scholarly journals Modeling Wind Speed with a Long-Term Horizon and High-Time Interval with a Hybrid Fourier-Neural Network Model

2021 ◽  
Vol 8 (3) ◽  
pp. 431-440
Author(s):  
Juan Gabriel Rueda-Bayona ◽  
Juan José Cabello Eras ◽  
Alexis Sagastume Gutiérrez
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Wind Speed ◽  
Neural Network Model ◽  
Local Scale ◽  
Time Interval ◽  
The Moment ◽  
Nonlinear Autoregressive ◽  
Fourier Model

The limited availability of local climatological stations and the limitations to predict the wind speed (WS) accurately are significant barriers to the expansion of wind energy (WE) projects worldwide. A methodology to forecast accurately the WS at the local scale can be used to overcome these barriers. This study proposes a methodology to forecast the WS with high-resolution and long-term horizons, which combines a Fourier model and a nonlinear autoregressive network (NAR). Given the nonlinearities of the WS variations, a NAR model is used to forecast the WS based on the variability identified with the Fourier analysis. The NAR modelled successfully 1.7 years of wind-speed with 3 hours of the time interval, what may be considered the longest forecasting horizon with high resolution at the moment.

scholarly journals A Comparative Study of Activation Functions of NAR and NARX Neural Network for Long-Term Wind Speed Forecasting in Malaysia

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Rasel Sarkar ◽  
Sabariah Julai ◽  
Sazzad Hossain ◽  
Wen Tong Chong ◽  
Mahmudur Rahman
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Wind Farm ◽  
Wind Power Generation ◽  
Activation Functions ◽  
Wind Speed Forecasting ◽  
Nonlinear Autoregressive ◽  
Narx Neural Network

Since wind power is directly influenced by wind speed, long-term wind speed forecasting (WSF) plays an important role for wind farm installation. WSF is essential for controlling, energy management and scheduled wind power generation in wind farm. The proposed investigation in this paper provides 30-days-ahead WSF. Nonlinear Autoregressive (NAR) and Nonlinear Autoregressive Exogenous (NARX) Neural Network (NN) with different network settings have been used to facilitate the wind power generation. The essence of this study is that it compares the effect of activation functions (namely, tansig and logsig) in the performance of time series forecasting since activation function is the core element of any artificial neural network model. A set of wind speed data was collected from different meteorological stations in Malaysia, situated in Kuala Lumpur, Kuantan, and Melaka. The proposed activation functions tansig of NARNN and NARXNN resulted in promising outcomes in terms of very small error between actual and predicted wind speed as well as the comparison for the logsig transfer function results.

scholarly journals Large-scale atmospheric forcing and topographic modification of precipitation rates over High Asia – a neural-network-based approach

2015 ◽  
Vol 6 (1) ◽  
pp. 61-81 ◽  
Author(s):  
L. Gerlitz ◽  
O. Conrad ◽  
J. Böhner
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Local Scale ◽  
Predictor Variables ◽  
High Mountain ◽  
Target Area ◽  
Monthly Precipitation ◽  
Highly Nonlinear

Abstract. The heterogeneity of precipitation rates in high-mountain regions is not sufficiently captured by state-of-the-art climate reanalysis products due to their limited spatial resolution. Thus there exists a large gap between the available data sets and the demands of climate impact studies. The presented approach aims to generate spatially high resolution precipitation fields for a target area in central Asia, covering the Tibetan Plateau and the adjacent mountain ranges and lowlands. Based on the assumption that observed local-scale precipitation amounts are triggered by varying large-scale atmospheric situations and modified by local-scale topographic characteristics, the statistical downscaling approach estimates local-scale precipitation rates as a function of large-scale atmospheric conditions, derived from the ERA-Interim reanalysis and high-resolution terrain parameters. Since the relationships of the predictor variables with local-scale observations are rather unknown and highly nonlinear, an artificial neural network (ANN) was utilized for the development of adequate transfer functions. Different ANN architectures were evaluated with regard to their predictive performance. The final downscaling model was used for the cellwise estimation of monthly precipitation sums, the number of rainy days and the maximum daily precipitation amount with a spatial resolution of 1 km2. The model was found to sufficiently capture the temporal and spatial variations in precipitation rates in the highly structured target area and allows for a detailed analysis of the precipitation distribution. A concluding sensitivity analysis of the ANN model reveals the effect of the atmospheric and topographic predictor variables on the precipitation estimations in the climatically diverse subregions.

Grey RBF Neural Network Forecasting on LV under the View of Government Responsibility

2012 ◽  
Vol 452-453 ◽  
pp. 700-704
Author(s):  
Feng Rong Zhang ◽  
Annik Magerholm Fet ◽  
Xin Wei Xiao
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Development Policy ◽  
Rbf Neural Network ◽  
Good Method ◽  
Government Responsibility ◽  
Long Period ◽  
The Government

At present, the domestic research on the scale of macroscopic logistics has yet belonged to the blankness, therefore, this research tries using LV in circulation and LV in stock to measure the logistics volume and forecasting it in a long period. In order to overcome the phenomenon of “floating upward” in long-term period, this paper establish the improved Grey RBF to forecast the LV next 5-10 year in Jilin province of China. The results show that the increased circulation of goods is the main reason leading to increased logistics volume, and the simulation also shows that the improved gray RBF neural network model is a good method for the government to establish the logistics development policy.

Generating long-term high-resolution land-use change datasets for regional climate modeling in CORDEX domains

2021 ◽  
Author(s):  
Peter Hoffmann ◽  
Diana Rechid ◽  
Vanessa Reinhart ◽  
Christina Asmus ◽  
Edouard L. Davin ◽  
...  
Keyword(s):  
Land Use ◽  
High Resolution ◽  
Land Use Change ◽  
Land Cover ◽  
Climate Modeling ◽  
Regional Climate ◽  
Regional Climate Modeling ◽  
Local Scale ◽  
Modeling Studies

<p>Land-use and land cover (LULC) are continuously changing due to environmental changes and anthropogenic activities. Many observational and modeling studies show that LULC changes are important drivers altering land surface feedbacks and land-atmosphere exchange processes that have substantial impact on climate on the regional and local scale. Yet, most long-term regional climate modeling studies do not account for these changes. Therefore, within the WCRP CORDEX Flagship Pilot Study LUCAS (Land Use Change Across Scales) a new workflow was developed to generate high-resolution annual land cover change time series based on past reconstructions and future projections. First, the high-resolution global land cover dataset ESA-CCI LC (~300 m resolution) is aggregated and converted to a 0.1° resolution, fractional plant functional type (PFT) dataset. Second, the land use change information from the land-use harmonized dataset (LUH2), provided at 0.25° resolution as input for CMIP6 experiments, is translated into PFT changes employing a newly developed land use translator (LUT). The new LUT was first applied to the EURO-CORDEX domain. The resulting LULC maps for past and future - the LUCAS LUC dataset - can be applied as land use forcing to the next generation RCM simulations for downscaling CMIP6 by the EURO-CORDEX community and in the framework of FPS LUCAS. The dataset includes land cover and land management practices changes important for the regional and local scale such as urbanization and irrigation. The LUCAS LUC workflow is applied to further CORDEX domains, such as Australasia and North America. The resulting past and future land cover changes will be presented, and challenges regarding the application of the new workflow to different regions will be addressed. In addition, issues related to the implementation of the dataset into different RCMs will be discussed.</p>

Stimulus configuration, long-term potentiation, and the hippocampus

1997 ◽  
Vol 20 (4) ◽  
pp. 629-631 ◽  
Author(s):  
Nestor A. Schmajuk
Keyword(s):  
Neural Network ◽  
Computer Simulations ◽  
Neural Network Model ◽  
Long Term Potentiation ◽  
Stimulus Configuration ◽  
Association Cortex ◽  
Hippocampal Function ◽  
Term Potentiation ◽  
External Stimuli

Shors & Matzel propose that hippocampal LTP increases the effective salience of discrete external stimuli and thereby facilitates the induction of memories at distant places. In line with this suggestion, a neural network model of associative learning and hippocampal function assumes that LTP increases hippocampal error signals to the cortex, thereby facilitating stimulus configuration in association cortex. Computer simulations show that under these assumptions the model correctly describes the effect of LTP induction and blockade in classical discriminations and place learning.

Sign in / Sign up

Export Citation Format

Share Document