A Hybrid Algorithm of GA Wavelet-BP Neural Networks to Predict Near Space Solar Radiation

Su, Jianmin; Song, Bifeng; Li, Baofeng

doi:10.1007/978-3-642-01510-6_51

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jianmin Su et al . (2009) used GA to improve the neural network performance in SR estimation . Since the back‐propagation (BP) neural networks are apt to converge at local optimal point, they used genetic algorithm to optimize BP neural networks' weights and threshold values.…”

Section: Review and Classification Of Sr Estimation Modelsmentioning

confidence: 99%

A review on classification and comparison of different models in solar radiation estimation

Tolabi

Moradi

Ayob

2014

Int. J. Energy Res.

View full text Add to dashboard Cite

SUMMARYThis paper introduces a new classification scheme for the solar radiation estimation techniques based on three categories: empirical models (based on statistical regression techniques), simulated models (based on training), and optimized models (based on optimization algorithms). For the optimized model category, a novelty bees algorithm estimation based on a linear empirical model is developed. Eight different methods from three classes have been tested on three sample geographic positions of Iran in order to compare the efficiency, complexity, sensed parameters, and required prior training of each category with others by implementing in the Matlab software. Among all tested models, the best properties are obtained for optimized empirical models by optimization algorithms. The main advantages of this model type are that it eliminates the training stage and therefore reduces the complexity rather than simulated models yet offers high accuracy estimation.

show abstract

Section: Review and Classification Of Sr Estimation Modelsmentioning

confidence: 99%

A review on classification and comparison of different models in solar radiation estimation

Tolabi

Moradi

Ayob

2014

Int. J. Energy Res.

View full text Add to dashboard Cite

show abstract

“…On the continuation of Xiao et al (2017) and respectively characterized large-scale and small-scale disturbances by cosine functions, and established the global atmospheric density model of near space, which further improved the accuracy. Artificial intelligence (AI) methods are also employed to study wind speed, total electron content (TEC) and solar radiation at different heights in middle and upper atmosphere (Chen et al, 2019(Chen et al, , 2023Su et al, 2009;F. Xie et al, 2012;Yang et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Refined Short‐Term Forecasting Atmospheric Temperature Profiles in the Stratosphere Based on Operators Learning of Neural Networks

Chen,

Sheng,

Cui

2024

Earth and Space Science

View full text Add to dashboard Cite

The efficacious forecasting of single‐station atmospheric temperature profiles can provide essential support for the structural design and flight missions of spacecrafts in near space. However, empirical models and reference atmospheric models most are calculations of the average state of the atmosphere profiles. Numerical assimilation models require expensive computational costs to improve the accuracy for medium and long‐term forecasting. It has been still a challenge to refined predict short‐term temperature profiles of near space at a low‐cost. We present a temperature profile operator method for refined modeling in the stratosphere by fusing the ability of Long Short‐Term Memory (LSTM) networks or its variants‐ bidirectional LSTM (BiLSTM) to exploit time series correlated information and deep operator networks (DeepONets) to approximate the solution operator of temperature profiles. It consists of three subnetworks. The first subnetwork is used to approximate the discrete temperature profile function, the second net is applied to represent the spatial information of pressure heights, and the third branch is utilized to encode the time domain of the temperature profile operator. We first use the hourly low latitude temperature data (20–50 km) from ERA5 for training, verification and iterative testing in the next 48 hr. The results denote that the temperature profile operator network has a stable and low error of cumulative generalization, and the BiLSTM operator significantly outperform the other models. We also apply two scenarios to testing the refined applicability of the high latitude temperature profile operator and the mid latitude wind profile operator in the stratosphere. This work provides a novel perspective for us to study the refined single‐station modeling of the upper and middle atmosphere.

show abstract

“…Su et al . used genetic algorithm (GA) to improve the neural networks performance in SR estimation. Because the back‐propagation (BP) neural networks are apt to converge at local optimal point, they used GA to optimize BP neural networks' weights and threshold values.…”

Section: Introductionmentioning

confidence: 99%

New technique for estimating the monthly average daily global solar radiation using bees algorithm and empirical equations

Tolabi

Ayob

Moradi

et al. 2013

Env Prog and Sustain Energy

View full text Add to dashboard Cite

Measurement of solar radiance demands expensive devices to be used. Alternatively, estimator models are used instead. In this article, a new method based on the empirical equations is introduced to estimate the monthly average daily global solar radiation (GSR) on a horizontal surface. The proposed method uses Bees algorithm as a heuristic and population-based search technique. The best coefficients of linear and nonlinear empirical models and GSR are calculated for seven different climate regions of Iran using proposed algorithm written in MATLAB software. The results of the proposed method are compared with other techniques. The result shows that the proposed method is more accurate in estimating the monthly average daily GSR.

show abstract

A Hybrid Algorithm of GA Wavelet-BP Neural Networks to Predict Near Space Solar Radiation

Cited by 3 publications

References 7 publications

A review on classification and comparison of different models in solar radiation estimation

A review on classification and comparison of different models in solar radiation estimation

Refined Short‐Term Forecasting Atmospheric Temperature Profiles in the Stratosphere Based on Operators Learning of Neural Networks

New technique for estimating the monthly average daily global solar radiation using bees algorithm and empirical equations

Contact Info

Product

Resources

About