The EnBiSys Lab is a highly collaborative, multidisciplinary research group housed in the Department of Electrical and Computer Engineering and the N.C. Plant Sciences Initiative at NC State University. We collaborate with researchers in many diverse fields, such as plant and microbial biology, forestry, chemical engineering and others. We develop techniques for understanding and influencing biological systems by using theories and methodologies from traditional electrical engineering areas, such as:

• Machine Learning
• Digital and Biological Signal and Data Processing
• Control Theory
• Computer Vision and Image Processing
• Nonlinear Systems Analysis

Current Research

Improving Crop Productivity and Value Through Heterogeneous Data Integration, Analytics and Decision Support Platforms

Project Description: Current research builds on the Sweet-APPS Project originally funded by the Game-Changing Research Incentive Programs for the Plant Science Initiative (GRIP4PSI) here at NC State in 2020. The initial project aimed to develop new technologies to minimize waste and maximize value for North Carolina sweetpotato producers, growers, and packers through innovations in high-throughput imaging, optical sensing and diagnostics, and integrated data analytics. In collaboration with other PSI faculty, the EnBiSys Lab helped develop an integrated data analytics and decision support platform that helps optimize management strategies to resolve inconsistencies in sweetpotato storage root quality, thereby improving outcomes and increasing produce value for North Carolina growers and packers. Current research focuses on expanding dashboard capabilities and functionality as well as expanding the data acquisition tools and sensors to other crops.

Contributors: Azizah Conerly, Mariella Carbajal Carrasco, and Jerome Maleski

InRoot: Molecular Mechanisms and Dynamics of Plant-Microbe Interactions at the Root-Soil Interface

Project Description: The project is one of three projects funded by the Novo Nordisk Foundation under the Collaborative Crop Resilience Program. This is an international collaboration between NC State, The University of Copenhagen, Aarhus University and the Technical University of Denmark. The goal of these projects is to take a systems-level view of plants and their interactions with microbes in the soil, roots and foliage to improve plant health and productivity. This is particularly important in the face of climate change and emerging pathogens and pests where leveraging microbes to help plants avoid stresses while acquiring nutrients to reduce fertilizer, pesticide and irrigation become important. Our lab is developing multiscale models across biological scales that can predict the contribution of key plant and microbe interactions, which mediate intra- and inter-organismic resource allocation and promote plant fitness and resilience.

Contributor: Max Gordon 

REFRAME: A Digital Framework for Optimizing Biomass Utilization and Bioenergy Systems

Project description: This project aims to develop an integrated framework to optimize the use of organic waste and agricultural residues for bioenergy and bioproducts. By linking feedstock availability with logistics, processing, and sustainability outcomes, it enables data-driven decisions for resource allocation and supply chain design. The EnBiSys Lab is leading the development of the digital backbone, focused on integrating and orchestrating heterogeneous data and models across the biomass value chain. This modular, AI-enabled platform leverages AI/ML-based surrogate models to accelerate analysis and enable rapid exploration of diverse scenarios. The system will also incorporate LLM-based tools to provide intuitive interaction, allowing users to ask flexible questions and explore pathways to convert underutilized biomass into biofuels and other bioproducts.

REFRAME is funded by Schmidt Sciences through the Virtual Institute on Feedstocks of the Future (VIFF), and conducted in collaboration with Idaho National Laboratory, the University of Illinois Urbana-Champaign, ICF International, and McCarl & Associates

Contributor: Mariella Carbajal

BeanPACK: Soybean Grower Decision Support Tool

Project Description: To ensure continued on-farm profitability, growers must have access to dynamic tools that allow them to use data science to advance the economic and environmental sustainability of their operations. The EnBiSys Lab is leading the development of a web-based grower decision support dashboard that will be easily navigable by growers across North Carolina. Using SAS Viya, a cloud-based Al tool for analytics and data management, and machine learning, this dashboard is being created using field data generated since 2019 that comprises 50,000 data points on the relationship of production practices with yield and quality across the state. The goal of this project is to ultimately develop web-accessible models that provide data-driven solutions about soybean production practices directly to growers.

Contributor: Somshubhra Roy

Automating the Assessment of Severity of Southern Leaf Blight (SLB) in Corn using Machine Learning

Project Description: Biotic stresses, such as SLB, may visually appear on a crop and allow for the quantification of infected regions. The quantification of such stress, which includes the scoring of plants based on the proportion of infected areas to healthy tissue, is often performed manually based on visual symptoms, and is thus, time intensive, causing crop loss due to a delay between disease identification and management efforts. The EnBiSys Lab is taking two parallel approaches to automate the detection and grading of SLB in corn, which allows for disease detection at the plant and the plot levels. The first approach is focused on using computer vision and machine learning to perform quantification and prediction of biotic stress in near isogenic lines of corn plants in an effort to develop a consistent and objective method to score leaves efficiently. The second approach focuses on using hyperspectral images of whole fields of corn to detect and grade areas affected by SLB.

Contributors: Grace Vincent and Chanae Ottley

Improving Crop Yield Prediction with Transfer Learning and Adaptive Data Augmentation

Project Description: Accurate crop yield prediction is challenging due to environmental variability and data limitations, particularly as global climate change alters regional growing conditions. This research investigates how deep learning models can be used to improve crop yield prediction when data is limited and environmental conditions change over time. To address this challenge, the EnBiSys Lab is applying pre-trained deep learning models with transfer learning to enhance the model’s ability to capture complex environmental variables. Specifically, the lab focuses on using feature extraction capabilities from pre-trained models and fine-tuning them on publicly available crop-specific agricultural datasets to improve prediction accuracy. The model integrates multi-source agricultural data to enhance predictive performance. The dataset includes daily weather data, soil properties, environmental data, and SNP-based breeding information. However, climate-driven shifts in environmental conditions can cause data distributions to change over time, leading to model performance degradation. To minimize this issue, the lab will incorporate USDA-NASS database data, which provides regional agricultural statistics to compensate for incomplete information. Currently, the study focuses on soybean and canola, two economically significant crops with distinct environmental and genetic characteristics. By validating this approach to these crops, the lab aims to develop a generalized deep-learning framework that can extend to other major crops to improve yield prediction accuracy across diverse agricultural environments.

Contributor: Peiran Wang

Systematically Exploring the Regulation of Gene Expression in Maize

Project Description: In collaboration with the Nelms Lab at the University of Georgia, high throughput screening (HTS) techniques are used to ectopically express transcription factors (TF) in Maize protoplasts. RNA-seq data is collected to measure gene expression in cells and to gain insights into the mechanisms of gene regulation. The EnBiSys Lab is leading the development of an improved statistical framework to analyze complex gene expression data to overcome technical and biological variations that are typical of HTS protocols. The lab is also taking the lead in deconvolving genetic regulatory networks from the RNA-seq data to uncover cellular programming and produce new understandings of the function of specific TFs. These experiments will offer a greater understanding of TF function and aid in engineering plant systems. This project aims to accelerate plant breeding to create the ‘crops of tomorrow,’ which is increasingly important in a changing climate.

Contributors: Teague McCracken and Max Gordon

Natural Variation and Systems-Level Properties of Gene Regulation in Drosophila

Project Description: Regulation of gene expression is of paramount importance in animal development, with improper regulation resulting in developmental defects and disease states. In developing tissues, several genes coding for transcription factors regulate each other in a complex web of interactions known as the genetic regulatory network (GRN). The structure of a GRN is thought to be responsible for the robust and precise cell fate decisions required in a developing tissue. The long-term goal is to deduce the genetic regulatory interactions necessary for robust patterns of gene expression. The overall objective in this proposal is to use the natural variation that occurs in a panel of wild-caught fly lines to characterize the GRN responsible for precise anterior-posterior (AP) patterning in the early Drosophila embryo. This will test the central hypothesis that gene expression patterns in the AP patterning system have undiscovered regulation that can be found by examining the correlation between gene expression and natural variation in the genomes of these flies. This research is performed in collaboration with the Reeves Lab at Texas A&M Univeristy.

Contributor: Sharva Hiremath

High-Throughput Multi-Scale Sensing for Tomato Disease Phenotyping

Project Description: Tomatoes are among the most produced and consumed vegetable crops globally, yet a wide range of destructive diseases threatens their production and fruit quality. Automated image-based systems powered by deep learning offer consistent, high-throughput disease assessments that are a scalable alternative to manual scouting. This collaborative project aims to develop an autonomous tomato disease scouting system using Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs). The EnBiSys Lab contributes by generating and leveraging high-quality 2D and 3D image representations of tomato plants to support model development and extract enriched information from controlled sensing modalities not typically available in production environments. These insights are used to improve disease assessments and distill knowledge into practical, deployable tools. The goal is to reduce bottlenecks in deep learning deployability by generating robust multimodal data to close the lab-to-field domain gap and develop models for edge hardware. This research is funded by USDA-NIFA and is conducted in collaboration with Lirong Xiang (Cornell University).

Understanding Cross Species Generalization in a Plant DNA LLM

Large language models (LLMs) trained on cross-species genomic sequences now predict gene regulation with unprecedented accuracy, but their internal representations remain opaque, hindering trust. Our study aimed to uncover how state-of-the-art plant-DNA LLMs (PlantCaudecus and NTV3) encode species identity, a key determinant of their ability to generalize across taxa and thus to serve as foundational models for plant breeding. Our preliminary findings illuminate the pathway to responsible AI in agriculture: by revealing how models encode biological context, we can assess bias, validate cross-species generalization, and ensure transparency in decision-support tools. If validated, such findings become a bridge between genomic data and actionable breeding strategies, enhancing efficiency, reducing resource waste, and sustaining competitive advantage for producers.

Contributor: Jerry Yu