Probabilistic and Point Solar Forecasting Using Attention Based Dilated Convolutional Neural Network

2020 ◽  
Author(s):  
Moumita Saha ◽  
Bhalchandra Naik ◽  
Claire Monteleoni
Keyword(s):  
Neural Network ◽  
Climate Change ◽  
Deep Learning ◽  
Solar Irradiance ◽  
Weather Prediction ◽  
Clean Energy ◽  
Solar Forecasting ◽  
Short Term ◽  
Term Forecast

<p>Climate change is evident at present with threatening effects as intense hurricanes, rising sea level, increase number of droughts, and shifting weather patterns. Burning of fossil fuels and anthropogenic activities increase the greenhouse gases concentration in atmosphere, which is a major cause behind the climate change. Renewable energy as solar is a good source for combating the causes of climate change by producing clean energy.  </p><p>The efficient integration of solar energy into electrical grids requires an accurate prediction of solar irradiance. The solar irradiance is the flux of radiant energy received per unit area of the earth from the sun. Existing techniques use basic stochastic (such Gaussian model, hidden Markov model, etc.) and ensemble neural network models for solar forecasting. However, recent literature reflects the potential of deep-learning models over the statistical model.</p><p>In this paper, we propose a deep-learning-based one-dimensional, multi-quantile convolution neural network for predicting the solar irradiance. The network employs dilation in its convolution kernel, which helps capturing the long-term dependencies between instances of the input climatic variables. Additionally, we also incorporate the attention mechanism between the input and learned representation from the convolution, which allows attending to the temporal instance of features for improved prediction. We perform both short-term (three hours ahead) and long-term (twenty-four hours ahead) solar irradiance prediction. We exhaustively present the forecast for all four seasons (spring, summer, fall, and winter) as well as for the whole year. We provide a point solar forecast along with forecast at different quantiles. Quantile forecast provides a range of estimates with varying confidence intervals, which allows better interpretation as compared to point forecast. This notion of confidence associated with each quantile makes the forecasting probabilistic.</p><p>In order to validate our approach, we consider two cities (Boulder and Fort Peck) from the SURFAD network and examine twenty climatic features as input to our model.  Additionally, we learned embedded reduced input dimension using an autoencoder. The proposed architecture is trained with all the input features and reduced features, independently. We observe the prediction error for Boulder is higher than Fort Peck, which can be due to the volatile weather of Boulder. The proposed model forecasts the solar irradiance for winter with a higher accuracy as compared to spring, summer, or fall. We observe the correlation coefficients as 0.90 (Boulder) and 0.92 (Fort Peck) between the actual and predicted solar irradiance.  The long-term forecast shows average improvements of 37.1% and 33.1% in root mean square error (RMSE) over existing numerical weather prediction model for Boulder and Fort Peck, respectively. Similarly, the short-term forecast shows improvements of 33.7% and 34.2% for the respective cities.</p>

scholarly journals Temporally Generalizable Land Cover Classification: A Recurrent Convolutional Neural Network Unveils Major Coastal Change through Time

2021 ◽  
Vol 13 (19) ◽  
pp. 3953
Author(s):  
Patrick Clifton Gray ◽  
Diego F. Chamorro ◽  
Justin T. Ridge ◽  
Hannah Rae Kerner ◽  
Emily A. Ury ◽  
...  
Keyword(s):  
Neural Network ◽  
Climate Change ◽  
Deep Learning ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Agricultural Land ◽  
Coastal Areas ◽  
Support Vector ◽  
Validation Data

The ability to accurately classify land cover in periods before appropriate training and validation data exist is a critical step towards understanding subtle long-term impacts of climate change. These trends cannot be properly understood and distinguished from individual disturbance events or decadal cycles using only a decade or less of data. Understanding these long-term changes in low lying coastal areas, home to a huge proportion of the global population, is of particular importance. Relatively simple deep learning models that extract representative spatiotemporal patterns can lead to major improvements in temporal generalizability. To provide insight into major changes in low lying coastal areas, our study (1) developed a recurrent convolutional neural network that incorporates spectral, spatial, and temporal contexts for predicting land cover class, (2) evaluated this model across time and space and compared this model to conventional Random Forest and Support Vector Machine methods as well as other deep learning approaches, and (3) applied this model to classify land cover across 20 years of Landsat 5 data in the low-lying coastal plain of North Carolina, USA. We observed striking changes related to sea level rise that support evidence on a smaller scale of agricultural land and forests transitioning into wetlands and “ghost forests”. This work demonstrates that recurrent convolutional neural networks should be considered when a model is needed that can generalize across time and that they can help uncover important trends necessary for understanding and responding to climate change in vulnerable coastal regions.

Monitoring and Prediction of Air Quality using Neural Network

2018 ◽  
Vol 8 (6) ◽  
pp. 47
Author(s):  
Shwetal Raipure
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Pollution Index ◽  
Learning Technologies ◽  
Short Term ◽  
Initial Information ◽  
Term Forecast ◽  
The Neural Network

Air Quality monitoring is very important in today s world. There are many harmful pollutants present in the air which are very harmful for human health. Prolonged consumption of such air may lead to severe death and harmful diseases. It is also harmful for crops as well as animals which may damage natural environment. There are  several pollutants which are present in the air that decreases the quality of air such as sulfur oxide, nitrogen dioxide, carbon monoxide and dioxide, and particulate matter. Neural Network  can be used for prediction of population for short term as well as long term using a deep learning technologies. Neural network specify two types of predictive models. the first one is the a temporal which is for short-term forecast of the pollutants in the air for the short coming or nearest days and the second one is  a spatial forecast of atmospheric pollution index in any point of city. The artificial neural networks takes initial information and consider the hidden dependencies are used to improve the efficiency and accuracy of the ecology management decisions. In this paper the forecasting of atmospheric air pollution index in industrial cities based on the  neural network model has proposed.

scholarly journals Short-Term Solar Forecasting Model using Artificial Neural Networks

2020 ◽  
Vol 6 (10) ◽  
pp. 1-6
Keyword(s):  
Solar Irradiance ◽  
Energy Demand ◽  
Renewable Energy Sources ◽  
Weather Prediction ◽  
Back Propagation ◽  
External Input ◽  
Weather Data ◽  
Forecasting Model ◽  
Solar Forecasting ◽  
Short Term

In present context, Electrical Energy generation in India is mostly based on the conventional sources, but the time has come to be not depend on these conventional sources and to make renewable Energy sources capable of producing total energy demand by its own. So the focus has been shifted towards Wind, Hydro and photovoltaic (PV) power generation. Accurate forecasting of solar irradiance is required for effective and efficient power scheduling & dispatching. And this weather data is needed by the control engineers for planning their control strategies. In this paper a simple approach for weather prediction is proposed which relies on hourly weather data such as Temperature, Relative humidity, surface pressure, wind speed & direction and solar irradiance. The solar forecasting model to predict short-term solar irradiance & other weather parameters, is done by using Leven-berg Marquardt and Bayesian regularization back-propagation algorithms with standard nonlinear autoregressive with external input NARXfeedforward Network. This approachis simple to implement fast in execution and provides good results for short-term time horizon predictions.

scholarly journals Short-Term Solar Irradiance Forecasting Based on a Hybrid Deep Learning Methodology

Information ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 32 ◽  
Author(s):  
Ke Yan ◽  
Hengle Shen ◽  
Lei Wang ◽  
Huiming Zhou ◽  
Meiling Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Solar Irradiance ◽  
Power Plants ◽  
Short Term Memory ◽  
Learning Model ◽  
Weather Data ◽  
Short Term ◽  
Original Dataset ◽  
Deep Learning Model

Accurate prediction of solar irradiance is beneficial in reducing energy waste associated with photovoltaic power plants, preventing system damage caused by the severe fluctuation of solar irradiance, and stationarizing the power output integration between different power grids. Considering the randomness and multiple dimension of weather data, a hybrid deep learning model that combines a gated recurrent unit (GRU) neural network and an attention mechanism is proposed forecasting the solar irradiance changes in four different seasons. In the first step, the Inception neural network and ResNet are designed to extract features from the original dataset. Secondly, the extracted features are inputted into the recurrent neural network (RNN) network for model training. Experimental results show that the proposed hybrid deep learning model accurately predicts solar irradiance changes in a short-term manner. In addition, the forecasting performance of the model is better than traditional deep learning models (such as long short term memory and GRU).

scholarly journals Preparing for changes in plant disease due to climate change

2010 ◽  
Vol 45 (Special Issue) ◽  
pp. S3-S10 ◽  
Author(s):  
W. Shaw M
Keyword(s):  
Climate Change ◽  
Plant Disease ◽  
Biological Effects ◽  
Short Term ◽  
Term Forecast ◽  
Climate Simulations ◽  
Long Time ◽  
Forecast Models ◽  
Long Term Trends

Climate change will change patterns of disease through changes in host distribution and phenology, changes in plant-associated microflora and direct biological effects on rapidly evolving pathogens. Short-term forecast models coupled with weather generated from climate simulations may be a basis for projection; however, they will often fail to capture long-term trends effectively. Verification of predictions is a major difficulty; the most convincing method would be to “back-forecast” observed historical changes. Unfortunately, we lack of empirical data over long time-spans; most of what is known concerns invasions, in which climate is not the main driving factor. In one case where long-term prevalence can be deduced, climate had little to do with change. Resilience to surprises should be the most important policy aim.

scholarly journals Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1151
Author(s):  
Carolina Gijón ◽  
Matías Toril ◽  
Salvador Luna-Ramírez ◽  
María Luisa Marí-Altozano ◽  
José María Ruiz-Avilés
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Data Traffic ◽  
Medium Term ◽  
Short Term ◽  
Traffic Forecasting ◽  
Series Analysis ◽  
Radio Planning

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

scholarly journals Multiple Pedestrians and Vehicles Tracking in Aerial Imagery Using a Convolutional Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1953
Author(s):  
Seyed Majid Azimi ◽  
Maximilian Kraus ◽  
Reza Bahmanyar ◽  
Peter Reinartz
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Object Tracking ◽  
Short Term Memory ◽  
Aerial Imagery ◽  
Future Research ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

In this paper, we address various challenges in multi-pedestrian and vehicle tracking in high-resolution aerial imagery by intensive evaluation of a number of traditional and Deep Learning based Single- and Multi-Object Tracking methods. We also describe our proposed Deep Learning based Multi-Object Tracking method AerialMPTNet that fuses appearance, temporal, and graphical information using a Siamese Neural Network, a Long Short-Term Memory, and a Graph Convolutional Neural Network module for more accurate and stable tracking. Moreover, we investigate the influence of the Squeeze-and-Excitation layers and Online Hard Example Mining on the performance of AerialMPTNet. To the best of our knowledge, we are the first to use these two for regression-based Multi-Object Tracking. Additionally, we studied and compared the L1 and Huber loss functions. In our experiments, we extensively evaluate AerialMPTNet on three aerial Multi-Object Tracking datasets, namely AerialMPT and KIT AIS pedestrian and vehicle datasets. Qualitative and quantitative results show that AerialMPTNet outperforms all previous methods for the pedestrian datasets and achieves competitive results for the vehicle dataset. In addition, Long Short-Term Memory and Graph Convolutional Neural Network modules enhance the tracking performance. Moreover, using Squeeze-and-Excitation and Online Hard Example Mining significantly helps for some cases while degrades the results for other cases. In addition, according to the results, L1 yields better results with respect to Huber loss for most of the scenarios. The presented results provide a deep insight into challenges and opportunities of the aerial Multi-Object Tracking domain, paving the way for future research.

scholarly journals Multiplexed neurochemical transmission emulated using a dual-excitatory synaptic transistor

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Mingxue Ma ◽  
Yao Ni ◽  
Zirong Chi ◽  
Wanqing Meng ◽  
Haiyang Yu ◽  
...  
Keyword(s):  
Neural Network ◽  
Central Nervous System ◽  
Nervous System ◽  
Long Term Potentiation ◽  
Short Term ◽  
Term Potentiation ◽  
Binary Neural Network ◽  
Neuromorphic Systems ◽  
Human Brains

AbstractThe ability to emulate multiplexed neurochemical transmission is an important step toward mimicking complex brain activities. Glutamate and dopamine are neurotransmitters that regulate thinking and impulse signals independently or synergistically. However, emulation of such simultaneous neurotransmission is still challenging. Here we report design and fabrication of synaptic transistor that emulates multiplexed neurochemical transmission of glutamate and dopamine. The device can perform glutamate-induced long-term potentiation, dopamine-induced short-term potentiation, or co-release-induced depression under particular stimulus patterns. More importantly, a balanced ternary system that uses our ambipolar synaptic device backtrack input ‘true’, ‘false’ and ‘unknown’ logic signals; this process is more similar to the information processing in human brains than a traditional binary neural network. This work provides new insight for neuromorphic systems to establish new principles to reproduce the complexity of a mammalian central nervous system from simple basic units.

Sign in / Sign up

Export Citation Format

Share Document