Search

We study the solution of integrated planning and scheduling problems that are formulated as bilevel programming problems with mixed-integer nonlinear lower levels using data-driven optimization algorithms. Due to their inherent interdependence, multi-scale nature, and volatile market conditions, decision-making in such multi-level supply chain networks poses challenging task. Traditionally, these problems are addressed sequentially but, this approach often results in production schedules that are not feasible. Motivated by this, we formulate enterprise-wide decision-making problems with linear production planning and mixed-integer nonlinear scheduling level as a bilevel optimization problem. We solve the resulting integrated problem using the DOMINO framework which is a data-driven optimization strategy to handle general constrained bilevel optimization problems. We demonstrate our approach on case studies with varying complexities from crude oil scheduling using a continuous-time formulation to scheduling of continuous manufacturing processes using a traveling salesman problem formulation. The results show that DOMINO can address bilevel programming problems with high-dimensional mixed-integer nonlinear lower levels and can be applied to complex integrated enterprise-wide optimization problems, regardless of the lower-level formulation type.

We develop a machine learning framework that integrates high content/high throughput image analysis and artificial neural networks (ANNs) to model the separation between chemical compounds based on their estrogenic receptor activity. Natural and man-made chemicals have the potential to disrupt the endocrine system by interfering with hormone actions in people and wildlife. Although numerous studies have revealed new knowledge on the mechanism through which these compounds interfere with various hormone receptors, it is still a very challenging task to comprehensively evaluate the endocrine disrupting potential of all existing chemicals and their mixtures by pure in vitro or in vivo approaches. Machine learning offers a unique advantage in the rapid evaluation of chemical toxicity through learning the underlying patterns in the experimental biological activity data. Motivated by this, we train and test ANN classifiers for modeling the activity of estrogen receptor-α agonists and antagonists at the single-cell level by using high throughput/high content microscopy descriptors. Our framework preprocesses the experimental data by cleaning, scaling, and feature engineering where only the middle 50% of the values from each sample with detectable receptor-DNA binding is considered in the dataset. Principal component analysis is also used to minimize the effects of experimental noise in modeling where these projected features are used in classification model building. The results show that our ANN-based nonlinear data-driven framework classifies the benchmark agonist and antagonist chemicals with 98.41% accuracy.

This work addresses the control optimization of time-varying systems without the full discretization of the underlying high-fidelity models and derives optimal control trajectories using surrogate modeling and data-driven optimization. Time-varying systems are ubiquitous in the chemical process industry and their systematic control is essential for ensuring each system to be operated at the desired settings. To this end, we postulate nonlinear continuous-time control action trajectories using time-varying surrogate models and derive the parameters of these functional forms using data-driven optimization. Data-driven optimization allows us to collect data from the high-fidelity model without pursuing any discretization and fine-tune candidate control trajectories based on the retrieved input-output information from the nonlinear system. We test exponential and polynomial surrogate forms for the control trajectories and explore various data-driven optimization strategies (local vs. global and sample-based vs. model-based) to test the consistency of each approach for controlling dynamic systems. The applicability of our approach is demonstrated on a motivating example and a CSTR control case study with favorable results.

A comprehensive evaluation of toxic chemicals and understanding their potential harm to human physiology is vital in mitigating their adverse effects following exposure from environmental emergencies. In this work, we develop data-driven classification models to facilitate rapid decision making in such catastrophic events and predict the estrogenic activity of environmental toxicants as estrogen receptor-α (ERα) agonists or antagonists. By combining high-content analysis, big-data analytics, and machine learning algorithms, we demonstrate that highly accurate classifiers can be constructed for evaluating the estrogenic potential of many chemicals. We follow a rigorous, high throughput microscopy-based high-content analysis pipeline to measure the single cell-level response of benchmark compounds with known in vivo effects on the ERα pathway. The resulting high-dimensional dataset is then pre-processed by fitting a non-central gamma probability distribution function to each feature, compound, and concentration. The characteristic parameters of the distribution, which represent the mean and the shape of the distribution, are used as features for the classification analysis via Random Forest (RF) and Support Vector Machine (SVM) algorithms. The results show that the SVM classifier can predict the estrogenic potential of benchmark chemicals with higher accuracy than the RF algorithm, which misclassifies two antagonist compounds.

Supply chain management is an interconnected problem that requires the coordination of various decisions and elements across long-term (i.e., supply chain structure), medium-term (i.e., production planning), and short-term (i.e., production scheduling) operations. Traditionally, decision-making strategies for such problems follow a sequential approach where longer-term decisions are made first and implemented at lower levels, accordingly. However, there are shared variables across different decision layers of the supply chain that are dictating the feasibility and optimality of the overall supply chain performance. Multi-level programming offers a holistic approach that explicitly accounts for this inherent hierarchy and interconnectivity between supply chain elements, however, requires more rigorous solution strategies as they are strongly NP-hard. In this work, we use the DOMINO framework, a data-driven optimization algorithm initially developed to solve single-leader single-follower bi-level mixed-integer optimization problems, and further develop it to address integrated planning and scheduling formulations with multiple follower lower-level problems, which has not received extensive attention in the open literature. By sampling for the production targets over a pre-specified planning horizon, DOMINO deterministically solves the scheduling problem at each planning period per sample, while accounting for the total cost of planning, inventories, and demand satisfaction. This input-output data is then passed onto a data-driven optimizer to recover a guaranteed feasible, near-optimal solution to the integrated planning and scheduling problem. We show the applicability of the proposed approach for the solution of a two-product planning and scheduling case study.

The National Institute of Environmental Health Sciences (NIEHS) Superfund Research Program (SRP) aims to support university-based multidisciplinary research on human health and environmental issues related to hazardous substances and pollutants. The Texas A&M Superfund Research Program comprehensively evaluates the complexities of hazardous chemical mixtures and their potential adverse health impacts due to exposure through a number of multi-disciplinary projects and cores. One of the essential components of the Texas A&M Superfund Research Center is the Data Science Core, which serves as the basis for translating the data produced by the multi-disciplinary research projects into useful knowledge for the community via data collection, quality control, analysis, and model generation. In this work, we demonstrate the Texas A&M Superfund Research Program computational platform, which houses and integrates large-scale, diverse datasets generated across the Center, provides basic visualization service to facilitate interpretation, monitors data quality, and finally implements a variety of state-of-the-art statistical analysis for model/tool development. The platform is aimed to facilitate effective integration and collaboration across the Center and acts as an enabler for the dissemination of comprehensive ad-hoc tools and models developed to address the environmental and health effects of chemical mixture exposure during environmental emergency-related contamination events.

The ultimate goal of the Texas A&M Superfund program is to develop comprehensive tools and models for addressing exposure to chemical mixtures during environmental emergency-related contamination events. With that goal, we aim to design a framework for optimal grouping of chemical mixtures based on their chemical characteristics and bioactivity properties, and facilitate comparative assessment of their human health impacts through read-across. The optimal clustering of the chemical mixtures guides the selection of sorption material in such a way that the adverse health effects of each group are mitigated. Here, we perform (i) hierarchical clustering of complex substances using chemical and biological data, and (ii) predictive modeling of the sorption activity of broad-acting materials via regression techniques. Dimensionality reduction techniques are also incorporated to further improve the results. We adopt several recent examples of chemical substances of Unknown or Variable composition Complex reaction products and Biological materials (UVCB) as benchmark complex substances, where the grouping of them is optimized by maximizing the Fowlkes-Mallows (FM) index. The effect of clustering method and different visualization techniques are shown to influence the communication of the groupings for read-across.