(2da) Machine Learning Solutions to Complex Problems in Health, Environment, and Materials

My research focuses on exploring the power of deep learning techniques in problems that are difficult to solve using state-of-the-art experimental or theoretical approaches. I am driven by the applicability of my research towards human and animal health and well-being, environmental concerns of this century, the next generation of materials, and sustainable material development. Because of my industry experience, I envision a part of my work to bridge the gap between academic and industrial research and collaboration, which I believe, is of paramount importance when thinking about the immediate welfare of our planet.

My research group will focus on three main areas: (1) Machine Learning (ML) pipelines for molecules, macromolecules, and micrographs. Whether it's a problem of establishing structure-property relationships, finding binding sites on proteins, or the responsible base-pair sequence on a strand of a DNA, figuring out molecular hotspots have been an area of immense importance. When constructed properly, I believe that trained ML models can reveal this information. I work on data representation for molecules requiring little to no feature engineering. Similarly, microscopy is a crucial characterization tool for biologists and materials scientists. For the purposes of ML, micrographs present a more complex problem than other image data because they contain additional artefacts/features, sometimes implicitly relevant to the study. Thus, micrographs are another area where I believe ML approaches will be particularly useful. (2) Extra-meta properties of metamaterials beginning with auxetic materials. I plan to use my experience with experimental auxetic metamaterials to explore their properties other than Poisson's ratio. Can auxeticity yield negative compressibility or thermal expansion, negative thermal conductivity, or unique acoustic manipulation? Does auxeticity imply tensegrity? Having developed commodity auxetics and scalable processing techniques that impart auxeticity, I wish to work towards finding ways to create low-cost metamaterials. (3) ML for industrial chemical formulations. A successful ML model could be one that predicts light transmittance or thermal conductivity, for instance, and maps it to the oligomers in the formulation and the curing parameters used. I am confident that deep neural networks have immense potential in capturing the complex mechanical-chemical properties of any formulation.

My current research involves building machine learning (ML) based pipelines for detecting airborne microbes, onset of diseases, and chemical discovery algorithms to find suitable ligands for virus purification. Previously, I worked in the area of experimental auxetic metamaterial development for my doctoral and first postdoctoral work. This was an area dominated by theoretical work, where we became pioneers in commodity auxetic materials and designed composites inspired from tensegrity structures. My industry experience was in a fast-paced R&D environment, where I managed a team of 5 scientists, working on functional coatings, formulations, and scale-up operations. I led several lab-to-production trials.

Teaching Interests

I thoroughly love and enjoy teaching, advising, and mentoring and don’t see them as just commitment or duty. I feel that I am able to truly understand something when I am able to teach it to someone else. I have taught 13+ classes as a guest lecturer in the area of polymer engineering and machine learning and have served as a Teaching Assistant for six semesters. I had the pleasure of mentoring over 16 scientists and engineers in universities and industry combined. Additionally, I have served as a research advisor for 17 researchers, 14 of whom were under my direct supervision, in the area of machine learning, protective and adhesive coatings, metamaterials, and polymer characterization and processing. I feel great pride and fulfillment in the success of my students, mentees, and advisees. My background has prepared me well to effectively teach courses like introduction to materials, polymer chemistry, organic chemistry, polymer characterization, polymer processing and rheology, structure property relationships in materials, and machine learning for chemical and materials straightaway.

Select Publications

1. P Verma, E Adeogun, ES Greene, S Dridi, U Nakarmi, et al.; Machine-learning classification of heat-stress in organisms using CNNs; ACS Sensors (submitted); 2023.
2. P Verma, DN Ansari, TU Ansari; Deep learning algorithms for extraction of aerosol chemical composition from temporal variations of total PM mass; Environmental Science and Technology (submitted); 2023.
3. E Adeogun, P Verma, D Iyer, S Srivastava, K Nayani; Formation of liquid crystalline coacervates via the complexation of chromonic mesogens and synthetic polymers; PNAS (submitted); 2023.
4. X Fang, H Sun, C Wu, P Verma, et al.; Ag nanoparticle-thiolated chitosan composite coating reinforced by Ag–S covalent bonds with excellent electromagnetic interference shielding and Joule heating performances; ACS Applied Materials & Interfaces (IF = 10.4); 2023.
5. H Sun, X Fang, Z Fang, P Verma, et al.; An ultra-sensitive and stretchable strain sensor based on micro-crack structure for motion monitoring; Micro Nano (Nature) (IF = 8.1); 8 (111); 2022.
6. TU Ansari, DN Ansari, P Verma*; Statistical and machine-learning approaches towards retrieving aerosol chemical composition from temporal variations of total PM mass concentrations: Theoretical approach and insights.; Earth and Space Science Open Archive; 2022.
7. P Verma, C Smith, AC Griffin, ML Shofner; Towards textile metamaterials: A pathway to auxeticity and tensegrity in a needle-punched nonwoven stiff felt; Materials Advances (RSC) (IF = 5.0); 2022.
8. P Verma, C Smith, AC Griffin, ML Shofner; Wool nonwovens as candidates for commodity auxetic materials; Engineering Research Express; 2 (4); 2021.
9. P Verma, C He, AC Griffin; Implications for auxetic response in liquid crystalline polymers; Physica Status Solidi B; 2000261; 2020; (appeared in Wiley's 'Hot Topics: Liquid Crystals')
10. N Jappar, P Verma, J Holmes; Development of functional films in roll-to-roll manufacturing; RadTech; 2018; (conference paper)