Comparing forecasting accuracy of selected grey and time series models based on energy consumption in Brazil and India

Khan, Atif Maqbool; Osińska, Magdalena

doi:10.1016/j.eswa.2022.118840

Cited by 30 publications

(13 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further verify the effectiveness of the prediction model, we also checked the Mean Absolute Percentage Error, Theil's U 1 -statistic, and Theil's U 2 -statistic values. As can be seen from Table 3, the Mean Absolute Percentage Error values obtained are all within 5%, which meets the normal Error requirements of the prediction model (Khan and Osińska, 2023). In addition, Theil's U 1 -statistic values are all close to 0, indicating that the prediction accuracy of the model is high.…”

Section: Model Testsupporting

confidence: 60%

Research on coal demand forecast and carbon emission reduction in Shanxi Province under the vision of carbon peak

Zhang²,

Qie³

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Facing the increasingly severe climate situation, China strives to improve its Nationally Determined Contributions, promising to reach its carbon peak by 2030. Accurately predicting the future demand quantity and changing the trends of coal resources is the key to maintaining national energy security and achieving the goal of “carbon peak” and is also an important research topic in the future. To improve the prediction accuracy, this study sorts out eight common factors affecting the coal demand from the aspects of the economy, population, and energy. The grey relational analysis method was used to describe the degree of importance of each factor and screen out the relatively vital factors. The system dynamics model for coal demand in Shanxi Province was also established. The coal demand and carbon emission trends in Shanxi Province from 2021 to 2030 were predicted under business-as-usual, low-speed and high-speed development scenarios. The study results show that: 1) During the 14th Five-Year Plan to 15th Five-year Plan, the trend of coal demand has changed from increasing to decreasing. Under the three scenarios, the coal demand in 2021 is expected to be 372.03 million tons, 365.97 million tons, 360.04 million tons, and it is expected that the coal demand will peak in 2025, and will reach 394.77 million tons, 390.27 million tons, and 385.66 million tons under the three scenarios, respectively. 2) With the development of population and economy, the total energy demand shows a continuously increasing trend. It is estimated that the total energy consumption will reach 237.46-242.93 million tons of standard coal in 2030, and the total energy demand will continue to grow in the foreseeable future. 3) The carbon dioxide emission is closely related to the coal demand, showing a similar variation trend. Under the business-as-usual development scenario, carbon emissions in 2021 are 699.62 million tons, and carbon emissions are expected to reach 681.12 million tons in 2030. The low-speed development and high-speed development scenarios have different degrees of energy saving and emission reduction benefits. Compared with the business-as-usual development scenario in 2030, the carbon dioxide emissions will be reduced by 1.64 million tons and 3.56 million tons respectively. Finally, we put forward important policy measures to promote the economic transformation and upgrading of Shanxi Province and accelerate the realization of the “carbon peak” goal.

show abstract

Section: Model Testsupporting

confidence: 60%

Research on coal demand forecast and carbon emission reduction in Shanxi Province under the vision of carbon peak

Zhang²,

Qie³

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…To evaluate the accuracy of the extracted Plant Height (PH) and the performance of the regression models, two metrics were employed: the coefficient of determination ( R 2 ) ( Karch, 2020 ), the root mean square error ( RMSE ) ( Hyndman and Koehler, 2006 ) and the normalized root mean square error ( NRMSE ) ( Khan and Osińska, 2023 ). R 2 serves as an indicator of the proportion of variance explained by the model relative to the total variance and typically falls between 0 and 1.…”

Section: Methodsmentioning

confidence: 99%

Improving the estimation of rice above-ground biomass based on spatio-temporal UAV imagery and phenological stages

Dai,

Yu,

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionUnmanned aerial vehicles (UAVs) equipped with visible and multispectral cameras provide reliable and efficient methods for remote crop monitoring and above-ground biomass (AGB) estimation in rice fields. However, existing research predominantly focuses on AGB estimation based on canopy spectral features or by incorporating plant height (PH) as a parameter. Insufficient consideration has been given to the spatial structure and the phenological stages of rice in these studies. In this study, a novel method was introduced by fully considering the three-dimensional growth dynamics of rice, integrating both horizontal (canopy cover, CC) and vertical (PH) aspects of canopy development, and accounting for the growing days of rice.MethodsTo investigate the synergistic effects of combining spectral, spatial and temporal parameters, both small-scale plot experiments and large-scale field testing were conducted in Jiangsu Province, China from 2021 to 2022. Twenty vegetation indices (VIs) were used as spectral features, PH and CC as spatial parameters, and days after transplanting (DAT) as a temporal parameter. AGB estimation models were built with five regression methods (MSR, ENet, PLSR, RF and SVR), using the derived data from six feature combinations (VIs, PH+CC, PH+CC+DAT, VIs+PH +CC, VIs+DAT, VIs+PH+CC+DAT).ResultsThe results showed a strong correlation between extracted and ground-measured PH (R2 = 0.89, RMSE=5.08 cm). Furthermore, VIs, PH and CC exhibit strong correlations with AGB during the mid-tillering to flowering stages. The optimal AGB estimation results during the mid-tillering to flowering stages on plot data were from the PLSR model with VIs and DAT as inputs (R2 = 0.88, RMSE=1111kg/ha, NRMSE=9.76%), and with VIs, PH, CC, and DAT all as inputs (R2 = 0.88, RMSE=1131 kg/ha, NRMSE=9.94%). For the field sampling data, the ENet model combined with different feature inputs had the best estimation results (%error=0.6%–13.5%), demonstrating excellent practical applicability.DiscussionModel evaluation and feature importance ranking demonstrated that augmenting VIs with temporal and spatial parameters significantly enhanced the AGB estimation accuracy. In summary, the fusion of spectral and spatio-temporal features enhanced the actual physical significance of the AGB estimation models and showed great potential for accurate rice AGB estimation during the main phenological stages.

show abstract

“…GM (1,1) is one of the commonly used models in the gray model 5 . It accumulates the original discrete non-negative data column once, and generates new regular discrete data column that weaken the randomness.…”

Section: Gm (11)mentioning

confidence: 99%

Dynamic combined prediction method for error state of capacitor voltage transformer based on elastic net regression

Lei,

Guo,

Wei

et al. 2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

The error state of capacitor voltage transformer (CVT) is an important index affecting the fairness of power system transactions, but its long-term stability is poor. In order to grasp the change of CVT error state in time, this paper proposes a dynamic combination forecasting method based on elastic network regression. This method starts with training the historical data of CVT error state by using multiple machine learning models. Then, white noise test are carried out on the trained model to judge the quality of the model. Furthermore, the prediction results of the model that conforms to the white noise test are regarded as input features to construct the elastic network regression model and find the optimal weight coefficient. Finally, the elastic network with the optimal coefficient is utilized for prediction. The experimental results show that each evaluation indexes of the proposed model under single-step prediction is lower than that of each single model, which can effectively improve the prediction accuracy.

show abstract

Comparing forecasting accuracy of selected grey and time series models based on energy consumption in Brazil and India

Cited by 30 publications

References 71 publications

Research on coal demand forecast and carbon emission reduction in Shanxi Province under the vision of carbon peak

Research on coal demand forecast and carbon emission reduction in Shanxi Province under the vision of carbon peak

Improving the estimation of rice above-ground biomass based on spatio-temporal UAV imagery and phenological stages

Dynamic combined prediction method for error state of capacitor voltage transformer based on elastic net regression

Contact Info

Product

Resources

About