scholarly journals Identifying the Sensitivity of Ensemble Streamflow Prediction by Artificial Intelligence

Water ◽  
2018 ◽  
Vol 10 (10) ◽  
pp. 1341 ◽  
Author(s):  
Yen-Ming Chiang ◽  
Ruo-Nan Hao ◽  
Jian-Quan Zhang ◽  
Ying-Tien Lin ◽  
Wen-Ping Tsai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Model ◽  
Global Climate ◽  
Bayesian Model Average ◽  
Streamflow Prediction ◽  
Arithmetic Average ◽  
Model Average ◽  
Sustainable Water Resources Management ◽  
Ensemble Streamflow Prediction

Sustainable water resources management is facing a rigorous challenge due to global climate change. Nowadays, improving streamflow predictions based on uneven precipitation is an important task. The main purpose of this study is to integrate the ensemble technique concept into artificial neural networks for reducing model uncertainty in hourly streamflow predictions. The ensemble streamflow predictions are built following two steps: (1) Generating the ensemble members through disturbance of initial weights, data resampling, and alteration of model structure; (2) consolidating the model outputs through the arithmetic average, stacking, and Bayesian model average. This study investigates various ensemble strategies on two study sites, where the watershed size and hydrological conditions are different. The results help to realize whether the ensemble methods are sensitive to hydrological or physiographical conditions. Additionally, the applicability and availability of the ensemble strategies can be easily evaluated in this study. Among various ensemble strategies, the best ESP is produced by the combination of boosting (data resampling) and Bayesian model average. The results demonstrate that the ensemble neural networks greatly improved the accuracy of streamflow predictions as compared to a single neural network, and the improvement made by the ensemble neural network is about 19–37% and 20–30% in Longquan Creek and Jinhua River watersheds, respectively, for 1–3 h ahead streamflow prediction. Moreover, the results obtained from different ensemble strategies are quite consistent in both watersheds, indicating that the ensemble strategies are insensitive to hydrological and physiographical factors. Finally, the output intervals of ensemble streamflow prediction may also reflect the possible peak flow, which is valuable information for flood prevention.

scholarly journals ENSURF: multi-model sea level forecast – implementation and validation results for the IBIROOS and Western Mediterranean regions

Ocean Science ◽  
2012 ◽  
Vol 8 (2) ◽  
pp. 211-226 ◽  
Author(s):  
B. Pérez ◽  
R. Brouwer ◽  
J. Beckers ◽  
D. Paradis ◽  
C. Balseiro ◽  
...  
Keyword(s):  
Real Time ◽  
Sea Level ◽  
Bayesian Model ◽  
Weighted Average ◽  
Western Mediterranean ◽  
Bayesian Model Average ◽  
Easy Access ◽  
Visualization Tool ◽  
Average Technique ◽  
Model Average

Abstract. ENSURF (Ensemble SURge Forecast) is a multi-model application for sea level forecast that makes use of several storm surge or circulation models and near-real time tide gauge data in the region, with the following main goals: 1. providing easy access to existing forecasts, as well as to its performance and model validation, by means of an adequate visualization tool; 2. generation of better forecasts of sea level, including confidence intervals, by means of the Bayesian Model Average technique (BMA). The Bayesian Model Average technique generates an overall forecast probability density function (PDF) by making a weighted average of the individual forecasts PDF's; the weights represent the Bayesian likelihood that a model will give the correct forecast and are continuously updated based on the performance of the models during a recent training period. This implies the technique needs the availability of sea level data from tide gauges in near-real time. The system was implemented for the European Atlantic facade (IBIROOS region) and Western Mediterranean coast based on the MATROOS visualization tool developed by Deltares. Results of validation of the different models and BMA implementation for the main harbours are presented for these regions where this kind of activity is performed for the first time. The system is currently operational at Puertos del Estado and has proved to be useful in the detection of calibration problems in some of the circulation models, in the identification of the systematic differences between baroclinic and barotropic models for sea level forecasts and to demonstrate the feasibility of providing an overall probabilistic forecast, based on the BMA method.

scholarly journals Forecasting International Sugar Prices: A Bayesian Model Average Analysis

Sugar Tech ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. 552-562
Author(s):  
El Mamoun Amrouk ◽  
Thomas Heckelei
Keyword(s):  
Bayesian Model ◽  
Bayesian Model Average ◽  
Model Average ◽  
Average Analysis

scholarly journals CÁC YẾU TỐ KINH TẾ VĨ MÔ TÁC ĐỘNG ĐẾN GIẢM NGHÈO Ở LÂM ĐỒNG

2017 ◽  
Vol 7 (1) ◽  
pp. 109
Author(s):  
Hồ Quang Thanh ◽  
Hoàng Trọng Vinh ◽  
Trần Tuấn
Keyword(s):  
Bayesian Model ◽  
Bayesian Model Average ◽  
Model Average

Nghiên cứu này xem xét các yếu tố kinh tế vĩ mô tác động đến giảm nghèo của tỉnh Lâm Đồng, được xác định trên cơ sở xây dựng mô hình hồi qui bội tối ưu bằng phương pháp BMA (Bayesian Model Average) dựa vào kết quả các chỉ số về thu nhập, thất nghiệp (việc làm), lạm phát và chất lượng nguồn nhân lực tại Lâm Đồng. Kết quả nghiên cứu đã tìm thấy 2 yếu tố quan trọng, có ý nghĩa thống kê và giá trị thực tiễn tác động đến giảm nghèo của tỉnh Lâm Đồng theo mức độ tầm quan trọng của từng trọng số, đó là: Thu nhập bình quân và Chất lượng nguồn nhân lực. Cuối cùng tác giả trình bày hàm ý và khuyến nghị một số giải pháp từ kết quả nghiên cứu.

scholarly journals Average Method of Mixed Sampling Distribution Bayesian Model

2018 ◽  
Vol 228 ◽  
pp. 01002
Author(s):  
Ying Zhang
Keyword(s):  
Bayesian Estimation ◽  
Prior Distribution ◽  
Bayesian Model ◽  
Average Method ◽  
Sampling Distribution ◽  
Bayesian Model Average ◽  
Econometric Modeling ◽  
Parametric Form ◽  
Model Average ◽  
Better Than

Based on the study of Bayesian model average (BMA), this paper proposes to mix the prior distribution and sampling distribution to obtain the average method of the mixed sampling distribution Bayesian model overcoming the problem that traditional econometric modeling method does not explicitly consider the uncertainty of the model. If all the alternative models have the same parametric form, then the new Bayesian estimation will degenerate into the BMA estimator. The empirical results show that the method is better than Bayesian model average.

scholarly journals Enabling Training of Neural Networks on Noisy Hardware

2021 ◽  
Vol 4 ◽  
Author(s):  
Tayfun Gokmen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Model Averaging ◽  
Model Averaging ◽  
Stochastic Gradient Descent ◽  
Test Accuracy ◽  
Noise Tolerance ◽  
Model Average ◽  
The Neural Network ◽  
Analog Arrays

Deep neural networks (DNNs) are typically trained using the conventional stochastic gradient descent (SGD) algorithm. However, SGD performs poorly when applied to train networks on non-ideal analog hardware composed of resistive device arrays with non-symmetric conductance modulation characteristics. Recently we proposed a new algorithm, the Tiki-Taka algorithm, that overcomes this stringent symmetry requirement. Here we build on top of Tiki-Taka and describe a more robust algorithm that further relaxes other stringent hardware requirements. This more robust second version of the Tiki-Taka algorithm (referred to as TTv2) 1. decreases the number of device conductance states requirement from 1000s of states to only 10s of states, 2. increases the noise tolerance to the device conductance modulations by about 100x, and 3. increases the noise tolerance to the matrix-vector multiplication performed by the analog arrays by about 10x. Empirical simulation results show that TTv2 can train various neural networks close to their ideal accuracy even at extremely noisy hardware settings. TTv2 achieves these capabilities by complementing the original Tiki-Taka algorithm with lightweight and low computational complexity digital filtering operations performed outside the analog arrays. Therefore, the implementation cost of TTv2 compared to SGD and Tiki-Taka is minimal, and it maintains the usual power and speed benefits of using analog hardware for training workloads. Here we also show how to extract the neural network from the analog hardware once the training is complete for further model deployment. Similar to Bayesian model averaging, we form analog hardware compatible averages over the neural network weights derived from TTv2 iterates. This model average then can be transferred to another analog or digital hardware with notable improvements in test accuracy, transcending the trained model itself. In short, we describe an end-to-end training and model extraction technique for extremely noisy crossbar-based analog hardware that can be used to accelerate DNN training workloads and match the performance of full-precision SGD.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

Sign in / Sign up

Export Citation Format

Share Document