Project Description

Plant pests and diseases account for approximately 40% of the attainable yield loss to global rice production.Increasing trend of yield loss has potential to threaten sustenance of small-scale farmers in predominantly agrarian economies such as India. The objective of the proposed project is to develop a prototype of an intelligent early warning system for prominent diseases affecting the rice cropping system. The system will comprise of three key elements: a) web-enabled, low-cost, in-field sensors for real-time collection of weather/farm/plant health data and its storage on cloud platforms, b) sophisticated AI/ML models to recognize crop abnormalities in early stages, c) user-friendly mobile application with regional language support to deliver advance alerts to farmers on a range of plant diseases, pest infestations and micro climatic stress factors. Current approaches rely on computer vision based analytic techniques that uses visual cues and emphasize “post-facto” detection of diseases, thereby, limiting famer’s ability to timely control crop damage. The project seeks to develop robust prediction models that process both sensor-data and micro-climatic parameters and assess their forecast accuracy through field validation in order to significantly improve lead times for disease control and management in rice cropping system.

Start Date

April 1, 2020

Postdoc Qualifications 

Master's degree in Agricultural/Electrical/Telecommunications/related engineering disciplines with a minimum of 3-years of experience beyond graduation
Demonstrable communication and writing skills
Ability to work in team
Prior grant writing experience is desirable

Co-advisors 

Dharmendra Saraswat
saraswat@purdue.edu
Agricultural and Biological Engineering
https://dad.saraswat.rcac.purdue.edu/

Shreyas Sen
shreyas@purdue.edu
Electrical and Computer Engineering
https://engineering.purdue.edu/~shreyas/SparcLab/

National Rice Research Institute, Cuttack, India 

References 

Baibhab Chatterjee, Ningyuan Cao, Arijit Raychowdhury, and Shreyas Sen, 2019. "Context-Aware Intelligence in Resource-Constrained IoT Nodes: Opportunities and Challenges," in IEEE Design and Test of Computers (IEEE D&T).

Etienne, A. and D. Saraswat,2019. "Machine learning approaches to automate weed detection by UAV based sensors," Proc. SPIE 11008, Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IV, 110080R. 

Baibhab Chatterjee, Debayan Das, Shovan Maity and Shreyas Sen. 2018. "RF-PUF: Enhancing IoT Security through Authentication of Wireless Nodes using In-situ Machine Learning," in IEEE Internet of Things Journal (JIoT).

Ningyuan Cao, Shreyas Sen, Arijit Raychowdhury. 2018. "Smart sensing for HVAC control: Collaborative intelligence in optical and IR cameras," in IEEE Transactions on Industrial Electronics.
Rahman, M., B. Blackwell, N., Banerjee, and D. Saraswat. 2015. Smartphone based Hierarchical Crowdsourcing for Weed Identification. Computers and Electronics in Agriculture 113: 14-23.