Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models

Bai, Yun; Chen, Zhiqiang; Xie, Jingjing; Li, Chuan

doi:10.1016/j.jhydrol.2015.11.011

Cited by 183 publications

(97 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While one of DL's main strengths is to be able to digest big data, it turned out that the network architecture can also be trained with data from a single or a few sites. Bai et al (2016) applied nonrecurrent DBN to predict 10.1029/2018WR022643…”

Section: In Hydrologymentioning

confidence: 99%

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Shen

2018

Water Resources Research

756

411

View full text Add to dashboard Cite

Deep learning (DL), a new generation of artificial neural network research, has transformed industries, daily lives, and various scientific disciplines in recent years. DL represents significant progress in the ability of neural networks to automatically engineer problem‐relevant features and capture highly complex data distributions. I argue that DL can help address several major new and old challenges facing research in water sciences such as interdisciplinarity, data discoverability, hydrologic scaling, equifinality, and needs for parameter regionalization. This review paper is intended to provide water resources scientists and hydrologists in particular with a simple technical overview, transdisciplinary progress update, and a source of inspiration about the relevance of DL to water. The review reveals that various physical and geoscientific disciplines have utilized DL to address data challenges, improve efficiency, and gain scientific insights. DL is especially suited for information extraction from image‐like data and sequential data. Techniques and experiences presented in other disciplines are of high relevance to water research. Meanwhile, less noticed is that DL may also serve as a scientific exploratory tool. A new area termed AI neuroscience, where scientists interpret the decision process of deep networks and derive insights, has been born. This budding subdiscipline has demonstrated methods including correlation‐based analysis, inversion of network‐extracted features, reduced‐order approximations by interpretable models, and attribution of network decisions to inputs. Moreover, DL can also use data to condition neurons that mimic problem‐specific fundamental organizing units, thus revealing emergent behaviors of these units. Vast opportunities exist for DL to propel advances in water sciences.

show abstract

Section: In Hydrologymentioning

confidence: 99%

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Shen

2018

Water Resources Research

756

411

View full text Add to dashboard Cite

show abstract

“…Ever since, it has stimulated breakthroughs in many domains from computer vision to genomics (LeCun et al 2015). Deep learning has been also utilized in the water resources domain recently for precipitation estimation (Tao et al 2016), reservoir inflow forecasting (Bai et al 2016), and hydrological inference (Marcais and Dreuzy, 2017). Deep learning holds promise for detection of cyberattacks to ICSs as well given the heterogeneity and massiveness of their data and intricacy of the underlying systems.…”

Section: Deep Learningmentioning

confidence: 99%

Cyberattack Detection Using Deep Generative Models with Variational Inference

Chandy

Rasekh

Barker

et al. 2019

J. Water Resour. Plann. Manage.

View full text Add to dashboard Cite

Recent years have witnessed a rise in the frequency and intensity of cyberattacks targeted at critical infrastructure systems. This study designs a versatile, data-driven cyberattack detection platform for infrastructure systems cybersecurity, with a special demonstration in water sector. A deep generative model with variational inference autonomously learns normal system behavior and detects attacks as they occur. The model can process the natural data in its raw form and automatically discover and learn its representations, hence augmenting system knowledge discovery and reducing the need for laborious human engineering and domain expertise. The proposed model is applied to a simulated cyberattack detection problem involving a drinking water distribution system subject to programmable logic controller hacks, malicious actuator activation, and deception attacks. The model is only provided with observations of the system, such as pump pressure and tank water level reads, and is blind to the internal structures and workings of the water distribution system. The simulated attacks are manifested in the model's generated reproduction probability plot, indicating its ability to discern the attacks. There is, however, need for improvements in reducing false alarms, especially by optimizing detection thresholds. Altogether, the results indicate ability of the model in distinguishing attacks and their repercussions from normal system operation in water distribution systems, and the promise it holds for cyberattack detection in other domains.

show abstract

“…Third, as the preprocessing techniques of the MLMs, time series decomposition methods have been applied to hybrid MLMs development. The methods included discrete wavelet transform (DWT) [37,38], maximal overlap DWT (MODWT) [39], wavelet packet transform (WPT) [40], empirical mode decomposition (EMD) [41,42], and ensemble EMD (EEMD) [43,44]. It has been reported that these hybrid MLMs, which consists of time series decomposition and sub-time series modeling, were able to achieve better performance compared with the single MLMs.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

2018

View full text Add to dashboard Cite

Accurate modeling for nonlinear and nonstationary rainfall-runoff processes is essential for performing hydrologic practices effectively. This paper proposes two hybrid machine learning models (MLMs) coupled with variational mode decomposition (VMD) to enhance the accuracy for daily rainfall-runoff modeling. These hybrid MLMs consist of VMD-based extreme learning machine (VMD-ELM) and VMD-based least squares support vector regression (VMD-LSSVR). The VMD is employed to decompose original input and target time series into sub-time series called intrinsic mode functions (IMFs). The ELM and LSSVR models are selected for developing daily rainfall-runoff models utilizing the IMFs as inputs. The performances of VMD-ELM and VMD-LSSVR models are evaluated utilizing efficiency and effectiveness indices. Their performances are also compared with those of VMD-based artificial neural network (VMD-ANN), discrete wavelet transform (DWT)-based MLMs (DWT-ELM, DWT-LSSVR, and DWT-ANN) and single MLMs (ELM, LSSVR, and ANN). As a result, the VMD-based MLMs provide better accuracy compared with the single MLMs and yield slightly better performance than the DWT-based MLMs. Among all models, the VMD-ELM and VMD-LSSVR models achieve the best performance in daily rainfall-runoff modeling with respect to efficiency and effectiveness. Therefore, the VMD-ELM and VMD-LSSVR models can be an alternative tool for reliable and accurate daily rainfall-runoff modeling.

show abstract

Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models

Cited by 183 publications

References 52 publications

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Cyberattack Detection Using Deep Generative Models with Variational Inference

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

Contact Info

Product

Resources

About