STL : A Seasonal-Trend Decomposition Procedure Based on Loess

By R. Cleveland. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, methodology): “Forecasting practitioners often use the decomposition of time series into trend and seasonality, such as those performed by the STL [7] and X13-ARIMA [30] procedures.”
Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “As the deseasonalization technique we use Seasonal and Trend decomposition using Loess (STL), as proposed by Cleveland et al. (1990), to divide a time series into trend, seasonal, and remainder components.”
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting (2021, methodology): “2 Decomposition of Time Series As a standard method in time series analysis, time series decomposition [1, 27] deconstructs a time series into several components, each representing one of the underlying categories of patterns that are more predictable.”
Are Transformers Effective for Time Series Forecasting? (2022, methodology): “Besides, Autoformer [28] ﬁrst applies seasonal-trend decomposition behind each neural block, which is a standard method in time series analysis to make raw data more predictable [6, 13].”
Long-term changes in fish abundance and environmental indices in the Black Sea (2003, methodology): “An STL procedure (seasonal trend decomposition based on LOESS: Cleveland et al. 1990) was applied in modelling seasonality.”
Towards Supporting Search over Trending Events with Social Media (2013, methodology): “We employed a LOESS-based seasonal decomposition algorithm (Cleveland et al. 1990) to isolate the longer-term temporal patterns from the daily variation.”
Multifractal Detrended Fluctuation Analysis of Streamflow in the Yellow River Basin, China (2015, unknown): “[27].”
Irreversibility and complex network behavior of stream flow fluctuations (2016, methodology): “are then smoothed by local scatter plot smoothing (LOESS) [32] following the rationale of the seasonal-trend decomposition 2 based on LOESS (STL) procedure [33], obtaining smoothed seasonal componentsmi and si.”
Modern Applied Statistics with S Fourth edition (2002, background): “Decompositions The functionstl is based on Cleveland et al. (1990). It is complex, and the details differ betweenS environments, so the on-line documentation and the reference should be consulted.”
A resampling scheme for regional climate simulations and its performance compared to a dynamical RCM (2008, methodology): “The noise signal from a time series can for example be extracted by the STL approach (Cleveland et al. 1990), for the comparison of the two empirical distributions the KolmogorovSmirnov test (KS test) is used (see, e. g., von Storch and Zwiers 1999).”
Internet Search Data and Issue Salience: The Properties of Google Trends as a Measure of Issue Salience (2014, methodology): “Seasonal adjustment was performed using Seasonal Trend Decomposition by LOESS (STL) (Cleveland et al., 1990), which separates a time series into trend, seasonal and remainder components (Cleveland et al.”
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series (2019, methodology): “This technique is based on Generalized Extreme Studentized Deviate (ESD) test [34] to handle more than one outliers, and Seasonal and Trend Decomposition using Loess (STL) [35] to deal with the decomposition of time series data and seasonality trends.”
Predicting the present with Bayesian structural time series (2014, methodology): “Because this series has been seasonally adjusted, it makes sense to seasonally adjust the predictors, which we did by passing each series through the STL procedure in R (Cleveland et al., 1990), and subtracting off the estimated seasonal component.”