scholarly journals Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation

2005 ◽  
Vol 9 (1/2) ◽  
pp. 111-126 ◽  
Author(s):  
N. J. de Vos ◽  
T. H. M. Rientjes
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Goodness Of Fit ◽  
Model Performance ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Trade Offs ◽  
Hourly Data ◽  
Artificial Neural ◽  
Daily Forecast

Abstract. The application of Artificial Neural Networks (ANNs) in rainfall-runoff modelling needs to be researched more extensively in order to appreciate and fulfil the potential of this modelling approach. This paper reports on the application of multi-layer feedforward ANNs for rainfall-runoff modelling of the Geer catchment (Belgium) using both daily and hourly data. The daily forecast results indicate that ANNs can be considered good alternatives for traditional rainfall-runoff modelling approaches, but the simulations based on hourly data reveal timing errors as a result of a dominating autoregressive component. This component is introduced in model simulations by using previously observed runoff values as ANN model input, which is a popular method for indirectly representing the hydrological state of a catchment. Two possible solutions to this problem of lagged predictions are presented. Firstly, several alternatives for representation of the hydrological state are tested as ANN inputs: moving averages over time of observed discharges and rainfall, and the output of the simple GR4J model component for soil moisture. A combination of these hydrological state representers produces good results in terms of timing, but the overall goodness of fit is not as good as the simulations with previous runoff data. Secondly, the possibility of using multiple measures of model performance during ANN training is mentioned.

scholarly journals Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation

2005 ◽  
Vol 2 (1) ◽  
pp. 365-415 ◽  
Author(s):  
N. J. de Vos ◽  
T. H. M. Rientjes
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Goodness Of Fit ◽  
Model Performance ◽  
Performance Measure ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Trade Offs ◽  
Hourly Data ◽  
Artificial Neural

Abstract. The application of Artificial Neural Networks (ANNs) on rainfall-runoff modelling needs to be researched more extensively in order to appreciate and fulfil the potential of this modelling approach. This paper reports on the application of multi-layer feedforward ANNs for rainfall-runoff modelling in the Geer catchment (Belgium) using both daily and hourly data. The good daily forecast results indicate that ANNs can be considered alternatives for traditional rainfall-runoff modelling approaches. However, investigation of the forecasts based on hourly data reveal a constraint that has hitherto been neglected by hydrologists. A timing error occurs due to a dominating autoregressive component that is introduced by using previous runoff values as ANN model input. The reason for the popular practice of using these previous runoff data is that this information indirectly represents the hydrological state of the catchment. Two possible solutions to this timing problem are discussed. Firstly, several alternatives for representation of the hydrological state are presented: moving averages over the previous discharge and over the previous rainfall, and the output of the simple GR4J model component for soil moisture. A combination of these various hydrological state representators produces good results in terms of timing, but the overall goodness of fit is not as good as the simulations with previous runoff data. Secondly, the use of a combination of multiple measures of model performance during ANN training is suggested, since not all differences between modelled and observed hydrograph characteristics such as timing, volume, and absolute values can be adequately expressed by a single performance measure. The possible undervaluation of timing errors by the commonly-used squared-error-based functions is a clear example of this inability.

Hydrological modelling using artificial neural networks

2001 ◽  
Vol 25 (1) ◽  
pp. 80-108 ◽  
Author(s):  
C. W. Dawson ◽  
R. L. Wilby
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Model Performance ◽  
Model Complexity ◽  
Network Architectures ◽  
Training Algorithms ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Validation Data ◽  
Artificial Neural

This review considers the application of artificial neural networks (ANNs) to rainfall-runoff modelling and flood forecasting. This is an emerging field of research, characterized by a wide variety of techniques, a diversity of geographical contexts, a general absence of intermodel comparisons, and inconsistent reporting of model skill. This article begins by outlining the basic principles of ANN modelling, common network architectures and training algorithms. The discussion then addresses related themes of the division and preprocessing of data for model calibration/validation; data standardization techniques; and methods of evaluating ANN model performance. A literature survey underlines the need for clear guidance in current modelling practice, as well as the comparison of ANN methods with more conventional statistical models. Accordingly, a template is proposed in order to assist the construction of future ANN rainfall-runoff models. Finally, it is suggested that research might focus on the extraction of hydrological ‘rules’ from ANN weights, and on the development of standard performance measures that penalize unnecessary model complexity.

scholarly journals The extrapolation of artificial neural networks for the modelling of rainfall—runoff relationships

2005 ◽  
Vol 7 (4) ◽  
pp. 291-296 ◽  
Author(s):  
P. Hettiarachchi ◽  
M. J. Hall ◽  
A. W. Minns
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Domain Knowledge ◽  
Low Frequency ◽  
Training Data ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Data Set ◽  
Feed Forward ◽  
Artificial Neural

The last decade has seen increasing interest in the application of Artificial Neural Networks (ANNs) for the modelling of the relationship between rainfall and streamflow. Since multi-layer, feed-forward ANNs have the property of being universal approximators, they are able to capture the essence of most input–output relationships, provided that an underlying deterministic relationship exists. Unfortunately, owing to the standardisation of inputs and outputs that is required to run ANNs, a problem arises in extrapolation: if the training data set does not contain the maximum possible output value, an unmodified network will be unable to synthesise this peak value. The occurrence of high magnitude, low frequency events within short periods of record is largely fortuitous. Therefore, the confidence in the neural network model can be greatly enhanced if some methodology can be found for incorporating domain knowledge about such events into the calibration and verification procedure in addition to the available measured data sets. One possible form of additional domain knowledge is the Estimated Maximum Flood (EMF), a notional event with a small but non-negligible probability of exceedence. This study investigates the suitability of including an EMF estimate in the training set of a rainfall–runoff ANN in order to improve the extrapolation characteristics of the network. A study has been carried out in which EMFs have been included, along with recorded flood events, in the training of ANN models for six catchments in the south west of England. The results demonstrate that, with prior transformation of the runoff data to logarithms of flows, the inclusion of domain knowledge in the form of such extreme synthetic events improves the generalisation capabilities of the ANN model and does not disrupt the training process. Where guidelines are available for EMF estimation, the application of this approach is recommended as an alternative means of overcoming the inherent extrapolation problems of multi-layer, feed-forward ANNs.

Predicting Viscosities of Heavy Oils and Solvent–Heavy Oil Mixtures Using Artificial Neural Networks

2021 ◽  
Vol 143 (11) ◽  
Author(s):  
Zehua Chen ◽  
Daoyong Yang
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Model Performance ◽  
Viscosity Data ◽  
Heavy Oils ◽  
Ann Model ◽  
Wide Range ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural

Abstract This study investigates the potential of artificial neural networks (ANNs) to accurately predict viscosities of heavy oils (HOs) as well as mixtures of solvents and heavy oils (S–HOs). The study uses experimental data collected from the public domain for HO viscosities (involving 20 HOs and 568 data points) and S–HO mixture viscosities (involving 12 solvents and 4057 data points) for a wide range of temperatures, pressures, and mass fractions. The natural logarithm of viscosity (instead of viscosity itself) is used as predictor and response variables for the ANNs to significantly improve model performance. Gaps in HO viscosity data (with respect to pressure or temperature) are filled using either the existing correlations or ANN models that innovatively use viscosity ratios from the available data. HO viscosities and mixture viscosities (weight-based, molar-based, and volume-based) from the trained ANN models are found to be more accurate than those from commonly used empirical correlations and mixing rules. The trained ANN model also fares well for another dataset of condensate-diluted HOs.

scholarly journals Predicting Sooting Propensity of Oxygenated Fuels Using Artificial Neural Networks

Processes ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 1070
Author(s):  
Abdul Gani Abdul Jameel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Functional Groups ◽  
Average Error ◽  
Ann Model ◽  
Oh Groups ◽  
Unseen Data ◽  
Learning Capabilities ◽  
Artificial Neural ◽  
Oxygenated Fuels

The self-learning capabilities of artificial neural networks (ANNs) from large datasets have led to their deployment in the prediction of various physical and chemical phenomena. In the present work, an ANN model was developed to predict the yield sooting index (YSI) of oxygenated fuels using the functional group approach. A total of 265 pure compounds comprising six chemical classes, namely paraffins (n and iso), olefins, naphthenes, aromatics, alcohols, and ethers, were dis-assembled into eight constituent functional groups, namely paraffinic CH3 groups, paraffinic CH2 groups, paraffinic CH groups, olefinic –CH=CH2 groups, naphthenic CH-CH2 groups, aromatic C-CH groups, alcoholic OH groups, and ether O groups. These functional groups, in addition to molecular weight and branching index, were used as inputs to develop the ANN model. A neural network with two hidden layers was used to train the model using the Levenberg–Marquardt (ML) training algorithm. The developed model was tested with 15% of the random unseen data points. A regression coefficient (R2) of 0.99 was obtained when the experimental values were compared with the predicted YSI values from the test set. An average error of 3.4% was obtained, which is less than the experimental uncertainty associated with most reported YSI measurements. The developed model can be used for YSI prediction of hydrocarbon fuels containing alcohol and ether-based oxygenates as additives with a high degree of accuracy.

scholarly journals Modelling and Prediction of Monthly Global Irradiation Using Different Prediction Models

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2332
Author(s):  
Cecilia Martinez-Castillo ◽  
Gonzalo Astray ◽  
Juan Carlos Mejuto
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Random Forests ◽  
Prediction Models ◽  
Meteorological Station ◽  
Ann Model ◽  
Global Irradiation ◽  
Artificial Neural ◽  
Input Variables ◽  
Using Data

Different prediction models (multiple linear regression, vector support machines, artificial neural networks and random forests) are applied to model the monthly global irradiation (MGI) from different input variables (latitude, longitude and altitude of meteorological station, month, average temperatures, among others) of different areas of Galicia (Spain). The models were trained, validated and queried using data from three stations, and each best model was checked in two independent stations. The results obtained confirmed that the best methodology is the ANN model which presents the lowest RMSE value in the validation and querying phases 1226 kJ/(m2∙day) and 1136 kJ/(m2∙day), respectively, and predict conveniently for independent stations, 2013 kJ/(m2∙day) and 2094 kJ/(m2∙day), respectively. Given the good results obtained, it is convenient to continue with the design of artificial neural networks applied to the analysis of monthly global irradiation.

scholarly journals Use of Nondestructive Testing of Ultrasound and Artificial Neural Networks to Estimate Compressive Strength of Concrete

Buildings ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 44
Author(s):  
Fernando A. N. Silva ◽  
João M. P. Q. Delgado ◽  
Rosely S. Cavalcanti ◽  
António C. Azevedo ◽  
Ana S. Guimarães ◽  
...  
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Artificial Neural Networks ◽  
Cross Sections ◽  
Influential Factors ◽  
Average Error ◽  
Ann Model ◽  
Cement Ratio ◽  
Water Cement Ratio ◽  
Artificial Neural

The work presents the results of an experimental campaign carried out on concrete elements in order to investigate the potential of using artificial neural networks (ANNs) to estimate the compressive strength based on relevant parameters, such as the water–cement ratio, aggregate–cement ratio, age of testing, and percentage cement/metakaolin ratios (5% and 10%). We prepared 162 cylindrical concrete specimens with dimensions of 10 cm in diameter and 20 cm in height and 27 prismatic specimens with cross sections measuring 25 and 50 cm in length, with 9 different concrete mixture proportions. A longitudinal transducer with a frequency of 54 kHz was used to measure the ultrasonic velocities. An ANN model was developed, different ANN configurations were tested and compared to identify the best ANN model. Using this model, it was possible to assess the contribution of each input variable to the compressive strength of the tested concretes. The results indicate an excellent performance of the ANN model developed to predict compressive strength from the input parameters studied, with an average error less than 5%. Together, the water–cement ratio and the percentage of metakaolin were shown to be the most influential factors for the compressive strength value predicted by the developed ANN model.

scholarly journals Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology?

2003 ◽  
Vol 7 (5) ◽  
pp. 693-706 ◽  
Author(s):  
E. Gaume ◽  
R. Gosset
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Conceptual Model ◽  
Linear Model ◽  
Case Studies ◽  
Stream Flow ◽  
River Flow ◽  
Prediction Models ◽  
Rainfall Runoff ◽  
Artificial Neural

Abstract. Recently Feed-Forward Artificial Neural Networks (FNN) have been gaining popularity for stream flow forecasting. However, despite the promising results presented in recent papers, their use is questionable. In theory, their “universal approximator‿ property guarantees that, if a sufficient number of neurons is selected, good performance of the models for interpolation purposes can be achieved. But the choice of a more complex model does not ensure a better prediction. Models with many parameters have a high capacity to fit the noise and the particularities of the calibration dataset, at the cost of diminishing their generalisation capacity. In support of the principle of model parsimony, a model selection method based on the validation performance of the models, "traditionally" used in the context of conceptual rainfall-runoff modelling, was adapted to the choice of a FFN structure. This method was applied to two different case studies: river flow prediction based on knowledge of upstream flows, and rainfall-runoff modelling. The predictive powers of the neural networks selected are compared to the results obtained with a linear model and a conceptual model (GR4j). In both case studies, the method leads to the selection of neural network structures with a limited number of neurons in the hidden layer (two or three). Moreover, the validation results of the selected FNN and of the linear model are very close. The conceptual model, specifically dedicated to rainfall-runoff modelling, appears to outperform the other two approaches. These conclusions, drawn on specific case studies using a particular evaluation method, add to the debate on the usefulness of Artificial Neural Networks in hydrology. Keywords: forecasting; stream-flow; rainfall-runoff; Artificial Neural Networks

Building hydrological single-model ensembles using artificial neural networks and a combinatorial optimization approach

2021 ◽  
Author(s):  
Juan F. Farfán-Durán ◽  
Luis Cea
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Goodness Of Fit ◽  
Hydrological Model ◽  
Hill Climbing ◽  
Single Model ◽  
Pearson Coefficient ◽  
Gradient Based ◽  
Artificial Neural ◽  
Model Ensembles

<p>In recent years, the application of model ensembles has received increasing attention in the hydrological modelling community due to the interesting results reported in several studies carried out in different parts of the world. The main idea of these approaches is to combine the results of the same hydrological model or a number of different hydrological models in order to obtain more robust, better-fitting models, reducing at the same time the uncertainty in the predictions. The techniques for combining models range from simple approaches such as averaging different simulations, to more complex techniques such as least squares, genetic algorithms and more recently artificial intelligence techniques such as Artificial Neural Networks (ANN).</p><p>Despite the good results that model ensembles are able to provide, the models selected to build the ensemble have a direct influence on the results. Contrary to intuition, it has been reported that the best fitting single models do not necessarily produce the best ensemble. Instead, better results can be obtained with ensembles that incorporate models with moderate goodness of fit. This implies that the selection of the single models might have a random component in order to maximize the results that ensemble approaches can provide.</p><p>The present study is carried out using hydrological data on an hourly scale between 2008 and 2015 corresponding to the Mandeo basin, located in the Northwest of Spain. In order to obtain 1000 single models, a hydrological model was run using 1000 sets of parameters sampled randomly in their feasible space. Then, we have classified the models in 3 groups with the following characteristics: 1) The 25 single models with highest Nash-Sutcliffe coefficient, 2) The 25 single models with the highest Pearson coefficient, and 3) The complete group of 1000 single models.</p><p>The ensemble models are built with 5 models as the input of an ANN and the observed series as the output. Then, we applied the Random-Restart Hill-Climbing (RRHC) algorithm choosing 5 random models in each iteration to re-train the ANN in order to identify a better ensemble. The algorithm is applied to build 50 ensembles in each group of models. Finally, the results are compared to those obtained by optimizing the model using a gradient-based method by means of the following goodness-of-fit measures: Nash-Sutcliffe (NSE) coefficient, adapted for high flows Nash-Sutcliffe (HF−NSE), adapted for low flows Nash-Sutcliffe (LF−W NSE) and coefficient of determination (R2).</p><p>The results show that the RRHC algorithm can identify adequate ensembles. The ensembles built using the group of models selected based on the NSE outperformed the model optimized by the gradient method in 64 % of the cases in at least 3 of 4 coefficients, both in the calibration and validation stages. Followed by the ensembles built with the group of models selected based on the Pearson coefficient with 56 %. In the case of the third group, no ensembles were identified that outperformed the gradient-based method. However, the most part of the ensembles outperformed the 1000 individual models.</p><p><strong>Keywords: Multi-model ensemble; Single-model ensemble; Artificial Neural Networks; Hydrological Model; Random-restart Hill-climbing</strong></p><p> </p>

Sign in / Sign up

Export Citation Format

Share Document