Imbalanced regression and extreme value prediction

Ribeiro, Rita P.; Moniz, Nuno

doi:10.1007/s10994-020-05900-9

Cited by 68 publications

(49 citation statements)

References 52 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Future research should focus on the development of methods of handling long-range dependence and extreme values. As mentioned in Section 3.4, multiple approaches have been proposed recently to train memory over a longer horizon on the basis of the well-established extreme value theory Ding et al [2019], Ribeiro and Moniz [2020].…”

Section: Discussionmentioning

confidence: 99%

“…The MSE loss, however, tends to suffer from extreme values, which is common for heavy-tailed distributions because the error is squared. Although numerous efforts have been made to predict extreme values (for example, the use of a memory network module and a variable loss function Ding et al [2019], Ribeiro and Moniz [2020]), these methods require a long training time because they need to access a different dataset for each batch.…”

Section: Maximum Correntropy Criterion Induced Losses For Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss

Kim,

Lee

2021

Preprint

View full text Add to dashboard Cite

Forecasting the particulate matter (PM) concentration in South Korea has become urgently necessary owing to its strong negative impact on human life. In most statistical or machine learning methods, independent and identically distributed data, for example, a Gaussian distribution, are assumed; however, time series such as air pollution and weather data do not meet this assumption. In this study, the maximum correntropy criterion for regression (MCCR) loss is used in an analysis of the statistical characteristics of air pollution and weather data. Rigorous seasonality adjustment of the air pollution and weather data was performed because of their complex seasonality patterns and the heavy-tailed distribution of data even after deseasonalization. The MCCR loss was applied to multiple models including conventional statistical models and state-of-the-art machine learning models. The results show that the MCCR loss is more appropriate than the conventional mean squared error loss for forecasting extreme values.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Maximum Correntropy Criterion Induced Losses For Regressionmentioning

confidence: 99%

Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss

Kim,

Lee

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Max‐min normalization method was used for data preprocessing of meteorological features. The logarithmic function was used for data preprocessing of emission amount due to its extremely uneven spatial distribution (Ribeiro & Moniz, 2020).…”

Section: Model Development Of the Deep Learning Surrogatementioning

confidence: 99%

Approximating Three‐Dimensional (3‐D) Transport of Atmospheric Pollutants via Deep Learning

Zhang

Cheng

et al. 2022

Earth and Space Science

View full text Add to dashboard Cite

Chemical transport model (CTM) is a fundamental research tool for atmospheric environment and is widely used for air quality forecasting, source apportionment, and strategy design of pollution alleviation (Chuang et al., 2018;Shen et al., 2020;Zhang et al., 2014). Physical transport process is the driving force for primary pollutants, thus then affects the concentration of secondary pollutants (Byun & Schere, 2006;Tilt, 2019). It is usually numerically solved based on the Euler's mass continuity equation in CTM and occupies 57%~60% of the entire CTM's computation time (Colella & Woodward, 1984;Ying & Li, 2011;Zhang et al., 2013). Moreover, the exponential growth of computational cost is observed with finer spatial resolution due to the smaller time step and larger iteration steps required (Boffi et al., 2007;Kasim et al., 2020). The solution of physical transport process has become the critical bottleneck of the CTM's computation efficiency.Machine learning, especially deep learning, has become a new research paradigm and acted as partial or whole replacement of complex geoscience models due to its excellent ability for non-linear fitting (Reichstein et al., 2019;Rolnick et al., 2019;Yuan et al., 2020). Specifically, for the surrogate of atmospheric transport process, Lauret et al. ( 2016) combined cellular automata and the artificial neural network (CA-ANN) to calculate the turbulence coefficient in horizontal two-dimensional (2-D) space. The R squared is over 0.7 for most testcases with the computation efficiency increases by ∼1.5 times. Wang and Qian (2018) extended the study to three-dimensional (3-D) space with the same CA-ANN. R squared for a single time step vary between 0.2 and 0.95, and is reduced to almost zero after 100 multiple-time-step. The computation efficiency increased is still ∼1.5 times. Vlasenko et al. ( 2021) emulated the entire CTM and the speed gain is 720 times of acceleration. Only 2-D horizontal distribution of daily average concentration, however, is concerned and the R squared values are only in the range of 0.38-0.67. The comprehensive performance with the aspects of efficiency promotion, long-term consistency, and spatial dimensions was still unsatisfied.

show abstract

“…A few were developed for imbalanced regression. Many approaches revolve around modifications of SMOTE such as adapted to regression SMOTER [38], augmented with Gaussian Noise SMOGN [39], or [40] work extending for prediction of extremely rare values. [41] proposed DenseWeight, a method based on Kernel Density Estimation for better assessment of the relevance function for sample reweighing.…”

Section: Related Workmentioning

confidence: 99%

Taming the Long Tail of Deep Probabilistic Forecasting

Kozerawski¹,

Sharan²,

Yu³

2022

Preprint

View full text Add to dashboard Cite

Deep probabilistic forecasting is gaining attention in numerous applications ranging from weather prognosis, through electricity consumption estimation, to autonomous vehicle trajectory prediction. However, existing approaches focus on improvements on the most common scenarios without addressing the performance on rare and difficult cases. In this work, we identify a long tail behavior in the performance of state-of-the-art deep learning methods on probabilistic forecasting. We present two moment-based tailedness measurement concepts to improve performance on the difficult tail examples: Pareto Loss and Kurtosis Loss. Kurtosis loss is a symmetric measurement as the fourth moment about the mean of the loss distribution. Pareto loss is asymmetric measuring right tailedness, modeling the loss using a generalized Pareto distribution (GPD). We demonstrate the performance of our approach on several real-world datasets including time series and spatiotemporal trajectories, achieving significant improvements on the tail examples.

show abstract

Imbalanced regression and extreme value prediction

Cited by 68 publications

References 52 publications

Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss

Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss

Approximating Three‐Dimensional (3‐D) Transport of Atmospheric Pollutants via Deep Learning

Taming the Long Tail of Deep Probabilistic Forecasting

Contact Info

Product

Resources

About