Root mean square error or mean absolute error? Use their ratio as well

Karunasingha, Dulakshi S. K.

doi:10.1016/j.ins.2021.11.036

Cited by 303 publications

(109 citation statements)

References 38 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…In this study, three performance metrics are used to evaluate the effectiveness of the developed machine-learning models: the coefficient of determination (R 2 ) [ 66 ], mean squared log error (MSLE) [ 67 ] and mean absolute error (MAE) [ 68 ], as shown in Table 3 . The results show that the model created by the XGBoost algorithm has the best coefficients of determination and the fewest errors (R 2 = 0.838, MSLE = 0.185).…”

Section: Resultsmentioning

confidence: 99%

The impact of COVID-19 pandemic on electricity consumption and electricity demand forecasting accuracy: Empirical evidence from the state of Qatar

Abulibdeh

Zaidan

Jabbar

2022

Energy Strategy Reviews

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

The impact of COVID-19 pandemic on electricity consumption and electricity demand forecasting accuracy: Empirical evidence from the state of Qatar

Abulibdeh

Zaidan

Jabbar

2022

Energy Strategy Reviews

View full text Add to dashboard Cite

“…The MAE represents the average of the absolute difference between the actual and predicted values of the residuals in the dataset. MAE values close to 0 indicate that the model is an accurate predictor [52], while the RMSE measures the standard deviation of residuals [56].…”

Section: Shoreline Position Forecastingmentioning

confidence: 99%

Estimating Quantitative Morphometric Parameters and Spatiotemporal Evolution of the Prokopos Lagoon Using Remote Sensing Techniques

Apostolopoulos

Avramidis

Nikolakopoulos

2022

JMSE

View full text Add to dashboard Cite

The Prokopos Lagoon is part of the Kotychi Strofilias National Wetlands Park, which is supervised by the Ministry of Environment, Energy and Climate Change of Greece. The lagoon is situated at the northwestern coast of the Peloponnese and is protected by the Ramsar Convention. It is an important ecosystem with ecological services providing habitats for many plants and animals and essential goods and services for humans as well. No previous relevant studies for the wider wetland area are available, and given that lagoons are important ecosystems, their diachronic evolution should be under constant monitoring. Using remote sensing techniques in Geographic Information System (GIS) environment, alterations in critical parameters could be measured and applied for the protection of the area. The present study examines the spatiotemporal changes of the water extent of the Prokopos Lagoon, estimating landscape metrics and several morphometric parameters and indices related to the geomorphological features of the lagoon for the 1945–2021 period. Moreover, the adjacent shoreline was studied for each past decade evolution from 1945 to present, and it is discussed to whether there is a relationship between shoreline changes and the lagoon. High resolution satellite images and air photos at scale 1:30,000 were used to digitize the shorelines and the polygons of the lagoon’s surface. Linear Regression Rates (LRR), Net Shoreline Movement (NSM), End Point Rate (EPR) and Shoreline Change Envelope (SCE) provided by the Digital Shoreline Analysis System (DSAS) were used to determine the changes. Finally, future shoreline positions for 2021 and 2031 are estimated, while based on statistic models, we found that in the coastal area, the erosion–accretion cycle is predicted to be completed in 2031, after almost 86 years since 1945.

show abstract

“…e Root Mean Square Error (RMSE) [31]and the Percent Relative Error (PRE) [32]are adopted to examine how subsidence is accurately and reliably predicted by using the formula for each observation line at any point in the surface. As a numerical measure of prediction accuracy, RMSE refers to the square root of the sum of the squares of the difference between predicted and measured values and the ratio of the number of observations n. A smaller RMSE value indicates a higher accuracy of prediction [33]. e PRE is advantageous in reflecting the reliability of the predicted formula, with a lower absolute value of PRE indicating a greater reliability.…”

Section: Prediction Error Of the Distribution Of The Surface Settleme...mentioning

confidence: 99%

Normality Test for Influence Function of Mining Surface Subsidence Based on Network Observation Station

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Coal is the primary energy source in China, while underground mining is the mainstream way of coal mining. By triggering surface movement and deformation, underground mining can cause damage to arable land, buildings, roads, and so on, which is detrimental to the ecological environment in the mining area. In order to assess the severity of damage caused by this to the ground buildings and ecological environment in the mining area, it is necessary to predict mining-induced surface subsidence before the mining activities are carried out. Currently, the most used prediction method is the Probability Integral Method. It is based on probabilistic theory to mathematically demonstrate that the surface downwelling caused by underground extraction conforms to normal distribution. However, there is a lack of validation with measured subsidence basin data. Since the 1960s, China has been paying increased attention to the study of mining subsidence. However, there are still few network stations built across China to monitor subsidence basin. Herein, SPSS software is applied to re-analyze these valuable historical data. By analyzing the observation results and comparing them with the calculation results as obtained by using the probability integral method, it can be found out that the surface subsidence in the center of the subsidence basin conforms to normal distribution, not the subsidence at the edge of the subsidence basin. Therefore, it is inevitable for errors to occur at the edge of the subsidence basin when the normal distribution function is used as the mining influence function to calculate the surface subsidence. This conclusion is expected to provide practical reference for the prediction of surface subsidence in coal mines, and this experience can be extended to the mining of other solid minerals.

show abstract

Root mean square error or mean absolute error? Use their ratio as well

Cited by 303 publications

References 38 publications

The impact of COVID-19 pandemic on electricity consumption and electricity demand forecasting accuracy: Empirical evidence from the state of Qatar

The impact of COVID-19 pandemic on electricity consumption and electricity demand forecasting accuracy: Empirical evidence from the state of Qatar

Estimating Quantitative Morphometric Parameters and Spatiotemporal Evolution of the Prokopos Lagoon Using Remote Sensing Techniques

Normality Test for Influence Function of Mining Surface Subsidence Based on Network Observation Station

Contact Info

Product

Resources

About