing, UAV-based technologies, and field experimentation to better understand crop–weed interactions and improve agricultural decision-making.
We aim to bridge the gap between scientific innovation and practical applications for farmers and industry stakeholders.
Principal Investigator
Dr. Dilshan Benaragama
Assistant Professor
Dr. Benaragama leads the Digital Agronomy and Weeds Lab at the University of Manitoba. His research focuses on developing innovative approaches to weed management and crop production using digital agriculture, UAV-based sensing, remote sensing, and data-driven decision support tools.
Research Areas
What we do
Our research integrates traditional weed science with digital technologies to advance sustainable crop production.
Integrated weed management
Weed Science & Management
Analytics and AI
Digital Agriculture & AI
People
Meet the DAWL team
A quick overview of the researchers, staff, and students advancing digital agronomy and weed science at the University of Manitoba.
DD
Principal Investigator
Dr. Dilshan Benaragama
Assistant Professor
Dr. Benaragama leads the Digital Agronomy and Weeds Lab at the University of Manitoba. His research focuses on developing innovative approaches to weed management and crop production using digital agriculture, UAV-based sensing, remote sensing, and data-driven decision support tools.
Research Staff
Dr. Mujahid Hussain
Postdoctoral Fellow
UAV spraying • Precision agriculture
Dr. Kenneth Anku
Postdoctoral Fellow
Remote sensing • Plant physiology
Mike Runzika
Research Technician
Field trials • Data collection
Test_1
Test
Test
Graduate Students
Shirmith Nirmal
M.Sc. Student
Machine learning for weed detection
Pantha
M.Sc. Student
UAV-based crop monitoring
Indeera
Ph.D. Student
Precision herbicide application
Uthpala
M.Sc. Student
Integrated weed management
Pantha Azad
M.Sc. Student
test run
Publications
Recent publications
Selected research outputs from DAWL and collaborators in weed science, crop–weed interactions, remote sensing, and sustainable agricultural systems.
CWRepViT-Net: An encoder-decoder deep learning framework with RepViT blocks for crop weed semantic segmentation in soybean fields through their life journey
Masoomeh Gomroki, Dilshan Benaragama, Christopher James Henry, Nasem Badreldin, Robert Gulden
Smart Agricultural Technology, 12: 101472
The impact of herbicide-resistant canola systems on the weed community dynamics in the Canadian Prairies
Theodore Chastko, Dilshan I. Benaragama, Julia L. Leeson, Christian J. Willenborg
Canadian Journal of Plant Science, 104(5): 514
Revisiting cropping systems research: An ecological framework towards long-term weed management
Dilshan I. Benaragama, Christian J. Willenborg, Steve J. Shirtliffe, Rob H. Gulden
Agricultural Systems, 213: 103811
Weed dynamics under diverse nutrient management and crop rotation practices in the dry zone of Sri Lanka
D. Wickramasinghe, D. I. Benaragama, and co-authors
Frontiers in Agronomy, 5: 1211755
Posters & Abstracts
Research posters and abstracts
Explore selected DAWL posters, abstracts, and conference research materials. Poster PDFs can be opened in a new tab or downloaded.
Click to open PDF
Poster2025MAC Poster
Development of Remote Sensing Tools to Evaluate In-Field Results of Best Management Practices (BMPs) for Peas
MD Pantha Azad Sabbyashachi, Kristen P. MacMillan, Claudia Quilesfogel-Esparza, Brodie Erb, and Dilshan Benaragama
This poster presents UAV-LiDAR approaches for evaluating best management practices in field pea. The study demonstrates how LiDAR-derived crop height, canopy volume, and structural measurements can help distinguish management responses and support data-driven recommendations for seeding rates and sowing times.
Connect with DAWL
Want to collaborate or join the lab?
Contact the Digital Agronomy & Weeds Lab to discuss research collaboration, student opportunities, postdoctoral positions, field work, or outreach.