scholarly journals Enhanced Neural Network Model for Worldwide Estimation of Weighted Mean Temperature

2021 ◽  
Vol 13 (12) ◽  
pp. 2405
Author(s):  
Fengyang Long ◽  
Chengfa Gao ◽  
Yuxiang Yan ◽  
Jinling Wang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Model Performance ◽  
Global Scale ◽  
Radiosonde Data ◽  
Model Parameters ◽  
Measured Temperature ◽  
Weighted Mean ◽  
Weighted Mean Temperature ◽  
Application Scope

Precise modeling of weighted mean temperature (Tm) is critical for realizing real-time conversion from zenith wet delay (ZWD) to precipitation water vapor (PWV) in Global Navigation Satellite System (GNSS) meteorology applications. The empirical Tm models developed by neural network techniques have been proved to have better performances on the global scale; they also have fewer model parameters and are thus easy to operate. This paper aims to further deepen the research of Tm modeling with the neural network, and expand the application scope of Tm models and provide global users with more solutions for the real-time acquisition of Tm. An enhanced neural network Tm model (ENNTm) has been developed with the radiosonde data distributed globally. Compared with other empirical models, the ENNTm has some advanced features in both model design and model performance, Firstly, the data for modeling cover the whole troposphere rather than just near the Earth’s surface; secondly, the ensemble learning was employed to weaken the impact of sample disturbance on model performance and elaborate data preprocessing, including up-sampling and down-sampling, which was adopted to achieve better model performance on the global scale; furthermore, the ENNTm was designed to meet the requirements of three different application conditions by providing three sets of model parameters, i.e., Tm estimating without measured meteorological elements, Tm estimating with only measured temperature and Tm estimating with both measured temperature and water vapor pressure. The validation work is carried out by using the radiosonde data of global distribution, and results show that the ENNTm has better performance compared with other competing models from different perspectives under the same application conditions, the proposed model expanded the application scope of Tm estimation and provided the global users with more choices in the applications of real-time GNSS-PWV retrival.

scholarly journals CONSTRUCTION OF REGIONAL WEIGHTED MEAN TEMPERATURE MODEL BASED ON OPTIMIZATION BP NEURAL NETWORK

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 1099-1105
Author(s):  
Z. X. Chen ◽  
L. L. Liu ◽  
L. K. Huang ◽  
Q. T. Wan ◽  
X. Q. Mo
Keyword(s):  
Neural Network ◽  
Water Vapor ◽  
Bp Neural Network ◽  
Precipitable Water ◽  
Precipitable Water Vapor ◽  
Radiosonde Data ◽  
Weighted Mean ◽  
Mean Temperature ◽  
Weighted Mean Temperature ◽  
Single Station

Abstract. The tropospheric weighted mean temperature (Tm) is one of the key characteristic parameters in the troposphere, which plays an important role in the conversion of Zenith Wet Delay (ZWD) to atmospheric Precipitable Water Vapor (PWV). The precision of Global Navigation Satellite System (GNSS) inversion of PWV can be significantly improved with the accurate calculation of Tm. Due to the strong nonlinear mapping ability of Back Propagation (BP) neural network, the algorithm can be used to excavate the law with massive data. In term of the nonlinear and non-stationary characteristics of GNSS precipitable water vapor, in this paper, we proposes a forecast method of GNSS precipitable water vapor based on BP neural network, which can modelling the weighted mean temperature of troposphere. The traditional BP neural network has some shortcomings, such as large amount of calculation, long training time and easy to appear “over-fitting” phenomenon and so on. In order to optimize the deficiency and numerical simulation, the three characteristic values include water vapor pressure, surface pressure and surface temperature provided are selected as input parameters, named as BP_Tm. The optimal initialization parameters of the model were obtained from the 2016 radiosonde data of 89 radiosonde stations in China, and the modeling and accuracy verification were conducted with the 2017 radiosonde data，and the accuracy of the new model was compared with the common regional Tm model. The results show the BP_Tm model has good simulation accuracy, the average deviation is −0.186K, and the root mean square error is 3.144K. When simulating the weighted mean temperature of a single station, the accuracy of the four models to simulate Tm is compared and analyzed, which the BP_Tm model can obtain good accuracy and reflect better stability and reliability.

A new hybrid model combining EMD and neural network for multi-step ahead load forecasting

2021 ◽  
pp. 1-16
Author(s):  
Hasmat Malik ◽  
Majed A. Alotaibi ◽  
Abdulaziz Almutairi
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Hybrid Model ◽  
Storage System ◽  
Load Forecasting ◽  
Model Performance ◽  
Energy Storage System ◽  
Electric Load ◽  
Real Time Analysis ◽  
Model Combining

The electric load forecasting (ELF) is a key area of the modern power system (MPS) applications and also for the virtual power plant (VPP) analysis. The ELF is most prominent for the distinct applications of MPS and VPP such as real-time analysis of energy storage system, distributed energy resources, demand side management and electric vehicles etc. To manage the real-time challenges and map the stable power demand, in different time steps, the ELF is evaluated in yearly, monthly, weekly, daily, and hourly, etc. basis. In this study, an intelligent load predictor which is able to forecast the electric load for next month or day or hour is proposed. The proposed approach is a hybrid model combining empirical mode decomposition (EMD) and neural network (NN) for multi-step ahead load forecasting. The model performance is demonstrated by suing historical dataset collected form GEFCom2012 and GEFCom2014. For the demonstration of the performance, three case studies are analyzed into two categories. The demonstrated results represents the higher acceptability of the proposed approach with respect to the standard value of MAPE (mean absolute percent error).

scholarly journals Real-time updating of HEC-RAS model for streamflow forecasting using an optimization algorithm

RBRH ◽  
2016 ◽  
Vol 21 (4) ◽  
pp. 855-870 ◽  
Author(s):  
Vinícius Alencar Siqueira ◽  
Mino Viana Sorribas ◽  
Juan Martin Bravo ◽  
Walter Collischonn ◽  
Auder Machado Vieira Lisboa ◽  
...  
Keyword(s):  
Real Time ◽  
Optimization Algorithm ◽  
Expert Knowledge ◽  
Model Performance ◽  
Small Population ◽  
Model Parameters ◽  
Streamflow Forecasting ◽  
Negative Effects ◽  
Shuffled Complex Evolution ◽  
Updating Procedure

ABSTRACT Real-time updating of channel flow routing models is essential for error reduction in hydrological forecasting. Recent updating techniques found in scientific literature, although very promising, are complex and often applied in models that demand much time and expert knowledge for their development, posing challenges for using in an operational context. Since powerful and well-known computational tools are currently available, which provide easy-to-use and less time-consuming platforms for preparation of hydrodynamic models, it becomes interesting to develop updating techniques adaptable to such tools, taking full advantage of previously calibrated models as well as the experience of the users. In this work, we present a real-time updating procedure for streamflow forecasting in HEC-RAS model, using the Shuffled Complex Evolution - University of Arizona (SCE-UA) optimization algorithm. The procedure consists in a simultaneous correction of boundary conditions and model parameters through: (i) generation of a lateral inflow, based on Soil Conservation Service (SCS) dimensionless unit hydrograph and; (ii) estimation of Manning roughness in the river channel. The algorithm works in an optimization window in order to minimize an objective function, given by the weighted sum of squared errors between simulated and observed flows where differences in later intervals (start of forecast) are more penalized. As a case study, the procedure was applied in a river reach between Salto Caxias dam and Hotel Cataratas stream gauge, located in the Lower Iguazu Basin. Results showed that, with a small population of candidate solutions in the optimization algorithm, it is possible to efficiently improve the model performance for streamflow forecasting and reduce negative effects caused by lag errors in simulation. An advantage of the developed procedure is the reduction of both excessive handling of external files and manual adjustments of HEC-RAS model, which is important when operational decisions must be taken in relatively short times.

scholarly journals A Regional Model for Predicting Tropospheric Delay and Weighted Mean Temperature in China Based on GRAPES_MESO Forecasting Products

2021 ◽  
Vol 13 (13) ◽  
pp. 2644
Author(s):  
Liying Cao ◽  
Bao Zhang ◽  
Junyu Li ◽  
Yibin Yao ◽  
Lilong Liu ◽  
...  
Keyword(s):  
Empirical Models ◽  
Radiosonde Data ◽  
Tropospheric Delay ◽  
In Situ Observation ◽  
Weighted Mean ◽  
Gnss Positioning ◽  
Gnss Meteorology ◽  
Mean Temperature ◽  
Weighted Mean Temperature ◽  
Gpt2w Model

Accurate tropospheric delay (TD) and weighted mean temperature (Tm) are important for Global Navigation Satellite System (GNSS) positioning and GNSS meteorology. For this purpose, plenty of empirical models have been built to provide estimates of TD and Tm. However, these models cannot resolve TD and Tm variations at synoptic timescales since they only model the average annual, semi-annual, and/or daily variations. As a result, the existed empirical models cannot perform well under extreme weather conditions. To address this limitation, we propose to estimate Zenith Hydrostatic Delay (ZHD), Zenith Wet Delay (ZWD), and Tm directly from the stratified numerical weather forecasting products of the mesoscale version of the Global/Regional Assimilation and PrEdiction System (GRAPES_MESO) of China. The GRAPES_MESO forecasting data has a temporal resolution of 3 h, which provides the opportunity to resolve the synoptic variation. However, it is found that the estimated ZWD and Tm exhibit apparent systematic deviation from in situ observation-based estimates, which is due to the inherent biases in the GRAPES_MESO data. To solve this problem, we propose to correct these biases using a linear model and a spherical cap harmonic model. The estimates after correction are termed as the “CTropGrid” products. When validated by the radiosonde data, the CTropGrid product has biases of 1.5 mm, −0.7 mm, and −0.1 K, and Root Mean Square (RMS) error of 8.9 mm, 20.2 mm, and 1.5 K for ZHD, ZWD, and Tm. Compared to the widely used GPT2w model, the CTropGrid products have improved the accuracies of ZHD, ZWD, and Tm by 11.9%, 55.6%, and 60.5% in terms of RMS. When validating the Zenith Tropospheric Delay (ZTD) products (the sum of ZHD and ZWD) using the IGS ZTD data, the CTropGrid ZTD has a bias of −0.7 mm and an RMS of 35.8 mm, which is 22.7% better than the GPT2w model in terms of RMS. Besides the accuracy improvements, the CTropGrid products well model the synoptic-scale variations of ZHD, ZWD, and Tm. Compared to the existing empirical models that only capture the tidal (seasonal and/or diurnal) variations, the CTropGrid products capture well the non-tidal variations of ZHD, ZWD, and Tm, which enhances the tropospheric delay corrections and GNSS water vapor monitoring at synoptic timescales. Therefore, the CTropGrid product is an important progress in GNSS positioning and GNSS meteorology.

scholarly journals A dynamic neural network model for predicting risk of Zika in real-time

2018 ◽  
Author(s):  
Mahmood Akhtar ◽  
Moritz U.G. Kraemer ◽  
Lauren M. Gardner
Keyword(s):  
Public Health ◽  
Neural Network ◽  
Real Time ◽  
Network Model ◽  
Neural Network Model ◽  
Model Performance ◽  
Air Travel ◽  
Risk Indicator ◽  
Modeling Framework ◽  
Dynamic Neural Network

AbstractBackgroundIn 2015 the Zika virus spread from Brazil throughout the Americas, posing an unprecedented challenge to the public health community. During the epidemic, international public health officials lacked reliable predictions of the outbreak’s expected geographic scale and prevalence of cases, and were therefore unable to plan and allocate surveillance resources in a timely and effective manner.MethodsIn this work we present a dynamic neural network model to predict the geographic spread of outbreaks in real-time. The modeling framework is flexible in three main dimensions i) selection of the chosen risk indicator, i.e., case counts or incidence rate, ii) risk classification scheme, which defines the high risk group based on a relative or absolute threshold, and iii) prediction forecast window (one up to 12 weeks). The proposed model can be applied dynamically throughout the course of an outbreak to identify the regions expected to be at greatest risk in the future.ResultsThe model is applied to the recent Zika epidemic in the Americas at a weekly temporal resolution and country spatial resolution, using epidemiological data, passenger air travel volumes, vector habitat suitability, socioeconomic and population data for all affected countries and territories in the Americas. The model performance is quantitatively evaluated based on the predictive accuracy of the model. We show that the model can accurately predict the geographic expansion of Zika in the Americas with the overall average accuracy remaining above 85% even for prediction windows of up to 12 weeks.ConclusionsSensitivity analysis illustrated the model performance to be robust across a range of features. Critically, the model performed consistently well at various stages throughout the course of the outbreak, indicating its potential value at any time during an epidemic. The predictive capability was superior for shorter forecast windows, and geographically isolated locations that are predominantly connected via air travel. The highly flexible nature of the proposed modeling framework enables policy makers to develop and plan vector control programs and case surveillance strategies which can be tailored to a range of objectives and resource constraints.

Artificial neural network for improving the estimation of weighted mean temperature in Egypt

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Mohamed Amin Abdelfatah
Keyword(s):  
Meteorological Data ◽  
Precipitable Water ◽  
Empirical Models ◽  
Radiosonde Data ◽  
Location Information ◽  
Site Location ◽  
Weighted Mean ◽  
Mean Temperature ◽  
Weighted Mean Temperature ◽  
One Year

Abstract One of the most important parameters in meteorological data is the Precipitable Water Vapor (PWV). It can be measured by radiosonde stations (RS), but the fact is that RS are not available in all times. Therefore, GNSS satellite signals are considered an accurate function to compute it within a conversation factor. The conversation factor depends on the weighted mean temperature ( T m {T_{m}} ) which is non-measurable. In this research, a new idea to estimate T m {T_{m}} is provided, which can potentially contribute to the GNSS meteorology. The T m {T_{m}} was designed, including six RS, over one year in Egypt as input parameters. The machine learning (ML) model has been utilized in the design (IBM SPSS Statistics 25 package). The new model needs to collect the day of year (DOY), site location information and surface temperature to predict the T m {T_{m}} . The results of ML model and four other empirical models (Bevis et al., Wayan and Iskanda, Yao and Elhaty et al. models) are compared. The validation work is carried out, using the radiosonde data, and results indicate that the new T m {T_{m}} model can achieve the best performance with RMS of 1.7 K.

scholarly journals Real time flood forecasting in the Upper Danube basin

2016 ◽  
Vol 64 (4) ◽  
pp. 404-414 ◽  
Author(s):  
Thomas Nester ◽  
Jürgen Komma ◽  
Günter Blöschl
Keyword(s):  
Real Time ◽  
Model Performance ◽  
Flood Forecasting ◽  
Model Parameters ◽  
Runoff Generation ◽  
Danube Basin ◽  
Runoff Forecasting ◽  
Forecast Lead Time ◽  
Forecasting Errors ◽  
Runoff Model

Abstract This paper reports on experience with developing the flood forecasting model for the Upper Danube basin and its operational use since 2006. The model system consists of hydrological and hydrodynamic components, and involves precipitation forecasts. The model parameters were estimated based on the dominant processes concept. Runoff data are assimilated in real time to update modelled soil moisture. An analysis of the model performance indicates 88% of the snow cover in the basin to be modelled correctly on more than 80% of the days. Runoff forecasting errors decrease with catchment area and increase with forecast lead time. The forecast ensemble spread is shown to be a meaningful indicator of the forecast uncertainty. During the 2013 flood, there was a tendency for the precipitation forecasts to underestimate event precipitation and for the runoff model to overestimate runoff generation which resulted in, overall, rather accurate runoff forecasts. It is suggested that the human forecaster plays an essential role in interpreting the model results and, if needed, adjusting them before issuing the forecasts to the general public.

scholarly journals Appraising the capability of a land biosphere model as a tool in modelling land surface interactions: results from its validation at selected European ecosystems

2015 ◽  
Vol 6 (1) ◽  
pp. 217-265 ◽  
Author(s):  
M. R. North ◽  
G. P. Petropoulos ◽  
G. Ireland ◽  
J. P. McCalmont
Keyword(s):  
Land Surface ◽  
Model Performance ◽  
Global Scale ◽  
Surface Interactions ◽  
Climatic Conditions ◽  
Model Parameters ◽  
Observation Data ◽  
Ongoing Research ◽  
In Situ Data

Abstract. In this present study the ability of the SimSphere Soil Vegetation Atmosphere Transfer (SVAT) model in estimating key parameters characterising land surface interactions was evaluated. Specifically, SimSphere's performance in predicting Net Radiation (Rnet), Latent Heat (LE), Sensible Heat (H) and Air Temperature (Tair) at 1.3 and 50 m was examined. Model simulations were validated by ground-based measurements of the corresponding parameters for a total of 70 days of the year 2011 from 7 CarboEurope network sites. These included a variety of biomes, environmental and climatic conditions in the models evaluation. Overall, model performance can largely be described as satisfactory for most of the experimental sites and evaluated parameters. For all model parameters compared, predicted H fluxes consistently obtained the highest agreement to the in-situ data in all ecosystems, with an average RMSD of 55.36 W m−2. LE fluxes and Rnet also agreed well with the in-situ data with RSMDs of 62.75 and 64.65 W m−2 respectively. A good agreement between modelled and measured LE and H fluxes was found, especially for smoothed daily flux trends. For both Tair 1.3 m and Tair 50 m a mean RMSD of 4.14 and 3.54 °C was reported respectively. This work presents the first all-inclusive evaluation of SimSphere, particularly so in a European setting. Results of this study contribute decisively towards obtaining a better understanding of the model's structure and its correspondence to the real world system. Findings also further establish the model's capability as a useful teaching and research tool in modelling Earth's land surface interactions. This is of considerable importance in the light of the rapidly expanding use of the model worldwide, including ongoing research by various Space Agencies examining its synergistic use with Earth Observation data towards the development of operational products at a global scale.

Sign in / Sign up

Export Citation Format

Share Document