Machine learning parallel system for integrated process-model calibration and accuracy enhancement in sewer-river system

Li, Yundong; Ma, Lina; Huang, Jingshui; Disse, Markus; Zhan, Wei; Li, Lipin; Zhang, Tianqi; Sun, Huihang; Tian, Yu

doi:10.1016/j.ese.2023.100320

Cited by 4 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even the simplest output processing techniques have demonstrably enhanced prediction performance. Additionally, metaheuristic algorithms have been used for parameter optimization and input variable selection to further improve prediction accuracy [159]. HBV and SWAT are the most widely used hydrological models, along with various data-driven models (Figure 7b).…”

Section: Discussion and Future Directionmentioning

confidence: 99%

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Yifru,

Lim,

Lee

2024

Sustainability

View full text Add to dashboard Cite

Streamflow prediction (SFP) constitutes a fundamental basis for reliable drought and flood forecasting, optimal reservoir management, and equitable water allocation. Despite significant advancements in the field, accurately predicting extreme events continues to be a persistent challenge due to complex surface and subsurface watershed processes. Therefore, in addition to the fundamental framework, numerous techniques have been used to enhance prediction accuracy and physical consistency. This work provides a well-organized review of more than two decades of efforts to enhance SFP in a physically consistent way using process modeling and flow domain knowledge. This review covers hydrograph analysis, baseflow separation, and process-based modeling (PBM) approaches. This paper provides an in-depth analysis of each technique and a discussion of their applications. Additionally, the existing techniques are categorized, revealing research gaps and promising avenues for future research. Overall, this review paper offers valuable insights into the current state of enhanced SFP within a physically consistent, domain knowledge-informed data-driven modeling framework.

show abstract

Section: Discussion and Future Directionmentioning

confidence: 99%

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Yifru,

Lim,

Lee

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…Two research articles [ 3 , 4 ] highlight the robustness and potential of AI-based techniques in detecting contamination events in water distribution systems and determining urban residential water consumption patterns, considering varying uncertainties in real-world situations. The other two studies [ 5 , 6 ] focus on the development of ML algorithms for modeling and forecasting performances of integrated water systems. Both claim emerging AI tools provide exciting opportunities to depict the complex interactions between ecological and artificial water purification processes.…”

mentioning

confidence: 99%

Artificial intelligence is transforming the research paradigm of environmental science and engineering

Wang,

Fu,

Ren

2024

Environmental Science and Ecotechnology

View full text Add to dashboard Cite

“…Ensemble Learning promote aggregation, whereby predictions are made based on multiple models. It can improve reliability and robustness through a combination of diverse routing strategies in WSNs [9], [10].…”

mentioning

confidence: 99%

Optimal Routing in Wireless Sensor Networks for Advancing IoT Efficiency and Sustainability using Enhanced Ant Colony Algorithm with machine learning approaches

A.Harshavardhan

2024

jes

View full text Add to dashboard Cite

This research study aims to investigate the incorporation of machine learning tools, such as Q-learning, Genetic Algorithms, Unsupervised Learning, and Ensemble Learning, into Enhanced Ant Colony Algorithm to assess the impacts of such incorporation on the WSN’s performance. Ten experimental trials were conducted on each to analyze the accuracy, precision, and F1 score results. It was observed that Q-learning achieves an average accuracy of 0.867; precision of 0.842; and F1 score of 0.854, making it highly adaptable and efficient in making routing decisions. The GA presented average accuracy of 0.833; precision of 0.812; and F1 score of 0.821 which show that the tool is highly robust in evolutionary optimization. Unsupervised learning machine performances indicate that the mean accuracy, precision, and F1 score for the model are 0.875, 0.856, and 0.865, respectively . As for ES with multi source models, the model showed the highest performance of 0.898, 0.882, and 0.891 in accuracy, precision, and F1 score, respectively . This study is thus very valuable in the backend regarding application of machine learning tools into routing optimization algorithms and efforts geared towards WSN efficiencies and sustainability..

show abstract

Machine learning parallel system for integrated process-model calibration and accuracy enhancement in sewer-river system

Cited by 4 publications

References 62 publications

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Artificial intelligence is transforming the research paradigm of environmental science and engineering

Optimal Routing in Wireless Sensor Networks for Advancing IoT Efficiency and Sustainability using Enhanced Ant Colony Algorithm with machine learning approaches

Contact Info

Product

Resources

About