Multiple Changepoint Detection via Genetic Algorithms

Li, Shanghong; Lund, Robert

doi:10.1175/2011jcli4055.1

Cited by 77 publications

(90 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As changepoint effects in the composite series should be minimal, any identified changepoints are attributed to the target series. The GA development here is similar to that in Li and Lund (2012), but has seasonal aspects.…”

Section: Genetic Algorithm and Spatial Smoothing Methodssupporting

confidence: 63%

“…, t k , N, P is a penalty term that accounts for the number and types of model parameters, and log 2 indicates logarithm base 2. MDL methods have yielded promising results in recent changepoint studies (Davis et al 2006;Lu et al 2010;Li and Lund 2012). The MDL penalty is based on minimum description length information theoretic principles.…”

Section: Estimation Of the Changepoint Configurationmentioning

confidence: 99%

“…, s T * , f, and s 2 are obtained. This computation is not overly difficult and is described in Li and Lund (2012).…”

Section: Estimation Of the Changepoint Configurationmentioning

confidence: 99%

See 2 more Smart Citations

Trends in Extreme U.S. Temperatures

Lee

Lund

2014

Journal of Climate

Self Cite

View full text Add to dashboard Cite

This paper develops trend estimation techniques for monthly maximum and minimum temperature time series observed in the 48 conterminous United States over the last century. While most scientists concur that this region has warmed on aggregate, there is no a priori reason to believe that temporal trends in extremes and averages will exhibit the same patterns. Indeed, under minor regularity conditions, the sample partial sum and maximum of stationary time series are asymptotically independent (statistically). Previous authors have suggested that minimum temperatures are warming faster than maximum temperatures in the United States; such an aspect can be investigated via the methods discussed in this study. Here, statistical models with extreme value and changepoint features are used to estimate trends and their standard errors. A spatial smoothing is then done to extract general structure. The results show that monthly maximum temperatures are not often greatly changing-perhaps surprisingly, there are many stations that show some cooling. In contrast, the minimum temperatures show significant warming. Overall, the southeastern United States shows the least warming (even some cooling), and the western United States, northern Midwest, and New England have experienced the most warming.

show abstract

Section: Genetic Algorithm and Spatial Smoothing Methodssupporting

confidence: 63%

Section: Estimation Of the Changepoint Configurationmentioning

confidence: 99%

See 1 more Smart Citation

Trends in Extreme U.S. Temperatures

Lee

Lund

2014

Journal of Climate

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lu et al (2010) first employed the MDL criterion in climatic changepoint research. Li and Lund (2012) introduced genetic algorithms into the MDL technique to optimize the objective function, and their improvements have led to an effective detection of the changepoints in annual TC genesis series over the North Atlantic basin. The form of MDL scores is given by…”

Section: B Methods Of Changepoint Detection For Decadal Changementioning

confidence: 99%

Decadal Change in Tropical Cyclone Activity over the South China Sea around 2002/03

Yao

Zhong

2015

Journal of Climate

View full text Add to dashboard Cite

This study investigates the decadal change in tropical cyclone (TC) activity over the South China Sea (SCS) in the boreal summer (June-August) since the early 1990s and explores possible causes behind it. Results show that the SCS TC activity experienced an abrupt decadal decrease at around 2003/03. Compared to the TC activities from the early 1990s to 2002, the number of TCs formed in the SCS markedly decreased from 2003 through the early 2010s. Moreover, most of the TCs were primarily confined within the SCS basin during this period. The TCs that formed during the period of 2003-11 usually moved west-northwestward and rapidly weakened after making landfall. It is found that a significant decadal-scale sea surface temperature (SST) warming occurred in the northern Indian Ocean and the western Pacific Ocean after 2002 while convection intensified over the tropical regions between 608 and 808E and around 1508E, respectively. The warm SST anomalies induced an anomalous subsiding flow over the SCS basin via the Walker-like (zonal) circulation. Meanwhile, anomalously dry, sinking air around 58-208N derived from local Hadley (meridional) circulation reinforced the subsiding flow of the zonal circulation. The above circulation patterns suppressed TC genesis over the northern SCS, leading to the decadal decrease in TC activity that occurred around 2002/03. In addition, in conjunction with the local anomalous easterly flow, the intraseasonal atmospheric variability over the SCS has decreased since the early 2000s. This is unfavorable for the development of synoptic-scale disturbances and may also contribute to the decadal decrease in TC activity.

show abstract

“…Recent work on detecting mean shift in climatic series includes [1,18,19,28]. [28] also provided a good literature review on the matter, while [25] provided a review and comparison of less recent techniques.…”

Section: Introductionmentioning

confidence: 99%

Detecting change-points in extremes

Dupuis

Sun

Wang

2015

Statistics and Its Interface

View full text Add to dashboard Cite

Even though most work on change-point estimation focuses on changes in the mean, changes in the variance or in the tail distribution can lead to more extreme events. In this paper, we develop a new method of detecting and estimating the change-points in the tail of multiple time series data. In addition, we adapt existing tail change-point detection methods to our specific problem and conduct a thorough comparison of different methods in terms of performance on the estimation of change-points and computational time. We also examine three locations on the U.S. northeast coast and demonstrate that the methods are useful for identifying changes in seasonally extreme warm temperatures.

show abstract

Multiple Changepoint Detection via Genetic Algorithms

Cited by 77 publications

References 28 publications

Trends in Extreme U.S. Temperatures

Trends in Extreme U.S. Temperatures

Decadal Change in Tropical Cyclone Activity over the South China Sea around 2002/03

Detecting change-points in extremes

Contact Info

Product

Resources

About