Regional flood frequency estimation for the contiguous USA using Artificial Neural Networks

2020 ◽  
Author(s):  
Valeriya Fillipova ◽  
David Leedal ◽  
Anthony Hammond
Keyword(s):  
Regression Model ◽  
Soil Type ◽  
Peak Flow ◽  
Frequency Estimation ◽  
Flood Frequency ◽  
Annual Rainfall ◽  
Ann Model ◽  
Artificial Neural ◽  
Hidden Layer ◽  
Regional Flood Frequency

<p>We have recently demonstrated the utility of a machine learning-based regional peak flow quantile regression model that is currently providing flood frequency estimation for the re/insurance industry across the contiguous US river network. The scheme uses an artificial neural network (ANN) regression model to estimate flood frequency quantiles from physical catchment descriptors. This circumvents the difficult-to-justify assumption of homogeneity required by alternative ‘region of hydrological similarity’ approaches. The structure of the model is as follows: the output (dependent) variable is a set of peak flow quantiles where the distributions used to derive the quantiles were parameterised from observations at 4,079 gauge sites using the USGS Bulletin 17C extreme value estimation method (notable for its inclusion of pre-instrumental flood events). The features (regressors) for the model were formed from 25 catchment descriptors covering; geometry, elevation, land cover, soil type and climate type for both the gauged sites and the catchments related to a further 906,000 ungauged sites where peak flow quantile estimation was undertaken. The feature collection requires massive computational resource to achieve catchment delineation and GIS processing of land-use, soil-type and precipitation data.</p><p>This project integrates many modelling and computational science elements. Here we focus attention on the ANN modelling component as this is of interest to the wider hydrology research community. We pass on our experience of working with this modelling approach and the unique challenges of working on a problem of this scale.</p><p>A baseline multiple linear regression model was generated, as were several non-linear alternative formulations. The ANN model was chosen as the best approach according to a root mean square error (RMSE) criterion. Alternative ANN formulations were evaluated. The RMSE indicated that a single hidden layer performed better than more complex multiple hidden layer models. Variable importance algorithms were used to assess the mechanistic credibility of the ANN model and showed that catchment area and mean annual rainfall were consistently identified as dominant features in agreement with the expectations of domain experts together with more subtle region-specific factors.</p><p>The results of this study show that ANN models, used as part of a carefully configured large-scale  computational hydrology project, produce very useful regional flood frequency estimates that can be used to inform flood risk management decision-making or drive further hydrodynamic 2D-modelling and are appropriate to the ever-increasing scale of contemporary hydrological modelling problems.</p>

scholarly journals Artificial neural network, predictor variables and sensitivity threshold for DNA methylation-based age prediction using blood samples

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zhonghui Thong ◽  
Jolena Ying Ying Tan ◽  
Eileen Shuzhen Loo ◽  
Yu Wei Phua ◽  
Xavier Liang Shun Chan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Regression Model ◽  
Sensitivity Threshold ◽  
Ann Model ◽  
Blood Samples ◽  
Ann Models ◽  
Artificial Neural ◽  
The Impact ◽  
Age Prediction

AbstractRegression models are often used to predict age of an individual based on methylation patterns. Artificial neural network (ANN) however was recently shown to be more accurate for age prediction. Additionally, the impact of ethnicity and sex on our previous regression model have not been studied. Furthermore, there is currently no age prediction study investigating the lower limit of input DNA at the bisulfite treatment stage prior to pyrosequencing. Herein, we evaluated both regression and ANN models, and the impact of ethnicity and sex on age prediction for 333 local blood samples using three loci on the pyrosequencing platform. Subsequently, we trained a one locus-based ANN model to reduce the amount of DNA used. We demonstrated that the ANN model has a higher accuracy of age prediction than the regression model. Additionally, we showed that ethnicity did not affect age prediction among local Chinese, Malays and Indians. Although the predicted age of males were marginally overestimated, sex did not impact the accuracy of age prediction. Lastly, we present a one locus, dual CpG model using 25 ng of input DNA that is sufficient for forensic age prediction. In conclusion, the two ANN models validated would be useful for age prediction to provide forensic intelligence leads.

scholarly journals An artificial neural network application to produce debris source areas of Barla, Besparmak, and Kapi Mountains (NW Taurids, Turkey)

2007 ◽  
Vol 7 (5) ◽  
pp. 557-570 ◽  
Author(s):  
M. C. Tunusluoglu ◽  
C. Gokceoglu ◽  
H. Sonmez ◽  
H. A. Nefeslioglu
Keyword(s):  
Engineering Geology ◽  
Source Area ◽  
Learning Ability ◽  
Susceptibility Map ◽  
Ann Model ◽  
New Approach ◽  
Failure Tolerance ◽  
Accelerate Convergence ◽  
Artificial Neural ◽  
Hidden Layer

Abstract. Various statistical, mathematical and artificial intelligence techniques have been used in the areas of engineering geology, rock engineering and geomorphology for many years. However, among the techniques, artificial neural networks are relatively new approach used in engineering geology in particular. The attractiveness of ANN for the engineering geological problems comes from the information processing characteristics of the system, such as non-linearity, high parallelism, robustness, fault and failure tolerance, learning, ability to handle imprecise and fuzzy information, and their capability to generalize. For this reason, the purposes of the present study are to perform an application of ANN to a engineering geology problem having a very large database and to introduce a new approach to accelerate convergence. For these purposes, an ANN architecture having 5 neurons in one hidden layer was constructed. During the training stages, total 40 000 training cycles were performed and the minimum RMSE values were obtained at approximately 10 000th cycle. At this cycle, the obtained minimum RMSE value is 0.22 for the second training set, while that of value is calculated as 0.064 again for the second test set. Using the trained ANN model at 10 000th cycle for the second random sampling, the debris source area susceptibility map was produced and adjusted. Finally, a potential debris source susceptibility map for the study area was produced. When considering the field observations and existing inventory map, the produced map has a high prediction capacity and it can be used when assessing debris flow hazard mitigation efforts.

Modeling of the Stress in 13Cr Supermartensitic Stainless Steel Welds by Artificial Neural Network

2010 ◽  
Vol 658 ◽  
pp. 141-144 ◽  
Author(s):  
Jun Hui Yu ◽  
De Ning Zou ◽  
Ying Han ◽  
Zhi Yu Chen
Keyword(s):  
Stainless Steel ◽  
Correlation Coefficients ◽  
Tensile Tests ◽  
Training Dataset ◽  
Ann Model ◽  
Supermartensitic Stainless Steel ◽  
Absolute Relative Error ◽  
Feed Forward Network ◽  
Artificial Neural ◽  
Hidden Layer

In this paper, artificial neural networks (ANN) has been proposed to determine the stresses of 13Cr supermartensitic stainless steel (SMSS) welds based on various deformation temperatures and strains using experimental data from tensile tests. The experiments provided the required data for training and testing. A three layer feed-forward network, deformation temperature and strain as input parameters while stress as the output, was trained with automated regularization (AR) algorithm for preventing overfitting. The results showed that the best fitting training dataset was obtained with ten units in the hidden layer, which made it possible to predict stress accurately. The correlation coefficients (R-value) between experiments and prediction for the training and testing dataset were 0.9980 and 0.9943, respectively, the biggest absolute relative error (ARE) was 6.060 %. As seen that the ANN model was an efficient quantitative tool to evaluate and predict the deformation behavior of type 13Cr SMSS welds during tensile test under different temperatures and strains.

Application of artificial neural network for modeling of phenol mineralization by photo-Fenton process using a multi-lamp reactor

2013 ◽  
Vol 69 (4) ◽  
pp. 768-774 ◽  
Author(s):  
André L. N. Mota ◽  
Osvaldo Chiavone-Filho ◽  
Syllos S. da Silva ◽  
Edson L. Foletto ◽  
José E. F. Moraes ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Uv Light ◽  
Fenton Process ◽  
Ann Model ◽  
Ferrous Ions ◽  
Phenol Mineralization ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

An artificial neural network (ANN) was implemented for modeling phenol mineralization in aqueous solution using the photo-Fenton process. The experiments were conducted in a photochemical multi-lamp reactor equipped with twelve fluorescent black light lamps (40 W each) irradiating UV light. A three-layer neural network was optimized in order to model the behavior of the process. The concentrations of ferrous ions and hydrogen peroxide, and the reaction time were introduced as inputs of the network and the efficiency of phenol mineralization was expressed in terms of dissolved organic carbon (DOC) as an output. Both concentrations of Fe2+ and H2O2 were shown to be significant parameters on the phenol mineralization process. The ANN model provided the best result through the application of six neurons in the hidden layer, resulting in a high determination coefficient. The ANN model was shown to be efficient in the simulation of phenol mineralization through the photo-Fenton process using a multi-lamp reactor.

scholarly journals Prediction of Compressive Strength Behavior of Ground Bottom Ash Concrete by an Artificial Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Kraiwut Tuntisukrarom ◽  
Raungrut Cheerarot
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Bottom Ash ◽  
Strength Development ◽  
Ann Model ◽  
Explicit Equation ◽  
Strength Behavior ◽  
Artificial Neural ◽  
Hidden Layer

The objective of this work was to examine the compressive strength behavior of ground bottom ash (GBA) concrete by using an artificial neural network. Four input parameters, specifically, the water-to-binder ratio (WB), percentage replacement of GBA (PR), median particle size of GBA (PS), and age of concrete (AC), were considered for this prediction. The results indicated that all four considered parameters affect the strength development of concrete, and GBA with a high fineness can act as a good pozzolanic material. The optimal ANN model had an architecture with two hidden layers, with six neurons in the first hidden layer and one neuron in the second hidden layer. The proposed ANN-based explicit equation represented a highly accurate predictive model, for which the statistical values of R2 were higher than 0.996. Moreover, the compressive strength behavior determined using the optimal ANN model closely followed the trend lines and surface plots of the experimental results.

Sign in / Sign up

Export Citation Format

Share Document