Project Goal

To provide a high performance solution for P2IRC researchers to efficiently and effectively collect, use, store, analyze, and share phenomic data.

Project Summary

Kevin Schneider, Chanchal Roy, and their team of computer scientists are working to develop ways for P2IRC researchers to manage their data so they can achieve their research objectives and collaborate with other researchers more efficiently. This project involves creating a private P2IRC "cloud" where multiple researchers can store their crop phenomics research data. It will allow scientists to model, analyze, visualize, and explore multi-dimensional data more quickly and efficiently. Researchers will also be able to move non-sensitive data to a public cloud so they can collaborate with researchers around the world.

Specifically, the P2IRC cloud will provide researchers with:

  • Data management services for collecting, storing, and sharing large quantities of phenotypic data.

  • Techniques and tools to support fusing, managing, provenance tracking, preserving, and securely accessing diverse phenomic datasets.

  • Software which will allow researchers to integrate and analyze data from other P2IRC projects.

Project Results to Date

Within Project 3.1, there are many different focus areas that will enable researchers to build their own data piplines without having to technically compute their data:

  • Big data resource management
  • Deep learning infrastructures
  • Cloud analysis support
  • Using Application Program Interfaces (APIs)
  • Data integration
  • Cyber currency use
  • Scalable statistical analysis
  • Data routing and formatting
  • High-speed protocols for long latency transfer
This image shows a prototype interface of the Cloud Analysis Support platform for managing plant genotyping and phenotyping workflows.

Practical Applications

  • The ultimate beneficiaries of the P2IRC Cloud and its support services are the different individuals and teams working on various P2IRC projects. Researchers do not have to worry about managing their data, or the computing necessary to process and analyze their data. This means that researchers and breeders are free to specialize within their own areas and work on achieving their individual project objectives.

  • The P2IRC Cloud supports and enables collaboration within and outside of P2IRC, as well as around the world. This is important to the future of digital agriculture, and a key factor in making quick and revolutionary advances in plant sciences and crop breeding.

  • The ultimate goal of this project is to make the computationally intensive Cloud usable on mobile devices. There are many commercial applications to having a product like this available, and various companies would be interested in having similar software for daily agricultural needs, such as to automate crop bidding.
This video shows the pipeline building software platform that Project 3.1 developed for current use by plant breeders and researchers.


Project 3.1 is also working in collaboration with other P2IRC projects:

Research Team

Project Leads:


Ralph Deters
Dwight Makaroff
Nadeem Jamali
Winfried Grassmann
Derek Eager

Research Associates:
Banani Roy
Steven Xue

PhD Students:
Mainul Hossain
Kawser Wazed Nafi
Waqas Rehman
Mayra Sasmniego
Sara Kassani

MSc Students:
Amit Kumar Mandol
Golam Mostaeen
Rayhan Fedous
Fadi AlMobayed
Habib Sabiu
Olowabi Adekoya
Mohammed Rashid Chowdhury
Ahmad Rahman

Summer Research Assistants:
Carl Hofmeister
Jarrod Pas
Bishal Saha
Parker Neufeld


  1. Banani Roy, Amit. K. Mondal, Chanchal. K. Roy, Kevin A. Schneider, and Kawser Wazed. Towards a reference architecture for cloud-based plant genotyping and phenotyping analysis frameworks. In Proceeding of International Conference on Software Architecture (ICSA), pp. 41–50. April 2017.

  2. Mondal A. K., Roy, B., Roy C. K., Schneider K. A. Recommendation of Features and Architecture of Big Data Processing System Considering the Challenges and Customer Demands of plant Phenotyping. Poster presented at P2IRC Symposium 2016, University of Saskatchewan. (Won the best poster award at student competition)

  3. Ahmed Abdel Moamen, Dezhong Wang and Nadeem Jamali. Supporting Resource Control for Actor Systems in Akka. In Proceedings of the International Conference on Distributed Computing Systems (ICDCS 2017), pp:1--4, June 2017 (Won the Audience Best Poster Award)