College of Sciences
Permanent URI for this communityhttps://hdl.handle.net/20.500.12588/256
Browse
Browsing College of Sciences by Department "Biomedical Engineering and Chemical Engineering"
Now showing 1 - 4 of 4
- Results Per Page
- Sort Options
Item A Review on Interpretable and Explainable Artificial Intelligence in Hydroclimatic Applications(2022-04-11) Başağaoğlu, Hakan; Chakraborty, Debaditya; Lago, Cesar Do; Gutierrez, Lilianna; Şahinli, Mehmet Arif; Giacomoni, Marcio; Furl, Chad; Mirchi, Ali; Moriasi, Daniel N.; Şengör, Sema SevinçThis review focuses on the use of Interpretable Artificial Intelligence (IAI) and eXplainable Artificial Intelligence (XAI) models for data imputations and numerical or categorical hydroclimatic predictions from nonlinearly combined multidimensional predictors. The AI models considered in this paper involve Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Extremely Randomized Trees, and Random Forest. These AI models can transform into XAI models when they are coupled with the explanatory methods such as the Shapley additive explanations and local interpretable model-agnostic explanations. The review highlights that the IAI models are capable of unveiling the rationale behind the predictions while XAI models are capable of discovering new knowledge and justifying AI-based results, which are critical for enhanced accountability of AI-driven predictions. The review also elaborates the importance of domain knowledge and interventional IAI modeling, potential advantages and disadvantages of hybrid IAI and non-IAI predictive modeling, unequivocal importance of balanced data in categorical decisions, and the choice and performance of IAI versus physics-based modeling. The review concludes with a proposed XAI framework to enhance the interpretability and explainability of AI models for hydroclimatic applications.Item Forces Governing the Transport of Pathogenic and Nonpathogenic Escherichia coli in Nitrogen and Magnesium Doped Biochar Amended Sand Columns(2023-02-07) Quinn, Katherine; Mood, Sohrab Haghighi; Cervantes, Elizabeth; Perez, Manuel Garcia; Abu-Lail, Nehal I.Background: Access to safe drinking water remains a global issue with fecal indicator bacteria being major pollutants. Biochars offer low-cost adsorbents for bacterial pathogens. A fundamental understanding of how biochars interact with bacterial pathogens is essential to designing effective biofilters. Methods: Water-saturated sand columns amended with Magnesium and Nitrogen-doped biochars produced by pyrolysis at 400, 500, 600, and 700 ◦C were used to Quantify the transport of pathogenic Escherichia coli O157:H7 and nonpathogenic E. coli k12 strains in porous media. Measured data were modeled using DLVO theory of colloidal stability. were explored. Results: (1) Biochar is hydrophobic while sand and bacteria are hydrophilic; (2) all Gibbs free energy values quantified between E. coli O157:H7 and biochar were negative except for biochar produced at 700 ◦C; (3) all types of forces investigated (van der Waals, electrostatic, and acid-base interactions) played a role in governing the interactions between bacteria and biochar. Conclusions: (1) Adding doped biochar to sand at a 2% weight ratio enhanced the retention of bacterial cells in the sand/biochar columns; (2) bacterial transport is strain-dependent and mediated by various types of forces resulting from interactions between the various functional groups displayed on bacteria and biochar/sand. Our findings emphasize the importance of monitoring biochar’s functionality to eliminate bacterial pollutants from contaminated water.Item Mesoscale Simulations of Polymer Solution Self-Assembly: Selection of Model Parameters within an Implicit Solvent Approximation(2021-03-19) Park, Juhae; Ramírez-Hernández, Abelardo; Thapar, Vikram; Hur, Su-MiCoarse-grained modeling is an outcome of scientific endeavors to address the broad spectrum of time and length scales encountered in polymer systems. However, providing a faithful structural and dynamic characterization/description is challenging for several reasons, particularly in the selection of appropriate model parameters. By using a hybrid particle- and field-based approach with a generalized energy functional expressed in terms of density fields, we explore model parameter spaces over a broad range and map the relation between parameter values with experimentally measurable quantities, such as single-chain scaling exponent, chain density, and interfacial and surface tension. The obtained parameter map allows us to successfully reproduce experimentally observed polymer solution assembly over a wide range of concentrations and solvent qualities. The approach is further applied to simulate structure and shape evolution in emulsified block copolymer droplets where concentration and domain shape change continuously during the process.Item The Preparation and Characterization of Co–Ni Nanoparticles and the Testing of a Heterogenized Co–Ni/Alumina Catalyst for CO Hydrogenation(2019-12-21) López-Tinoco, Julián; Mendoza-Cruz, Rubén; Bazán-Díaz, Lourdes; Karuturi, Sai Charan; Martinelli, Michela; Cronauer, Donald C.; Kropf, A. Jeremy; Marshall, Christopher L.; Jacobs, GarySamples of well-controlled nanoparticles consisting of alloys of cobalt and nickel of different atomic ratios were synthesized using wet chemical methods with oleylamine as the solvent and the reducing agent. These materials were characterized by a variety of techniques, including high-angle annular dark-field scanning transmission electron microscopy (HAADF-STEM), X-ray energy dispersive spectroscopy (EDS), and X-ray diffraction (XRD). Small amounts of heterogenized catalysts were prepared using alumina as the support. However, the potential for use of Co–Ni catalysts in CO hydrogenation was explored using a larger amount of Co–Ni/alumina catalyst prepared from standard aqueous impregnation methods and tested in a continuously stirred tank reactor (CSTR) for Fischer–Tropsch synthesis (FTS). Results are compared to a reference catalyst containing only cobalt. The heterogenized catalysts were characterized using synchrotron methods, including temperature programmed reduction with extended X-ray absorption fine structure spectroscopy and X-ray absorption near edge spectroscopy (TPR-EXAFS/XANES). The characterization results support intimate contact between Co and Ni, strongly suggesting alloy formation. In FTS testing, drawbacks of Ni addition included decreased CO conversion on a per gram catalyst basis, although Ni did not significantly impact the turnover number of cobalt, and produced slightly higher light gas selectivity. Benefits of Ni addition included an inverted induction period relative to undoped Co/Al2O3, where CO conversion increased with time on-stream in the initial period, and the stabilization of cobalt nanoparticles at a lower weight % of Co.