Deep neural network for marine water quality classification with the consideration of coastal current circulation effect

Chu, Carlin C.F.; Yuen, S. C.; Wong, Yee Keung

doi:10.1109/iss1.2017.8389437

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction of the occurrence of red tide requires the use of time-lagged interrelated chemical and climatological information. Recent studies have demonstrated that the modeling accuracy can be further improved by including information collected from nearby coastal regions [4], [12], [29]. As a result, the prediction of red tide involves the use of hundreds of interrelated time-lagged features where some of them are presented complementarily in nature.…”

Section: A Datamentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection Using Approximated High-Order Interaction Components of the Shapley Value for Boosted Tree Classifier

Chu

Chan²

2020

IEEE Access

View full text Add to dashboard Cite

The Shapely value originates from the cooperative game theory and has been widely used in solving machine learning problems due to its high interpretability and consistency. The typical Shapley value evaluates the importance score of a feature as its average marginal contribution to a fully parameterized model under all possible feature combinations; as a result, its value includes the influences from both selected features and unselected ones. To better separate the corresponding sources, it is suggested to decompose the Shapley value into high-order interaction effect components such that the influences from each individual feature can be effectively untangled. A feature's contribution is decomposed into distinct interaction components, and each component corresponds to a joint contribution resulting from a particular feature combination. The feature ranking is therefore evaluated with respect to the selected feature subset and calculated as the total incremental contribution by summing up its corresponding decomposed interaction values. In this study, a computationally efficient model-dependent greedy search algorithm on the high-order interaction components is proposed to solve an optimal subset selection problem with hundreds of time-lagged interrelated input features. Our algorithm extends a recently developed low-order polynomial time method for calculating the interaction component values. The empirical analysis demonstrates that the proposed method always outperforms other methods that are based on the typical Shapley value, the gain or the split count criteria, in terms of in-sample representativeness and out-of-sample forecasting performance for handling a problem with hundreds of time-lagged input features.

show abstract

Section: A Datamentioning

confidence: 99%

“…http://epic.epd.gov.hk/EPICRIVER/marine/?lang=en2 The Hong Kong Observatory -Climatological Information Services. http://www.hko.gov.hk/cis/climat_e.htm3 The threshold is set to be 20 µg/L after referencing the information listed in the Hong Kong red tide database 4. The Python XGBoost implementation is employed in this study.…”

mentioning

confidence: 99%

Feature Selection Using Approximated High-Order Interaction Components of the Shapley Value for Boosted Tree Classifier

Chu

Chan²

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

Development of Image Analysis Methods for Detecting Nonhomogeneity and Anomalies in the Marine Environment

Shishkin

Grekov

2021

2021 International Russian Automation Conference (RusAutoCon)

View full text Add to dashboard Cite

Remote Sensing Inversion of Water Quality Grades Using a Stacked Generalization Approach

Zhao,

Wan,

Wang

et al. 2024

Sensors

View full text Add to dashboard Cite

Understanding water quality is crucial for environmental management and policy formulation. However, existing methods for assessing water quality are often unable to fully integrate with multi-source remote sensing data. This study introduces a method that employs a stacking algorithm within the Google Earth Engine (GEE) for classifying water quality grades in the Songhua River Basin (SHRB). By leveraging the strengths of multiple machine learning models, the Stacked Generalization (SG) model achieved an accuracy of 91.67%, significantly enhancing classification performance compared to traditional approaches. Additionally, the analysis revealed substantial correlations between the normalized difference vegetation index (NDVI) and precipitation with water quality grades. These findings underscore the efficacy of this method for effective water quality monitoring and its implications for understanding the influence of natural factors on water pollution.

show abstract

Deep neural network for marine water quality classification with the consideration of coastal current circulation effect

Cited by 3 publications

References 12 publications

Feature Selection Using Approximated High-Order Interaction Components of the Shapley Value for Boosted Tree Classifier

Feature Selection Using Approximated High-Order Interaction Components of the Shapley Value for Boosted Tree Classifier

Development of Image Analysis Methods for Detecting Nonhomogeneity and Anomalies in the Marine Environment

Remote Sensing Inversion of Water Quality Grades Using a Stacked Generalization Approach

Contact Info

Product

Resources

About