Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss
- URL: http://arxiv.org/abs/2106.03032v1
- Date: Sun, 6 Jun 2021 05:17:24 GMT
- Title: Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss
- Authors: Jongsu Kim and Changhoon Lee
- Abstract summary: The maximum correntropy criterion for regression (MCCR) loss is used in an analysis of the statistical characteristics of air pollution and weather data.
The MCCR loss is more appropriate than the conventional mean squared error loss for forecasting extreme values.
- Score: 1.7797683504485504
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: 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.
Related papers
- Conditional diffusion models for downscaling & bias correction of Earth system model precipitation [1.5193424827619018]
We propose a novel machine learning framework for simultaneous bias correction and downscaling.
Our approach ensures statistical fidelity, preserves large-scale spatial patterns and outperforms existing methods.
arXiv Detail & Related papers (2024-04-05T11:01:50Z) - A Generative Deep Learning Approach for Crash Severity Modeling with Imbalanced Data [6.169163527464771]
This study proposes a crash data generation method based on Conditional Tabular GAN.
A crash severity model is employed to estimate the performance of classification and interpretation.
The results indicate that using synthetic data generated by CTGAN-RU for crash severity modeling outperforms original data or synthetic data generated by other resampling methods.
arXiv Detail & Related papers (2024-04-02T16:07:27Z) - Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
This paper tackles the emerging challenge of training generative models within a self-consuming loop.
We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models.
We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
arXiv Detail & Related papers (2024-02-19T02:08:09Z) - ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast.
We also introduce a training-free extreme value enhancement strategy named ExEnsemble, which increases the variance of pixel values and improves the forecast robustness.
Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
arXiv Detail & Related papers (2024-02-02T10:34:13Z) - Residual Diffusion Modeling for Km-scale Atmospheric Downscaling [51.061954281398116]
A cost-effective downscaling model is trained from a high-resolution 2-km weather model over Taiwan.
textitCorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes.
Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to-km-scales machine learning weather predictions.
arXiv Detail & Related papers (2023-09-24T19:57:22Z) - DiffESM: Conditional Emulation of Earth System Models with Diffusion
Models [2.1989764549743476]
A key application of Earth System Models (ESMs) is studying extreme weather events, such as heat waves or dry spells.
We show that diffusion models can effectively emulate the trends of ESMs under previously unseen climate scenarios.
arXiv Detail & Related papers (2023-04-23T17:12:33Z) - An Asymmetric Loss with Anomaly Detection LSTM Framework for Power
Consumption Prediction [1.6156983514505385]
Power consumption patterns of the residential sector contain fluctuations and anomalies making them challenging to predict.
We propose multiple Long Short-Term Memory (LSTM) frameworks with different asymmetric loss functions to impose a higher penalty on underpredictions.
Considering the effect of weather and social factors, seasonality splitting is performed on the three considered datasets from France, Germany, and Hungary.
arXiv Detail & Related papers (2023-02-05T17:16:15Z) - DeepVol: Volatility Forecasting from High-Frequency Data with Dilated
Causal Convolutions [78.6363825307044]
We propose DeepVol, a model based on Dilated Causal Convolutions to forecast day-ahead volatility by using high-frequency data.
We show that the dilated convolutional filters are ideally suited to extract relevant information from intraday financial data.
arXiv Detail & Related papers (2022-09-23T16:13:47Z) - SurvLatent ODE : A Neural ODE based time-to-event model with competing
risks for longitudinal data improves cancer-associated Deep Vein Thrombosis
(DVT) prediction [68.8204255655161]
We propose a generative time-to-event model, SurvLatent ODE, which parameterizes a latent representation under irregularly sampled data.
Our model then utilizes the latent representation to flexibly estimate survival times for multiple competing events without specifying shapes of event-specific hazard function.
SurvLatent ODE outperforms the current clinical standard Khorana Risk scores for stratifying DVT risk groups.
arXiv Detail & Related papers (2022-04-20T17:28:08Z) - Churn Reduction via Distillation [54.5952282395487]
We show an equivalence between training with distillation using the base model as the teacher and training with an explicit constraint on the predictive churn.
We then show that distillation performs strongly for low churn training against a number of recent baselines.
arXiv Detail & Related papers (2021-06-04T18:03:31Z) - Modeling Atmospheric Data and Identifying Dynamics: Temporal Data-Driven
Modeling of Air Pollutants [2.578242050187029]
We present an empirical approach using data-driven techniques to study air quality in Madrid.
We find parsimonious systems of ordinary differential equations that model the concentration of pollutants and their changes over time.
Our results show that Akaike's Information Criterion can work well in conjunction with best subset regression as to find an equilibrium between sparsity and goodness of fit.
arXiv Detail & Related papers (2020-10-13T16:46:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.