About

Warren Jasper is a professor in the Textiles Complex at NC State University, with a background that includes designing data acquisition and control systems for textile processes. His research interests encompass measurement and control of dyeing, plasma textiles for nanoparticle filtration, and writing Linux device drivers. Jasper has been involved in real-time monitoring and control of batch dyeing processes, filtration technologies such as electret filters and plasma textiles, and real-time defect detection in woven fabrics. His work also extends to the measurement and characterization of yarn using wavelets. Jasper's educational background includes a BS and MS from the Massachusetts Institute of Technology and a PhD from Stanford University. He has received several awards, including the Gertrude M. Cox Award for Innovative Excellence in Teaching and Learning with Technology, a Fulbright Specialist award, and recognition as an Outstanding Faculty in Extension and Engagement. His professional focus combines engineering, textile science, and sustainability, with ongoing projects aimed at enhancing wildland firefighter protection, mitigating aerosol transmission of viruses via plasma textile filters, and implementing Lean Six Sigma methodologies to improve dyeing processes for sustainability and cost reduction.

Research topics

• Composite material
• Artificial Intelligence
• Materials science
• Computer Science
• Engineering
• Mathematics
• Geometry
• Manufacturing engineering
• Mechanical engineering
• Process engineering
• Chemical engineering

Selected publications

• Ferrofluid bend channel flows for multi-parameter tunable heat transfer enhancement Part 2 Deep Learning and Neural Network Modeling

  ArXiv.org · 2026-02-09

  articleOpen accessSenior author

  This work is the second in a series focused on ferrofluid bend channel flows. Here, ferrofluid flows in bend channels are modeled using machine learning methods, based on data generated from the CFD simulation discussed in the first work in this series. Predicting convective heat transfer in ferrofluid flows influenced by magnetic fields is key to advancing thermal management in microscale and energy-intensive systems.

  PublisherOA PDF

• Carbon dioxide point-source and direct air capture using biocatalytic textiles

  Carbon Capture Science & Technology · 2026-03-14

  articleOpen access

  • Carbonic anhydrase reliably enhances carbon capture under eco-friendly conditions • Textile contactors promote liquid wicking for efficient CO 2 reactive absorption • Bifunctional reactive dyes offer a scalable enzyme immobilization approach • Enzyme catalysis shows potential to enhance ex situ mineralization • Biocatalytic textiles offer a diverse and practical platform for CO 2 mitigation Biocatalytic textiles were developed and tested as high-efficiency gas-liquid contactors for reactive CO 2 absorption using eco-friendly solvents catalyzed by carbonic anhydrase. The testing in lab to bench-scale systems with various configurations showed that biocatalytic textiles are durable and compatible with multiple different alkaline CO 2 absorption solvents across wide working concentrations, including secondary amines, carbonates, amino acids, and abundant natural water sources like pH-adjusted seawater and spring water. Biocatalytic textile contactors proved to be remarkably robust across diverse conditions, delivering similar percent CO 2 capture regardless of inlet CO 2 concentrations. By controlling gas and liquid flows, packing height and mode of enzyme delivery, single-pass CO 2 absorption efficiencies up to 95% were achieved at lab scale. Biocatalytic textiles were able to withstand repeated washing and drying, immersion and shaking in heated solvents, ambient dry storage for many months, and continuous solvent flow testing for hundreds of hours without performance reduction. Integrated bench unit testing with aqueous MDEA solvent and biocatalytic textile packing modules achieved a CO 2 adsorption rate increase of over 200% at low 1.8 L/G when compared to traditional steel structured packing. A straightforward enzyme crosslinking technology based on fiber reactive dyes developed in the course of this work makes fabrication and scale up possible using established textile manufacturing infrastructure, and a solvent composition based on seawater and wood ash extract offers potential for ex-situ mineralization of CO 2 to permanent solid carbonates for utilization or storage.

  PublisherDOI

• Ferrofluid bend channel flows for multi-parameter tunable heat transfer enhancement Part 2 Deep Learning and Neural Network Modeling

  Open MIND · 2026-02-09

  preprintSenior author

  This work is the second in a series focused on ferrofluid bend channel flows. Here, ferrofluid flows in bend channels are modeled using machine learning methods, based on data generated from the CFD simulation discussed in the first work in this series. Predicting convective heat transfer in ferrofluid flows influenced by magnetic fields is key to advancing thermal management in microscale and energy-intensive systems.

  DOI

• Carbon dioxide point-source and direct air capture using biocatalytic textiles

  SSRN Electronic Journal · 2026-01-01

  preprintOpen access
  PublisherDOI

• Ferrofluid bend channel flows for multi-parameter tunable heat transfer enhancement Part 1 Numerical Modeling & Characterization

  Open MIND · 2026-02-09

  preprintSenior author

  This study investigates ferrohydrodynamic heat transfer enhancement in a two-dimensional 90 degree bend channel through systematic parametric analysis of externally applied non-uniform magnetic fields, using Numerical CFD simulations.

  DOI

• Enhancing cotton yield prediction with robust deep neural network-based framework

  European Journal of Agronomy · 2025-07-08 · 3 citations

  articleOpen access

  Accurate prediction of cotton yield is essential for optimizing agricultural resource allocation, mitigating risks, and informing decision-making. This study introduces a deep learning framework that combines advanced feature engineering with a Deep Neural Network (DNN) model to forecast cotton production. The model incorporates meteorological variables such as precipitation, snowfall, temperature extremes, and derived features like Growing Degree Days (GDD), extreme weather indices, and seasonal precipitation metrics. To address missing data, time-series interpolation is employed, and features are engineered to capture key growth-stage influences and extreme climatic events. The DNN with noise injection model achieved an impressive R 2 of 97.9% and a Root Mean Square Error (RMSE) of 25.3 lb/acre, significantly outperforming traditional machine learning models. This framework effectively captures the non-linear relationships between climate and crop yield, offering valuable insights for agricultural planning. Using North Carolina as a case study, the model predicts cotton yield at the county level, shedding light on regional yield variations. By incorporating diverse weather data, this study provides actionable insights for optimizing cotton production and resource allocation in the supply chain. The framework is adaptable and can serve as a benchmark for yield prediction in other crops and regions, driving advancements in precision agriculture. • Developed a deep neural network framework to predict cotton yield. • Integrated climatic features like GDD and extreme weather indices. • Integrated advanced feature engineering tailored to North Carolina’s climate. • Achieved R 2 of 97.9% with ANN and noise injection for robust prediction. • Provided insights to optimize agricultural practices and resource use.

  PublisherDOI

• A review of the evolution and concepts of deep learning and AI in the textile industry

  Textile Research Journal · 2025-01-16 · 13 citations

  reviewSenior author

  Machine learning (ML) and deep learning (DL) are transforming the textile industry by integrating advanced technologies into various processes. Textiles, once seen as passive materials, are now essential components of complex systems due to automation and innovative materials. This review focuses on articles that utilized AI, ML, or DL in textile research and industry. The review presents bibliometric analysis of AI methods in textiles. Later, the review is structured into sections that examine the effect of ML and DL across the textile sector. We outline key ML and DL methods applied in textiles, discussing their main uses and potential applications. This overview aims to clarify the working principles behind these methods, which are explored in greater detail. The methods analyzed range from basic linear regression to ensemble techniques such as XGBoost. DL techniques include convolutional neural networks for image analysis and long short-term memory networks for time-series analysis. In addition, a bibliometric review identifies trends and gaps in the literature, highlighting areas for future research. We also provide a detailed examination of how these methods are implemented in textiles.

  PublisherDOI

• Feasibility Study of a Hybrid Solid Liquid Vibration Energy Harvester: Numerical Simulation & Analysis

  arXiv (Cornell University) · 2025-01-02

  preprintOpen accessSenior author

  In this paper, we have introduced and studied the feasibility of a hybrid solid liquid vibration energy harvester. The energy harvester consists of a ferrofluid partially filled in a tank and a piezoelectric beam fixed at one of the tank walls. The tank is assumed to be placed in a nonuniform magnetic field created by placing two powerful magnets symmetrically external to the tank walls. This magnetic field was then implemented by a Magnetic field function modeling the magnetic field produced by the two magnets. We used piezoelectric beam configurations and oscillation loads to study and characterize this 2D multiscale, multiphysics, and multiphase fluid structure interaction. The tank is subjected to an external oscillatory motion, which sloshes the ferrofluid and oscillates the beam utilizing two modes, one due to the beams inertia and the second due to the impact of the ferrofluid on the beam. The parameters varied in piezo materials, ferrofluid fill height, piezoelectric beam length, and oscillation frequency. The natural frequency modes for the piezoelectric beam are very important since the beam harvests the highest power in those modes. We have observed that when the fluid motion vibrates the beam, in some instances, the voltage output from piezoelectric material peaks to a high value, which is indicative of material nearing resonance frequencies at the fluid loading realized in those instances. However, in other cases, the voltage output varies with the loading, and hence, the response of the piezoelectric beam is broadband, very similar to the sloshing, which is inherently broadband.

  PublisherOA PDFDOI

• A Controlled Study on Machine Learning Applications to Predict Dry Fabric Color from Wet Samples: Influences of Dye Concentration and Squeeze Pressure

  Fibers · 2025-04-15 · 3 citations

  articleOpen access1st authorCorresponding

  Most dyeing occurs when a fabric is in a wet state, while color matching is performed when the fabric is in a dry state. As water is a colorless liquid, it has been difficult to analytically map these two states using existing color theories. Machine learning models provide a heuristic approach to this class of problems. Linear regression, random forest, eXtreme Gradient Boosting (XGBoost), and multiple neural network models were constructed and compared to predict the color of dry cotton fabric from its wet state. Different models were developed based on squeeze pressure (water pickup), with inputs to the models consisting of the L*a*b* (L*: lightness; a*: red–green axis; b*: blue–yellow axis) coordinates in the wet state and the outputs of the models consisting of the predicted L*a*b* coordinates in the dry state. The neural network model performed the best by correctly predicting the final shade to under a 1.0 color difference unit using the International Commission on Illumination (CIE) 2000 color difference formula (CIEDE2000) color difference equation about 63.9% of the time. While slightly less accurate, XGBoost and other tree-based models could be trained in a fraction of the time.

  PublisherOA PDFDOI

• A review of deep learning and artificial intelligence in dyeing, printing and finishing

  Textile Research Journal · 2024 · 24 citations

  Senior authorCorresponding
  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  This review focuses on the transformative applications of deep learning and artificial intelligence in textile dyeing, printing, and finishing. In textile dyeing, the topics span color prediction, color-based classification, dyeing recipe prediction, dyeing pattern recognition, and the nuanced domain of color fabric defect detection. In textile printing, applications of artificial intelligence and machine learning center around pattern detection in printed fabrics, the generation of novel patterns, and the critical task of detecting defects in printed textiles. In textile finishing the prediction of fabric thermosetting parameters is discussed. Artificial neural networks, diverse convolutional neural network variations like AlexNet, traditional machine learning approaches including support vector regression, principal component analysis, XGBoost, and generative artificial intelligence such as generative adversarial networks, as well as genetic algorithms all find application in this multifaceted exploration. At its core, the interest to use these methodologies is because of the need to minimize repetitive and time-consuming manual tasks, curtail prototyping costs, and promote process automation. The review unravels a plethora of innovative architectures and frameworks, each tailored to address specific challenges. However, a persistent hurdle looms – the scarcity of data, which remains a significant impediment. While unveiling a collection of research findings, the review also spotlights the inherent challenges in implementing artificial intelligence solutions in the textile dyeing and printing domain.

  PublisherDOI

Frequent coauthors

• A. V. Kuznetsov

  North Carolina State University

  9 shared

• Melih Günay

  Akdeniz University

  8 shared

• Minyoung Suh

  North Carolina State University

  7 shared

• Srinivasan C. Rasipuram

  University of Louisville

  7 shared

• Juan P. Hinestroza

  Cornell University

  7 shared

• D. G. Hinks

  North Carolina State University

  6 shared

• Jooyoun Kim

  Seoul National University

  5 shared

• Roger L. Barker

  North Carolina State University

  4 shared

Labs

• Research Lab at Wilson College of TextilesPI

Education

• B.S., Not Provided

  University Name Not Provided

• M.S., Not Provided

  University Name Not Provided

• Ph.D., Not Provided

  University Name Not Provided

Awards & honors

• Gertrude M. Cox Award for Innovative Excellence in Teaching…
• Fulbright Specialist award 2014 & 2019
• Jefferson Science Fellow, National Academies of Science, Eng…
• Academy of Outstanding Faculty in Extension and Engagement 2…
• Outstanding Engagement Award 2019