Evaluating Ecohydrological Model Sensitivity to Input Variability with an Information-Theory-Based Approach

Farahani, Mozhgan A.; Vahid, Alireza; Goodwell, Allison E.

doi:10.3390/e24070994

Cited by 8 publications

(5 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also did not specifically focus on the optimization of hyperparameters within each ML model, which could have an effect on functional and predictive performance. Moreover, the precision and general quality of the forcing variables and Fc are important as they have underlying uncertainties and have been gap-filled, and our interpolation methods may have more effect on some model structures than others and future research could explore how models use information encoded in forcing data (Farahani et al, 2022). We also note that the MLR performance can be significantly influenced by multicollinearity among the forcing variables, and we did not test for this aspect.…”

Section: Discussionmentioning

confidence: 97%

Causal Drivers of Land-Atmosphere Carbon Fluxes from Machine Learning Models and Data

Farahani,

Goodwell

2023

Preprint

View full text Add to dashboard Cite

Interactions among atmospheric, root-soil, and vegetation processes drive carbon dioxide fluxes (Fc) from land to atmosphere. Eddy covariance measurements are commonly used to measure Fc at sub-daily timescales and validate process-based and data-driven models. However, these validations do not reveal process interactions, thresholds, and key differences in how models replicate them. We use information theory-based measures to explore multivariate information flow pathways from forcing data to observed and modeled hourly Fc, using flux tower datasets in the Midwestern U.S. in intensively managed corn-soybean landscapes. We compare Multiple Linear Regressions (MLR), Long-Short Term Memory (LSTM), and Random Forests (RF) to evaluate how different model structures use information from combinations of sources to predict Fc. We extend a framework for model predictive performance and functional performance, which examines the full suite of dependencies from all forcing variables to the observed or modeled target. Of the three model types, RF exhibited the highest functional and predictive performance. Regionally trained models demonstrate lower predictive but higher functional performance compared to site-specific models, suggesting superior reproduction of observed relationships. This study shows that some metrics of predictive performance encapsulate functional behaviors better than others, highlighting the need for multiple metrics of both types. This study improves our understanding of carbon fluxes in an intensively managed landscape, and more generally provides insight into how model structures and forcing variables translate to interactions that are well versus poorly captured in models.

show abstract

Section: Discussionmentioning

confidence: 97%

Causal Drivers of Land-Atmosphere Carbon Fluxes from Machine Learning Models and Data

Farahani,

Goodwell

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We also did not specifically focus on the optimization of hyperparameters within each ML model, which could affect functional and predictive performance. Furthermore, the precision and general quality of the forcing variables and Fc measurements are important as they have underlying uncertainties and have been gap‐filled, and our interpolation methods may influence some model structures than others and future research could explore how models use information encoded in forcing data (Farahani et al., 2022). We also note that the MLR performance can be significantly influenced by multicollinearity among the forcing variables (Farahani et al., 2023; Mojtaba et al., 2023), and we did not test for this aspect.…”

Section: Discussionmentioning

confidence: 99%

Causal Drivers of Land‐Atmosphere Carbon Fluxes From Machine Learning Models and Data

Farahani,

Goodwell

2024

JGR Biogeosciences

View full text Add to dashboard Cite

Interactions among atmospheric, root‐soil, and vegetation processes drive carbon dioxide fluxes (Fc) from land to atmosphere. Eddy covariance measurements are commonly used to measure Fc at sub‐daily timescales and validate process‐based and data‐driven models. However, these validations do not reveal process interactions, thresholds, and key differences in how models replicate them. We use information theory‐based measures to explore multivariate information flow pathways from forcing data to observed and modeled hourly Fc, using flux tower data sets in the Midwestern U.S. in intensively managed corn‐soybean landscapes. We compare multiple linear regressions, long‐short term memory, and random forests (RF), and evaluate how different model structures use information from combinations of sources to predict Fc. We extend a framework for model predictive and functional performance, which examines a suite of dependencies from all forcing variables to the observed or modeled target. Of the three model types, RF exhibited the highest functional and predictive performance, correctly capturing strong dependencies between radiation and temperature variables with Fc. Regionally trained models demonstrate lower predictive but higher functional performance compared to site‐specific models, suggesting superior reproduction of observed relationships at the expense of predictive accuracy. This study shows that some metrics of predictive performance encapsulate functional behaviors better than others, highlighting the need for multiple metrics of both types. This study improves our understanding of carbon fluxes in an intensively managed landscape, and more generally provides insight into how model structures and forcing variables translate to interactions that are well versus poorly captured in models.

show abstract

“…The analysis of time-series data has proven valuable in extracting meaningful events in smart manufacturing systems [3]. While time-series data can be found in various domains such as healthcare [4], climate [5], robotics [6], ecohydrology [7], stock markets [8], energy systems [9], etc., this paper focuses on the plastic processing industry as a case study within the manufacturing domain. A comprehensive review of time-series applications in manufacturing can be found in [10].…”

Section: Introductionmentioning

confidence: 99%

Multivariate Time-Series Classification of Critical Events from Industrial Drying Hopper Operations: A Deep Learning Approach

Rahman,

Farahani,

Wuest

2023

JMMP

View full text Add to dashboard Cite

In recent years, the advancement of Industry 4.0 and smart manufacturing has made a large amount of industrial process data attainable with the use of sensors installed on machines. This paper proposes an experimental predictive maintenance framework for an industrial drying hopper so that it can detect any unusual event in the hopper, which reduces the risk of erroneous fault diagnosis in the manufacturing shop floor. The experimental framework uses Deep Learning (DL) algorithms to classify Multivariate Time-Series (MTS) data into two categories—failure or unusual events and regular events—thus formulating the problem as a binary classification. The raw data extracted from the sensors contained missing values, suffered from imbalancedness, and were not labeled. Therefore, necessary preprocessing is performed to make them usable for DL algorithms and the dataset is self-labeled after defining the two categories precisely. To tackle the imbalanced data issue, data balancing techniques like ensemble learning with undersampling and Synthetic Minority Oversampling Technique (SMOTE) are used. Moreover, along with DL algorithms like Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), Machine Learning (ML) algorithms like Support Vector Machine (SVM) and K-nearest neighbor (KNN) have also been used to perform a comparative analysis on the results obtained from these algorithms. The result shows that CNN is arguably the best algorithm for classifying this dataset into two categories and outperforms other traditional approaches as well as deep learning algorithms.

show abstract

Evaluating Ecohydrological Model Sensitivity to Input Variability with an Information-Theory-Based Approach

Cited by 8 publications

References 63 publications

Causal Drivers of Land-Atmosphere Carbon Fluxes from Machine Learning Models and Data

Causal Drivers of Land-Atmosphere Carbon Fluxes from Machine Learning Models and Data

Causal Drivers of Land‐Atmosphere Carbon Fluxes From Machine Learning Models and Data

Multivariate Time-Series Classification of Critical Events from Industrial Drying Hopper Operations: A Deep Learning Approach

Contact Info

Product

Resources

About