An official website of the United States government
Abstract The state of the art for optimal water reservoir operations is rapidly evolving, driven by emerging societal challenges. Changing values for balancing environmental resources, multisectoral human system pressures, and more frequent climate extremes are increasing the complexity of operational decision making. Today, reservoir operations benefit from technological advances, including improved monitoring and forecasting systems as well as increasing computational power. Past research in this area has largely focused on improving solution algorithms within the limits of the available computational power, using simplified problem formulations that can misrepresent important systemic complexities and intersectoral interactions. In this study, we review the recent literature focusing on how the operation design problem is formulated, rather than solved, to address existing challenges and take advantage of new opportunities. This paper contributes a comprehensive classification of over 300 studies published over the last years into distinctive categories depending on the adopted problem formulation, which clarifies consolidated methodological approaches and emerging trends. Our analysis also suggests that control policy design methods may benefit from broadening the types of information that is used to condition operational decisions, and from using emulation modeling to identify low‐order, computationally efficient surrogate models capturing realistic representations of river basin systems' complexity in order to isolate key decision‐relevant processes. These advances in reservoir operations hold significant promise for better addressing the challenges of conflicting human pressures and a changing world, which is particularly important, given the renewed interest in dam construction globally.
more »
« less
Efficient and robust sequential decision making algorithms
Abstract Sequential decision‐making involves making informed decisions based on continuous interactions with a complex environment. This process is ubiquitous in various applications, including recommendation systems and clinical treatment design. My research has concentrated on addressing two pivotal challenges in sequential decision‐making: (1) How can we design algorithms that efficiently learn the optimal decision strategy with minimal interactions and limited sample data? (2) How can we ensure robustness in decision‐making algorithms when faced with distributional shifts due to environmental changes and the sim‐to‐real gap? This paper summarizes and expands upon the talk I presented at the AAAI 2024 New Faculty Highlights program, detailing how my research aims to tackle these challenges.
more »
« less
- Award ID(s):
- 2323112
- PAR ID:
- 10544380
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- AI Magazine
- Volume:
- 45
- Issue:
- 3
- ISSN:
- 0738-4602
- Format(s):
- Medium: X Size: p. 376-385
- Size(s):
- p. 376-385
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract During a design process, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are important to the development of new algorithms embedded with human intelligence to augment computational design. In this paper, we develop a deep learning based approach to model and predict designers’ sequential decisions in a system design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short term memory unit model for deep leaning. This approach is demonstrated in a solar energy system design case study, and its prediction accuracy is evaluated benchmarked on several commonly used models for sequential design decisions, such as Markov Chain model, Hidden Markov Chain model, and random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to reply on both short-term and long-term memory of past design decisions in guiding their decision making in future design process. Our approach is general to be applied in many other design contexts as long as the sequential design action data is available.more » « less
-
Abstract The objective of this study is to investigate students’ decision-making during the information gathering activities of a design process. Existing literature in engineering education has shown that students face difficulties while gathering information in various activities of a design process such as brainstorming and CAD modeling. Decision-making is an important aspect of these activities. While gathering information, students make several decisions such as what information to acquire and how to acquire that information. There lies a research gap in understanding how students make decisions while gathering information in a product design process. To address this gap, we conduct semi-structured interviews and surveys in a product design course. We analyze the students’ decision-making activities from the lens of a sequential information acquisition and decision-making (SIADM) framework. We find that the students recognize the need to acquire information about the physics and dynamics of their design artifact during the CAD modeling activity of the product design process. However, they do not acquire such information from their CAD models primarily due to the lack of the project requirements, their ability, and the time to do so. Instead, they acquire such information from the prototyping activity as their physical prototype does not satisfy their design objectives. However, the students do not get the opportunity to iterate their prototype with the given cost and time constraints. Consequently, they rely on improvising during prototyping. Based on our observations, we discuss the need for designing course project activities such that it facilitates students’ product design decisions.more » « less
-
null (Ed.)Abstract In engineering systems design, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are essential to the development of new algorithms embedded with human intelligence to augment the computational design. In this paper, we develop a deep learning-based approach to model and predict designers’ sequential decisions in the systems design context. The core of this approach is an integration of the function-behavior-structure (FBS) model for design process characterization and the long short-term memory unit (LSTM) model for deep leaning. This approach is demonstrated in two case studies on solar energy system design, and its prediction accuracy is evaluated benchmarking on several commonly used models for sequential design decisions, such as the Markov Chain model, the Hidden Markov Chain model, and the random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to rely on both short-term and long-term memory of past design decisions in guiding their future decision-making in the design process. Our approach can support human–computer interactions in design and is general to be applied in other design contexts as long as the sequential data of design actions are available.more » « less
-
Abstract Reasoning with declarative knowledge (RDK) and sequential decision‐making (SDM) are two key research areas in artificial intelligence. RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning [PP] and reinforcement learning [RL]) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty. Despite the rich literature in these two areas, researchers have not fully explored their complementary strengths. In this paper, we survey algorithms that leverage RDK methods while making sequential decisions under uncertainty. We discuss significant developments, open problems, and directions for future work.more » « less
