Skip to main content

Agricultural & Biological Engineering

Students may apply to one or more of the below projects, indicating this in their statement of interest, or they may apply for "ABE: General," indicating in their statement of interest their skills and background and some faculty with whom they would be interested in working.  ABE Faculty List

Title Name Email Project Name Project Description Requirements
Assoc. Prof. Shweta Singh Machine Learning for Sustainability of Emerging Technologies Sustainability of emerging technologies is difficult to model due to lack of established methods and predictive models available. In this project, the aim is to overcome this challenge by using novel machine learning methods integrated with network modeling along with using the available heterogeneous data. Specific emerging technologies of interest are: bio-based manufacturing, automation in industries, renewable energy and waste-to-value added. The student will contribute to identification and development of appropriate machine learning algorithms for predictive modeling and connect with mechanism based models. The technology selection will be decided as per the student interest since the emphasis is on method identification and testing. Chemical Engineering, Bio-processing degrees. Numerical Methods knowledge, Programming experience in Python, Modeling Knowledge for process modeling (either by coding or use of software such as ASPEN or ChemCad), Desire to learn new machine learning algorithms and applications in engineering systems.
Assoc. Prof. Dharmendra Saraswat Deep Learning for Plant Classification and Identification Deep learning has become an important tool for image analysis in the field of agriculture. However, low quality and sparse availability of training data combined with field variability does not allow achieving high accuracy for plant classification and detection. A major goal of this project is to evaluate newer approaches in machine learning and update an existing system for acquiring enhanced quality of training data to assess the impact of both these interventions on the classification and detection outputs for plants of interest. The student will be involved in identifying appropriate machine learning algorithm and updating a training data acquisition system to support the goal of the project. An exposure to Purdue’s newest Community Cluster will be provided.  Experience with open source programming language (e.g. Python) and an exposure to machine learning is preferred. Desire to learn new skills independently and work in a team environment is needed.
Assoc. Prof. Dharmendra Saraswat Analytics for Internet-of-Things (IoT) Sensors It is reported that currently almost 33 percent of the global population is affected by water scarcity and by 2030, this figure is expected to climb up to almost 50 percent. Around 60 percent of the water used for irrigation is wasted, either due to
evapotranspiration, land runoff, or simply inefficient, primitive irrigation application methods. This realization has brought attention to smart irrigation – powered by the internet of things (IoTs) – that can be a better way of managing water stress on a global basis. The selected student will design a cloud-based system for acquiring, storing, analyzing, and visualizing data from field-based sensors, perform calculations/combine new data, plot functions for visual understanding and perform sophisticated analysis by combining data from several field nodes.
Programing skills in any language with some experience in statistics is desired.
Asst. Prof. Somali Chaterji Genomics Data Science Developing machine learning algorithms for finding patterns in the genome, using both clustering and supervised learning for applications in synthetic biology and precision medicine. We have also used natural language processing for understanding the "language of the genome" and correcting errors in genome sequencing, 2 recent Nature papers on this topic. For more, check out: https:// Coding: Python/C
Desired course work, not required coursework: Machine learning, compilers, OS, natural language processing
Some knowledge of: genomics, logic gates/integrated circuits
Asst. Prof. Somali Chaterji In-sensor Analytics and Edge Computing for Energy-aware Approximate Computing My lab, "Cells and Machines Innovatory" develops algorithms and platforms for both Internet of Things (IoT)-related applications (e.g., digital agriculture) and precision-health related applications (e.g., logic gate for synthetic biology). Our lab develops machine learning (ML) algorithms, both at scale for distributed deployments and in lightweight (approximate) formats for running on Raspberry Pi-class devices. Tools and techniques for this project: how do you run deep learning algorithms on embedded boards with a bounded loss of accuracy using approximation techniques.
Experience with TensorFlow, Python programming recommended or some other ML-friendly programming language. The student will work with a grad student mentor and have access to our group's resources and high-end servers and AWS for cloud computing.
Check: for projects going on in our laboratory.
Coding: Python/C/Java; some experience with using ML packages, experience with CUDA/GPUs will be great.


Return to main content

Purdue University, 1201 West State Street, West Lafayette, IN 47907, (765) 494-9095

© 2019 Purdue University | An equal access/equal opportunity university | Copyright Complaints | Maintained by Office of Corporate and Global Partnerships

Trouble with this page? Disability-related accessibility issue? Please contact Office of Corporate and Global Partnerships at