An official website of the United States government
Karst groundwater is a critical freshwater resource for numerous regions worldwide. Monitoring and predicting karst spring discharge is essential for effective groundwater management and the preservation of karst ecosystems. However, the high heterogeneity and karstification pose significant challenges to physics-based models in providing robust predictions of karst spring discharge. In this study, an interpretable multi-step hybrid deep learning model called selective EEMD-TFT is proposed, which adaptively integrates temporal fusion transformers (TFT) with ensemble empirical mode decomposition (EEMD) for predicting karst spring discharge. The selective EEMD-TFT hybrid model leverages the strengths of both EEMD and TFT techniques to learn inherent patterns and temporal dynamics from nonlinear and nonstationary signals, eliminate redundant components, and emphasize useful characteristics of input variables, leading to the improvement of prediction performance and efficiency. It consists of two stages: in the first stage, the daily precipitation data is decomposed into multiple intrinsic mode functions using EEMD to extract valuable information from nonlinear and nonstationary signals. All decomposed components, temperature and categorical date features are then fed into the TFT model, which is an attention- based deep learning model that combines high-performance multi-horizon prediction and interpretable insights into temporal dynamics. The importance of input variables will be quantified and ranked. In the second stage, the decomposed precipitation components with high importance are selected to serve as the TFT model’s input features along with temperature and categorical date variables for the final prediction. Results indicate that the selective EEMD-TFT model outperforms other sequence-to-sequence deep learning models, such as LSTM and single TFT models, delivering reliable and robust prediction performance. Notably, it maintains more consistent prediction performance at longer forecast horizons compared to other sequence-to-sequence models, highlighting its capacity to learn complex patterns from the input data and efficiently extract valuable information for karst spring prediction. An interpretable analysis of the selective EEMD-TFT model is conducted to gain insights into relationships among various hydrological processes and analyze temporal patterns.
more »
« less
Data-Driven Global Sensitivity Analysis of Variable Groups for Understanding Complex Physical Interactions in Engineering Design
Abstract In engineering design, global sensitivity analysis (GSA) is used for analyzing the effects of inputs on the system response and is commonly studied with analytical or surrogate models. However, such models fail to capture nonlinear behaviors in complex systems and involve several modeling assumptions. Besides model-focused methods, a data-driven GSA approach, rooted in interpretable machine learning, would also identify the relationships between system components. Moreover, a special need in engineering design extends beyond performing GSA for input variables individually, but instead evaluating the contributions of variable groups on the system response. In this article, we introduce a flexible, interpretable artificial neural network model to uncover individual as well as grouped global sensitivity indices for understanding complex physical interactions in engineering design problems. The proposed model allows the investigation of the main effects and second-order effects in GSA according to functional analysis of variance (FANOVA) decomposition. To draw a higher-level understanding, we further use the subset decomposition method to analyze the significance of the groups of input variables. Using the design of a programmable material system (PMS) as an example, we demonstrate the use of our approach for examining the impact of material, architecture, and stimulus variables as well as their interactions. This information lays the foundation for managing design space complexity, summarizing the relationships between system components, and deriving design guidelines for PMS development.
more »
« less
- PAR ID:
- 10563115
- Publisher / Repository:
- ASME
- Date Published:
- Journal Name:
- Journal of Mechanical Design
- Volume:
- 146
- Issue:
- 9
- ISSN:
- 1050-0472
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Calibration of agent‐based models (ABMs) is a major challenge due to the complex nature of the systems being modeled, the heterogeneous nature of geographical regions, the varying effects of model inputs on the outputs, and computational intensity. Nevertheless, ABMs need to be carefully tuned to achieve the desirable goal of simulating spatiotemporal phenomena of interest, and a well‐calibrated model is expected to achieve an improved understanding of the phenomena. To address some of the above challenges, this article proposes an integrated framework of global sensitivity analysis (GSA) and calibration, called GSA‐CAL. Specifically, variance‐based GSA is applied to identify input parameters with less influence on differences between simulated outputs and observations. By dropping these less influential input parameters in the calibration process, this research reduces the computational intensity of calibration. Since GSA requires many simulation runs, due to ABMs' stochasticity, we leverage the high‐performance computing power provided by the advanced cyberinfrastructure. A spatially explicit ABM of influenza transmission is used as the case study to demonstrate the utility of the framework. Leveraging GSA, we were able to exclude less influential parameters in the model calibration process and demonstrate the importance of revising local settings for an epidemic pattern in an outbreak.more » « less
-
In this paper, we investigate hyperelastic and viscoelastic model parameters using Global Sensitivity Analysis(GSA). These models are used to characterize the physical response of many soft-elastomers, which are used in a wide variety of smart material applications. Recent research has shown the effectiveness of using fractional-order calculus operators in modeling the viscoelastic response. The GSA is performed using parameter subset selection (PSS), which quantifies the relative parameter contributions to the linear and nonlinear, fractional-order viscoelastic models. Calibration has been performed to quantify the model parameter uncertainty; however, this analysis has led to questions regarding parameter sensitivity and whether or not the parameters can be uniquely identified given the available data. By performing GSA we can determine which parameters are most influential in the model, and fix non-influential parameters at a nominal value. The model calibration can then be performed to quantify the uncertainty of the influential parameters.more » « less
-
Global sensitivity analysis (GSA) of distribution system with respect to stochastic PV variations plays an important role in designing optimal voltage control schemes. This paper proposes a Kriging, i.e., Gaussian process modeling enabled data-driven GSA method. The key idea is to develop a surrogate model that captures the hidden global relationship between voltage and real and reactive power injections from the historical data. With the surrogate model, the Sobol index can be conveniently calculated to assess the global sensitivity of voltage to various power injection variations. Comparison results with other model-based GSA methods on the IEEE 37-bus feeder, such as the polynomial chaos expansion and the Monte Carlo approaches demonstrate that the proposed method can achieve accurate GSA outcomes while maintaining high computational efficiency.more » « less
-
Paszynski, M.; Kranzlmüller, D.; Krzhizhanovskaya, V.V.; Dongarra, J.J.; Sloot, P.M. (Ed.)Global sensitivity analysis (GSA) is a method to quantify the effect of the input parameters on outputs of physics-based systems. Performing GSA can be challenging due to the combined effect of the high computational cost of each individual physics-based model, a large number of input parameters, and the need to perform repetitive model evaluations. To reduce this cost, neural networks (NNs) are used to replace the expensive physics-based model in this work. This introduces the additional challenge of finding the minimum number of training data samples required to train the NNs accurately. In this work, a new method is introduced to accurately quantify the GSA values by iterating over both the number of samples required to train the NNs, terminated using an outer-loop sensitivity convergence criteria, and the number of model responses required to calculate the GSA, terminated with an inner-loop sensitivity convergence criteria. The iterative surrogate-based GSA guarantees converged values for the Sobol’ indices and, at the same time, alleviates the specification of arbitrary accuracy metrics for the surrogate model. The proposed method is demonstrated in two cases, namely, an eight-variable borehole function and a three-variable nondestructive testing (NDT) case. For the borehole function, both the first- and total-order Sobol’ indices required 200 and 105 data points to terminate on the outer- and inner-loop sensitivity convergence criteria, respectively. For the NDT case, these values were 100 for both first- and total-order indices for the outer-loop sensitivity convergence, and 106 and 103 for the inner-loop sensitivity convergence, respectively, for the first- and total-order indices, on the inner-loop sensitivity convergence. The differences of the proposed method with GSA on the true functions are less than 3% in the analytical case and less than 10% in the physics-based case (where the large error comes from small Sobol’ indices).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1115/1.4064633
