The Met Office operational global ocean forecast system FOAM-ORCA12

2021 ◽  
Author(s):  
Ana Barbosa Aguiar ◽  
Jennifer Waters ◽  
Martin Price ◽  
Gordon Inverarity ◽  
Christine Pequignet ◽  
...  
Keyword(s):  
Computational Cost ◽  
Absolute Error ◽  
Global Ocean ◽  
Background Error ◽  
Verification Methods ◽  
Climate Simulations ◽  
Forecast Models ◽  
The Mean ◽  
Lower Continuous ◽  
Better Than

<div> <p>The importance of oceans for atmospheric forecasts as well as climate simulations is being increasingly recognised with the advent of coupled ocean / atmosphere forecast models. Having comparable resolutions in both domains maximises the benefits for a given computational cost. The Met Office has recently upgraded its operational global ocean-only model from an eddy permitting 1/4 degree tripolar grid (ORCA025) to the eddy resolving 1/12 degree ORCA12 configuration while retaining 1/4 degree data assimilation. </p> </div><div> <p>We will present a description of the ocean-only ORCA12 system, FOAM-ORCA12, alongside some initial results. Qualitatively, FOAM-ORCA12 seems to represent better (than FOAM-ORCA025) the details of mesoscale features in SST and surface currents. Overall, traditional statistical results suggest that the new FOAM-ORCA12 system performs similarly or slightly worse than the pre-existing FOAM-ORCA025. However, it is known that comparisons of models running at different resolutions suffer from a double penalty effect, whereby higher-resolution models are penalised more than lower-resolution models for features that are offset in time and space. Neighbourhood verification methods seek to make a fairer comparison using a common spatial scale for both models and it can be seen that, as neighbourhood sizes increase, ORCA12 consistently has lower continuous ranked probability scores (CRPS) than ORCA025. CRPS measures the accuracy of the pseudo-ensemble created by the neighbourhood method and generalises the mean absolute error measure for deterministic forecasts. </p> </div><div> <p>The focus over the next year will be on diagnosing the performance of both the model and assimilation. A planned development that is expected to enhance the system is the update of the background-error covariances used for data assimilation. </p> </div>

scholarly journals Day-Ahead Forecasting of Hourly Photovoltaic Power Based on Robust Multilayer Perception

2018 ◽  
Vol 10 (12) ◽  
pp. 4863 ◽  
Author(s):  
Chao Huang ◽  
Longpeng Cao ◽  
Nanxin Peng ◽  
Sijia Li ◽  
Jing Zhang ◽  
...  
Keyword(s):  
Power Plants ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Multilayer Perception ◽  
Squared Error ◽  
The Mean ◽  
Effectiveness And Efficiency ◽  
Mlp Network ◽  
Grid Operation ◽  
Better Than

Photovoltaic (PV) modules convert renewable and sustainable solar energy into electricity. However, the uncertainty of PV power production brings challenges for the grid operation. To facilitate the management and scheduling of PV power plants, forecasting is an essential technique. In this paper, a robust multilayer perception (MLP) neural network was developed for day-ahead forecasting of hourly PV power. A generic MLP is usually trained by minimizing the mean squared loss. The mean squared error is sensitive to a few particularly large errors that can lead to a poor estimator. To tackle the problem, the pseudo-Huber loss function, which combines the best properties of squared loss and absolute loss, was adopted in this paper. The effectiveness and efficiency of the proposed method was verified by benchmarking against a generic MLP network with real PV data. Numerical experiments illustrated that the proposed method performed better than the generic MLP network in terms of root mean squared error (RMSE) and mean absolute error (MAE).

scholarly journals Prediction by using Artificial Neural Networks and Box-Jenkins methodologies: Comparison Study

2017 ◽  
Vol 9 (2) ◽  
Author(s):  
Mohammed Habib Al- Sharoot ◽  
Emaan Yousif Abdoon
Keyword(s):  
Neural Networks ◽  
Exchange Rate ◽  
Absolute Error ◽  
Percentage Error ◽  
Neural Network Approach ◽  
Decision Making Processes ◽  
The Mean ◽  
Us Dollar ◽  
Stable Economy ◽  
Better Than

The variations in exchange rate, especially the sudden unexpected increases and decreases, have significant impact on the national economy of any country. Iraq is no exception; therefore, the accurate forecasting of exchange rate of Iraqi dinar to US dollar plays an important role in the planning and decision-making processes as well as the maintenance of a stable economy in Iraq. This research aims to compare Box-Jenkins methodology to neural networks in terms of forecasting the exchange rate of Iraqi dinar to US dollar based on data provided by the Iraqi Central Bank for the period  30/01/2004 and 30/12/2014. Based on the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the Mean Absolute Percentage Error (MAPE) as criteria to compare the two methodologies, it was concluded that Box-Jenkins is better than neural network approach in forecasting.

A Fast-Converging Ensemble Infilling Approach Balancing Global Exploration and Local Exploitation: The Go-Inspired Hybrid Infilling Strategy

2019 ◽  
Vol 142 (2) ◽  
Author(s):  
Liye Lv ◽  
Maolin Shi ◽  
Xueguan Song ◽  
Wei Sun ◽  
Jie Zhang
Keyword(s):  
Adaptive Sampling ◽  
Computational Cost ◽  
Expected Improvement ◽  
Sampling Strategies ◽  
Key Factors ◽  
Engineering Problems ◽  
The Mean ◽  
Global And Local ◽  
Probability Of Improvement ◽  
Better Than

AbstractInfilling strategies have been proposed for decades and are widely used in engineering problems. It is still challenging to achieve an effective trade-off between global exploration and local exploitation. In this paper, a novel decision-making infilling strategy named the Go-inspired hybrid infilling (Go-HI) strategy is proposed. The Go-HI strategy combines multiple individual infilling strategies, such as the mean square error (MSE), expected improvement (EI), and probability of improvement (PoI) strategies. The Go-HI strategy consists of two major parts. In the first part, a tree-like structure consisting of several subtrees is built. In the second part, the decision value for each subtree is calculated using a cross-validation (CV)-based criterion. Key factors that significantly influence the performance of the Go-HI strategy, such as the number of component infilling strategies and the tree depth, are explored. Go-HI strategies with different component strategies and tree depths are investigated and also compared with four baseline adaptive sampling strategies through three numerical functions and one engineering case. Results show that the number of component infilling strategies exerts a larger influence on the global and local performance than the tree depth; the Go-HI strategy with two component strategies performs better than the ones with three; the Go-HI strategy always outperforms the three component infilling strategies and the other four benchmark strategies in global performance and robustness and saves much computational cost.

scholarly journals Validation of MODIS C6.1 and MERRA-2 AOD Using AERONET Observations: A Comparative Study over Turkey

Atmosphere ◽  
2020 ◽  
Vol 11 (9) ◽  
pp. 905
Author(s):  
Midyan Aldabash ◽  
Filiz Bektas Balcik ◽  
Paul Glantz
Keyword(s):  
Absolute Error ◽  
Coefficient Of Determination ◽  
Space Agency ◽  
Moderate Resolution ◽  
Resolution Imaging ◽  
The Mean ◽  
Moderate Resolution Imaging Spectroradiometer ◽  
Modern Era ◽  
Relative Root ◽  
Better Than

This study validated MODIS (Moderate Resolution Imaging Spectroradiometer) of the National Aeronautics and Space Agency, USA, Aqua and Terra Collection 6.1, and MERRA-2 (Modern-ERA Retrospective Analysis for Research and Application) Version 2 of aerosol optical depth (AOD) at 550 nm against AERONET (Aerosol Robotic Network) ground-based sunphotometer observations over Turkey. AERONET AOD data were collected from three sites during the period between 2013 and 2017. Regression analysis showed that overall, seasonally and daily statistics of MODIS are better than MERRA-2 by the mean of coefficient of determination (R2), mean absolute error (MAE), and relative root mean square deviation (RMSDrel). MODIS combined Terra/Aqua AOD and MERRA-2 AOD corresponding to morning and noon hours resulted in better results than individual sub datasets. A clear annual cycle in AOD was detected by the three platforms. However, overall, MODIS and MERRA-2 tend to overestimate and underestimate AOD, respectively, in comparison with AERONET. MODIS showed higher efficiency in detecting extreme events than MERRA-2. There was no clear relation found between the accuracy in MODIS/MERRA-2 AOD and surface relative humidity (RH).

The Effectiveness of Alternative Preference Elicitation Procedures in Predicting Choice

1993 ◽  
Vol 30 (1) ◽  
pp. 105-114 ◽  
Author(s):  
Joel Huber ◽  
Dick R. Wittink ◽  
John A. Fiedler ◽  
Richard Miller
Keyword(s):  
Large Scale ◽  
Absolute Error ◽  
Accurate Method ◽  
Preference Elicitation ◽  
National Study ◽  
Relative Preference ◽  
Full Profile ◽  
The Mean ◽  
Combining Information ◽  
Better Than

In a large-scale national study, the authors evaluated the effectiveness of several preference elicitation techniques for predicting choices. The criteria for accuracy included both individual hit rates and a new measure, the mean absolute error predicting aggregate share using a logit choice simulator. The central finding is that hybrid models combining information from different preference elicitation tasks consistently outperform models based on one task. For example, ACA, a method that combines a self-explicated prior with relative preference measures on pairs, predicts choices better than full-profile conjoint when warmup tasks are lacking. However, there is no difference between the models if ACA's prior is combined with the full-profile information. Further, the most accurate method combines data from all three sources, suggesting that each preference elicitation technique taps a different aspect of the choice process in the validation task. Finally, full-profile conjoint is found to be significantly more accurate after rather than before, other preference elicitation tasks, implying that its performance can be improved with warmup exercises.

scholarly journals Statistical Models in Estimating Air Temperature in a Mountainous Region of Greece

2017 ◽  
Vol 12 (3) ◽  
pp. 544-549 ◽  
Author(s):  
Stelios Maniatis ◽  
Kostas Chronopoulos ◽  
Aristidis Matsoukis ◽  
Athanasios Kamoutsis
Keyword(s):  
Air Temperature ◽  
Statistical Models ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Multi Layer Perceptron ◽  
Simple Linear Regression ◽  
The Mean ◽  
Of Greece ◽  
Better Than

The current work focuses on the estimation of air temperature (T) conditions in two high altitude (alt) sites (1580 m), each one at different orientation (southeast and northwest) in the mountain (Mt) Aenos in the island of Cephalonia, Greece, by using two well-known statistical models, simple linear regression (SLR) and multi-layer perceptron ( MLP), one of the most commonly used artificial neural networks. More specifically, the estimation of mean, maximum and minimum T in high alt sites was based on the respective T data of two lower alt sites (1100 m), the first at southeast and the second at northwest orientations, and was carried out separately for each orientation. The performance of both SLR and MLP models was evaluated by the coefficient of determination (R2) and the Mean Absolute Error (MAE). Results showed that the examined models (SLR and MLP) provided very satisfactory results with regard to the estimation of mean, maximum and minimum T, regarding southeast orientation (R2 ranging from 0.96 to 0.98), with mean T estimation being relatively better, as confirmed by the lowest MAE (0.83). Regarding northwest orientation, T estimation was less accurate (lower R2 and higher MAE), compared to the respective estimation of southeast orientation, but, the results were considered adequate (R2 and MAE ranging from 0.88 to 0.92 and 1.00 to 1.40, respectively). In general, the estimations of the mean T were better than those of the extreme ones (minimum and maximum T). In addition, better results (higher R2 and lower, in general, MAE) were obtained when T estimations were based on T data derived from sites located at areas with similar surroundings, as in the case of dense and tall vegetation of the sites at southeast orientation, irrespective of applied method.

SVR Model for Prediction of Incidence Influenza Based on Automated Method

2014 ◽  
Vol 926-930 ◽  
pp. 1159-1163
Author(s):  
Jia Song
Keyword(s):  
Mean Absolute Error ◽  
Absolute Error ◽  
Public Health Issue ◽  
Support Vector ◽  
Automated Method ◽  
Significant Public Health ◽  
The Mean ◽  
Single Support Vector Machine ◽  
Absolute Percent Error ◽  
Better Than

As is a significant public health issue to predict the incidence of influenza, this paper present a supported vector regression (SVR) model based on an automated method which worked as the following steps: firstly, the automated method is used to select the texts which highly related to the influenza, and then the SVR algorithm will find out the nonlinear between each context. According to the result, when assessing by the root mean squared predict error, the mean absolute error and the mean absolute percent error of the whole system, the SVR performed much better than single support vector machine regression prediction. Also, the validity of this method is verified.

scholarly journals Bats: An Appliance Safety Hazards Factors Detection Algorithm with an Improved Nonintrusive Load Disaggregation Method

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3547
Author(s):  
Wei Wang ◽  
Zilin Wang ◽  
Yanru Chen ◽  
Min Guo ◽  
Zhengyu Chen ◽  
...  
Keyword(s):  
Sparse Coding ◽  
Absolute Error ◽  
Detection Algorithm ◽  
Safety Hazards ◽  
Safety Hazard ◽  
Potential Safety ◽  
Load Disaggregation ◽  
The Mean ◽  
The Internet Of Things ◽  
Better Than

In an electrical safe microenvironment, all kinds of electrical appliances can be operated safely to ensure the safety of life and property. The significance of safety hazard factors detection is to detect safety hazards in advance, to remind the administrators to exclude risk, to reduce the unnecessary loss, and to ensure that the electrical operation is healthy and orderly before the occurrence of accidents. In this paper, batteries are selected as the primary research subject of safety detection because batteries are used more and more in the Internet of Things (IOT), and they often cause fire in the process of discharging and charging. The existing algorithms need to be embedded into the specialized sensor for each important electrical appliance. However, they are limited by the actual deployment, so it is extremely difficult to spread widely. According to the opinions above, an improved load disaggregation algorithm based on dictionary learning and sparse coding with optimal dictionary matrix period is proposed to detect potential safety hazards of battery loads. For safety-related electrical applications, doing so can increase interpretability. Through experiments, we test this algorithm on the REDD dataset, and compare it with the baseline algorithms (combinatorial optimization, factorial hidden Markov model, basic discriminative dictionary sparse coding algorithm) to achieve a degree of trust. The Mean Absolute Error (MAE) value is 8.26, which drops by 70%. The Root Mean Square Error (RMSE) value is 97.75, which is also better than those baseline algorithms.

scholarly journals An Adaptive Compensatory Approach of the Fixed Localization in the EnKF

2015 ◽  
Vol 143 (11) ◽  
pp. 4714-4735 ◽  
Author(s):  
Xinrong Wu ◽  
Wei Li ◽  
Guijun Han ◽  
Lianxin Zhang ◽  
Caixia Shao ◽  
...  
Keyword(s):  
Multiscale Analysis ◽  
General Circulation ◽  
Computational Cost ◽  
Circulation Model ◽  
Adaptive Method ◽  
Background Error ◽  
Error Covariance ◽  
Incremental Improvement ◽  
Better Than

Abstract Although the fixed covariance localization in the ensemble Kalman filter (EnKF) can significantly increase the reliability of background error covariance, it has been demonstrated that extreme impact radii can cause the EnKF to lose some useful information. Tuning an optimal impact radius, on the other hand, is always difficult for a general circulation model. The EnKF multiscale analysis (MSA) approach was presented to make up for the above-mentioned drawback of the fixed localization. As a follow-up, this study presents an adaptive compensatory approach to further improve the performance of the EnKF-MSA. The new method adaptively triggers a multigrid analysis (MGA) to extract multiscale information from the observational residual after the EnKF without inflation is completed at each analysis step. Within a biased twin experiment framework consisting of a barotropic spectral model and an idealized observing system, the performance of the adaptive method is examined. Results show that the MGA reduces the computational cost of the MSA by 93%. On the assimilation quality, the adaptive method has an incremental improvement over the EnKF-MSA. That is, the adaptive EnKF-MGA reduces to the EnKF without inflation, which is better than the EnKF-MSA, for moderate impact radii. The proposed scheme works for a broader range of impact radii than the standard EnKF (i.e., the EnKF with inflation). For extreme impact radii, the adaptive EnKF-MGA can produce smaller assimilation errors than the standard EnKF and shorten the spinup period by 53%. In addition, the computational cost of the MGA is negligible relative to that of the standard EnKF.

scholarly journals Forecasting Daily and Monthly Reference Evapotranspiration in the Aidoghmoush Basin Using Multilayer Perceptron Coupled with Water Wave Optimization

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Fatemeh Sayyahi ◽  
Saeed Farzin ◽  
Hojat Karami
Keyword(s):  
Multilayer Perceptron ◽  
Water Wave ◽  
Reference Evapotranspiration ◽  
Mean Absolute Error ◽  
Principal Component ◽  
Absolute Error ◽  
Swarm Optimization ◽  
The Mean ◽  
Better Than ◽  
Computing Models

The aim of this study is to evaluate the ability of soft computing models including multilayer perceptron- (MLP-) water wave optimization (MLP-WWO), MLP-particle swarm optimization (MLP-PSO), and MLP-genetic algorithm (MLP-GA), to simulate the daily and monthly reference evapotranspiration (ET) at the Aidoghmoush basin (Iran). Principal component analysis (PCA) was used to find the best input combination including the lagged ETs. According to the results, the ET values with 1, 2, and 3 (days) lags as well as those with 1, 2, and 3 (months) lags were the most effective variables in the formation of the PCs. The total variance proportion of inputs and eigenvalues was used to identify the most important variables. The accuracy of the models was assessed based on multiple statistical indices such as the mean absolute error (MAE), Nash–Sutcliff efficiency (NSE), and percent bias (PBIAS). The results showed that the performance of hybrid MLP models was better than that of the standalone MLP. The findings confirmed that the MLP-WWO could precisely predict ET.

Sign in / Sign up

Export Citation Format

Share Document