Deep shared representation learning for weather elements forecasting

Mehrkanoon, Siamak

doi:10.1016/j.knosys.2019.05.009

Cited by 64 publications

(45 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a preprocessing step, both datasets are normalized using the min-max normalization based on values coming from the corresponding training sets. The discussed datasets have been previously introduced in [3] and [7]. We train our model with two variants: with γ set to 1 and with γ learnt with other parameters.…”

Section: Resultsmentioning

confidence: 99%

“…Deep learning based models have been successfully applied for weather elements forecasting [1][2][3]. Although Long Short-Term Memory (LSTM) recurrent networks [4], work well for time series prediction [5], they do not explicitly include spatial relations within the data.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…Authors in [6] combined LSTM with convolutions to create ConvLSTM, which was used for precipitation tasks, while also capturing the data spatial structure. The authors in [3] introduced convolutional neural network (CNN) models based on 1D-CNNs for multi-source 1D weather data, 2D-and 3D-CNNs to process the tensor-form 3D weather data. In this way, the spatial-temporal relations were extracted with 2D and 3D CNNs.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Graph Convolutional Networks for Wind Speed Prediction

Stańczyk¹,

Mehrkanoon²

2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce a new model for wind speed prediction based on spatio-temporal graph convolutional networks. Here, weather stations are treated as nodes of a graph with a learnable adjacency matrix, which determines the strength of relations between the stations based on the historical weather data. The self-loop connection is added to the learnt adjacency matrix and its strength is controlled by additional learnable parameter. Experiments performed on real datasets collected from weather stations located in Denmark and the Netherlands show that our proposed model outperforms previously developed baseline models on the referenced datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Graph Convolutional Networks for Wind Speed Prediction

Stańczyk¹,

Mehrkanoon²

2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…These models were popular in computer vision for RGB image processing ( Ou et al, 2020 ). The applications of CNN were also extended to one-dimension data (such as pixel-level spectra) ( Zhou et al, 2019 ) and three-dimension data ( Zhang et al, 2018 ; Mehrkanoon, 2019 ). In this research, the features of the wheat kernel were in a shape of 200 ∗ 1.…”

Section: Methodsmentioning

confidence: 99%

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

et al. 2020

View full text Add to dashboard Cite

“…In [9], changes in precipitable water vapour were estimated by a nonlinear autoregressive approach with exogenous input (NARX). In [10], temperature and wind speed were predicted using different upgraded versions of convolutional neural networks (CNN). In [11], the performance of multilayer perceptron (MLP) and multigene genetic programming (MGGP) neural networks for estimating the solar irradiance in PV systems are compared.…”

Section: Introductionmentioning

confidence: 99%

Photovoltaic Power Prediction Using Artificial Neural Networks and Numerical Weather Data

et al. 2020

View full text Add to dashboard Cite

The monitoring of power generation installations is key for modelling and predicting their future behaviour. Many renewable energy generation systems, such as photovoltaic panels and wind turbines, strongly depend on weather conditions. However, in situ measurements of relevant weather variables are not always taken into account when designing monitoring systems, and only power output is available. This paper aims to combine data from a Numerical Weather Prediction model with machine learning tools in order to accurately predict the power generation from a photovoltaic system. An Artificial Neural Network (ANN) model is used to predict power outputs from a real installation located in Puglia (southern Italy) using temperature and solar irradiation data taken from the Global Data Assimilation System (GDAS) sflux model outputs. Power outputs and weather monitoring data from the PV installation are used as a reference dataset. Three training and testing scenarios are designed. In the first one, weather data monitoring is used to both train the ANN model and predict power outputs. In the second one, training is done with monitoring data, but GDAS data is used to predict the results. In the last set, both training and result prediction are done by feeding GDAS weather data into the ANN model. The results show that the tested numerical weather model can be combined with machine learning tools to model the output of PV systems with less than 10% error, even when in situ weather measurements are not available.

show abstract

Deep shared representation learning for weather elements forecasting

Cited by 64 publications

References 16 publications

Deep Graph Convolutional Networks for Wind Speed Prediction

Deep Graph Convolutional Networks for Wind Speed Prediction

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Photovoltaic Power Prediction Using Artificial Neural Networks and Numerical Weather Data

Contact Info

Product

Resources

About