scholarly journals Modeling and interpreting hydrological responses of sustainable urban drainage systems with explainable machine learning methods

2020 ◽  
Author(s):  
Yang Yang ◽  
Ting Fong May Chui
Keyword(s):  
Machine Learning ◽  
Management Practices ◽  
Hydrological Processes ◽  
Rainfall Time Series ◽  
Hydrograph Separation ◽  
Learning Methods ◽  
Drainage Systems ◽  
Factors Affecting ◽  
Machine Learning Methods ◽  
Hydrological Responses

Abstract. Sustainable drainage systems (SuDS) are decentralized stormwater management practices that mimic the natural drainage processes. Their modeling is often challenged by insufficient data and unknown factors affecting the hydrological processes. This study uses machine learning methods to model directly the correlation between hydrological responses and rainfalls at fine temporal scales in two catchments of different sizes. A feature engineering method is developed to extract useful information from rainfall time series and is used in combination with a nested cross-validation procedure to derive high-quality models and to estimate their generalization errors. The SHAP method is adopted to explain the basis of each prediction, which is then used for estimating catchment response time and hydrograph separation. The explanations of the predictions provide valuable insights into the models’ behavior and the involved hydrological processes. Thus, interpreting machine learning models is found as a useful way to study catchment hydrology.

scholarly journals Modeling and interpreting hydrological responses of sustainable urban drainage systems with explainable machine learning methods

2021 ◽  
Vol 25 (11) ◽  
pp. 5839-5858
Author(s):  
Yang Yang ◽  
Ting Fong May Chui
Keyword(s):  
Machine Learning ◽  
Management Practices ◽  
Hydrological Processes ◽  
Urban Drainage ◽  
Observation Data ◽  
Physical Processes ◽  
Large Uncertainty ◽  
Drainage Systems ◽  
Hydrological Responses ◽  
Urban Drainage Systems

Abstract. Sustainable urban drainage systems (SuDS) are decentralized stormwater management practices that mimic natural drainage processes. The hydrological processes of SuDS are often modeled using process-based models. However, it can require considerable effort to set up these models. This study thus proposes a machine learning (ML) method to directly learn the statistical correlations between the hydrological responses of SuDS and the forcing variables at sub-hourly timescales from observation data. The proposed methods are applied to two SuDS catchments with different sizes, SuDS practice types, and data availabilities in the USA for discharge prediction. The resulting models have high prediction accuracies (Nash–Sutcliffe efficiency, NSE, >0.70). ML explanation methods are then employed to derive the basis of each ML prediction, based on which the hydrological processes being modeled are then inferred. The physical realism of the inferred hydrological processes is then compared to that would be expected based on the domain-specific knowledge of the system being modeled. The inferred processes of some models, however, are found to be physically implausible. For instance, negative contributions of rainfall to runoff have been identified in some models. This study further empirically shows that an ML model's ability to provide accurate predictions can be uncorrelated with its ability to offer plausible explanations to the physical processes being modeled. Finally, this study provides a high-level overview of the practices of inferring physical processes from the ML modeling results and shows both conceptually and empirically that large uncertainty exists in every step of the inference processes. In summary, this study shows that ML methods are a useful tool for predicting the hydrological responses of SuDS catchments, and the hydrological processes inferred from modeling results should be interpreted cautiously due to the existence of large uncertainty in the inference processes.

scholarly journals Advances in Blast-Induced Impact Prediction—A Review of Machine Learning Applications

Minerals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 601
Author(s):  
Nelson K. Dumakor-Dupey ◽  
Sampurna Arya ◽  
Ankit Jha
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Academic Research ◽  
Empirical Models ◽  
Rock Breakage ◽  
Environmental Implications ◽  
Learning Methods ◽  
Factors Affecting ◽  
Impact Prediction ◽  
Machine Learning Methods

Rock fragmentation in mining and construction industries is widely achieved using drilling and blasting technique. The technique remains the most effective and efficient means of breaking down rock mass into smaller pieces. However, apart from its intended purpose of rock breakage, throw, and heave, blasting operations generate adverse impacts, such as ground vibration, airblast, flyrock, fumes, and noise, that have significant operational and environmental implications on mining activities. Consequently, blast impact studies are conducted to determine an optimum blast design that can maximize the desirable impacts and minimize the undesirable ones. To achieve this objective, several blast impact estimation empirical models have been developed. However, despite being the industry benchmark, empirical model results are based on a limited number of factors affecting the outcomes of a blast. As a result, modern-day researchers are employing machine learning (ML) techniques for blast impact prediction. The ML approach can incorporate several factors affecting the outcomes of a blast, and therefore, it is preferred over empirical and other statistical methods. This paper reviews the various blast impacts and their prediction models with a focus on empirical and machine learning methods. The details of the prediction methods for various blast impacts—including their applications, advantages, and limitations—are discussed. The literature reveals that the machine learning methods are better predictors compared to the empirical models. However, we observed that presently these ML models are mainly applied in academic research.

scholarly journals Deep Learning and Machine Learning in Hydrological Processes, Climate Change and Earth Systems: A Systematic Review

2019 ◽  
Author(s):  
Sina Faizollahzadeh ardabili ◽  
Amir Mosavi ◽  
Majid Dehghani ◽  
Annamária R. Várkonyi-Kóczy
Keyword(s):  
Climate Change ◽  
Machine Learning ◽  
Deep Learning ◽  
Model Performance ◽  
Hydrological Processes ◽  
Learning Methods ◽  
Earth Systems ◽  
Machine Learning Methods ◽  
Ensemble Techniques ◽  
Current State

Artificial intelligence methods and application have recently shown great contribution in modeling and prediction of the hydrological processes, climate change, and earth systems. Among them, deep learning and machine learning methods mainly have reported being essential for achieving higher accuracy, robustness, efficiency, computation cost, and overall model performance. This paper presents the state of the art of machine learning and deep learning methods and applications in this realm and the current state, and future trends are discussed. The survey of the advances in machine learning and deep learning are presented through a novel classification of methods. The paper concludes that deep learning is still in the first stages of development, and the research is still progressing. On the other hand, machine learning methods are already established in the fields, and novel methods with higher performance are emerging through ensemble techniques and hybridization.

scholarly journals Dataset segmentation considering the information about impact factors

2021 ◽  
pp. 29-38
Author(s):  
Iliya Lebedev
Keyword(s):  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Impact Factors ◽  
Learning Methods ◽  
Factors Affecting ◽  
Machine Learning Methods ◽  
Multiple Data ◽  
Long Run ◽  
Data Value

Introduction: The application of machine learning methods involves the collection and processing of data which comes from the recording elements in the offline mode. Most models are trained on historical data and then used in forecasting, classification, search for influencing factors or impacts, and state analysis. In the long run, the data value ranges can change, affecting the quality of the classification algorithms and leading to the situation when the models should be constantly trained or readjusted taking into account the input data. Purpose: Development of a technique to improve the quality of machine learning algorithms in a dynamically changing and non-stationary environment where the data distribution can change over time. Methods: Splitting (segmentation) of multiple data based on the information about factors affecting the ranges of target variables. Results: A data segmentation technique has been proposed, based on taking into account the factors which affect the change in the data value ranges. Impact detection makes it possible to form samples based on the current and alleged situations. Using PowerSupply dataset as an example, the mass of data is split into subsets considering the effects of factors on the value ranges. The external factors and impacts are formalized based on production rules. The processing of the factors using the membership function (indicator function) is shown. The data sample is divided into a finite number of non-intersecting measurable subsets. Experimental values of the neural network loss function are shown for the proposed technique on the selected dataset. Qualitative indicators (Accuracy, AUC, F-measure) of the classification for various classifiers are presented. Practical relevance: The results can be used in the development of classification models of machine learning methods. The proposed technique can improve the classification quality in dynamically changing conditions of the functioning.

scholarly journals Research on and Application of Tunnel Structure Defects Prediction Using Machine Learning Methods

2021 ◽  
Author(s):  
Bo Shi ◽  
Hui Su ◽  
Xu Du ◽  
Bao Jiao ◽  
Lin Wang
Keyword(s):  
Machine Learning ◽  
Rapid Development ◽  
Development Trend ◽  
Tunnel Structure ◽  
Underground Engineering ◽  
Learning Methods ◽  
Factors Affecting ◽  
Machine Learning Methods ◽  
Tree Algorithms ◽  
Subway Tunnels

With the rapid development of underground engineering in China, more metro tunnels are being constructed, the mileage of subway tunnels is increasing, and the corresponding problems of tunnel structure diseases are becoming more prominent. At present, the treatment of tunnel structural diseases mainly relies on manual inspection and identification, and research on defects prediction is still lacking. Because of the complexity of the factors affecting tunnel structure diseases, it is difficult to analyze the causes and development trend of the diseases comprehensively by manual analysis. Fortunately, machine learning methods have gained popularity in classification and regression tasks in recent decades. Many algorithms, such as decision tree algorithms, the random forest algorithm, and XGBoost, have been applied in fields including finance, engineering, and transportation. This study aimed to analyze the prediction effect of machine learning models by feeding 68055 segment lining rings of six subway lines in a city. According to the disease records from 2014 to 2016 and the corresponding convergence and characteristic data, defect conditions in 2017 were predicted and compared with real defect conditions in 2017. The accuracy rates and F1 values of the predicted results were all above 80%. The prediction results can help tunnel maintenance departments and relevant government regulators make auxiliary decisions to control tunnel structure diseases, and can help them focus on the tunnel interval of severe diseases to clarify the development trend of tunnel disease.

Sign in / Sign up

Export Citation Format

Share Document