scholarly journals Testing reliability of the spatial Hurst exponent method for detecting a change point

2021 ◽  
Author(s):  
Uday Pratap Singh ◽  
Ashok Kumar Mittal
Keyword(s):  
Dynamical System ◽  
Change Point ◽  
Hurst Exponent ◽  
Abrupt Change ◽  
Climate Dynamics ◽  
Change Points ◽  
Fluctuation Analysis ◽  
Multiple Variables ◽  
Spatio Temporal ◽  
Hurst Exponents

Abstract The reliability of using abrupt changes in the spatial Hurst exponent for identifying temporal points of abrupt change in climate dynamics is explored. If a spatio-temporal dynamical system undergoes an abrupt change at a particular time, the time series of spatial Hurst exponent obtained from the data of any variable of the system should also show an abrupt change at that time. As expected, spatial Hurst exponents for each of the two variables of a model spatio-temporal system – a globally coupled map lattice based on the Burgers' chaotic map – showed abrupt change at the same time that a parameter of the system was changed. This method was applied for the identification of change points in climate dynamics using the NCEP/NCAR data on air temperature, pressure and relative humidity variables. Different abrupt change points in spatial Hurst exponents were detected for the data of these different variables. That suggests, for a dynamical system, change point detected using the two-dimensional detrended fluctuation analysis method on a single variable alone is insufficient to comment about the abrupt change in the system dynamics and should be based on multiple variables of the dynamical system.

CHANGE POINT ANALYSIS: A STATISTICAL APPROACH TO DETECT POTENTIAL ABRUPT CHANGE

2017 ◽  
Vol 79 (5) ◽  
Author(s):  
Siti Nur Afiqah Mohd Arif ◽  
Mohamad Farhan Mohamad Mohsin ◽  
Azuraliza Abu Bakar ◽  
Abdul Razak Hamdan ◽  
Sharifah Mastura Syed Abdullah
Keyword(s):  
Relative Humidity ◽  
Change Point ◽  
Abrupt Change ◽  
Carbon Dioxide Concentration ◽  
Change Points ◽  
Change Point Analysis ◽  
Total Rainfall ◽  
Essential Information ◽  
Point Analysis ◽  
Annual Means

Change-point analysis has proven to be an efficient tool in understanding the essential information contained in meteorological data, such as rainfall, ozone level, and carbon dioxide concentration. In this study, change-point analysis was used to discover potential significant changes in the annual means of total rainfall, temperature and relative humidity from 25 years of Malaysian climate data. Two methods, the CUSUM and bootstrap, were used in the analysis, where the CUSUM was used to analyze the data trends and patterns and bootstrapping was used to calculate the occurrence of change points based on the confidence level. The results of the analysis showed that potential abrupt shifts seem to have taken place in 1999, 2001 and 2002 with respect to the annual means for relative humidity, temperature and total rainfall, respectively. These identified change points will be further analyzed as potential candidates of abrupt change by extending the proposed method in a future study.

Analysis on the Process of Flow-Sediment in Jianli Reach of Yangtze River before and after the Construction of Three Gorges Project

2012 ◽  
Vol 212-213 ◽  
pp. 230-235
Author(s):  
Xiao Fang Liu ◽  
He Qing Huang ◽  
Cai Yun Deng
Keyword(s):  
Time Series ◽  
Change Point ◽  
Hurst Exponent ◽  
Yangtze River ◽  
Abrupt Change ◽  
Sediment Load ◽  
Kendall Test ◽  
Annual Runoff ◽  
Runoff Series ◽  
Anomaly Analysis

Jianli Reach has long been exposed to labile main flow and the frequent translocation between the main channel and the lateral branch. To investigate how the long-term process of flow-sediment influences the adjustment of river channel pattern, monthly time series (1951-2009) of runoff and sediment load at Jianli hydrological station of Yangtze River were analyzed using three methods: R/S analysis to estimate Hurst exponent, Mann-Kendall method and the time series anomaly analysis. The result shows that on 1 year time scale, the values of Hurst exponent are indicating persistence, that is to say, the trend of runoff and sediment in the future will generally be the same as the past, and the persistence in runoff series is stronger than that in the sediment load. The period of oscillation in annual runoff and in sediment load is about 30 years. The result of Mann-Kendall test shows an abrupt change point of runoff time-series at 1967 and an abrupt change point of sediment load time-series at 2003. And during the flood season, the values of Hurst exponent still indicate persistence, which is weaker than that in whole year correspondingly.

scholarly journals Variations of the Precipitation Extremes over the Guangdong-Hong Kong-Macao Greater Bay Area in China

2021 ◽  
Author(s):  
Xianru Li ◽  
Zhigang Wei ◽  
Huan Wang ◽  
Li Ma ◽  
Shitong Guo
Keyword(s):  
Hong Kong ◽  
Change Point ◽  
Abrupt Change ◽  
Precipitation Amount ◽  
Heavy Precipitation ◽  
Change Points ◽  
China Meteorological Administration ◽  
Annual Variations ◽  
Intensity Index ◽  
Bay Area

Abstract By using the gridded 0.25°×0.25° observation dataset of CN05.1 provided by the China Meteorological Administration, this study investigates the variations of the nine precipitation extreme indices over the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) in China in the period from 1961 to 2018. Based on trends and inter-annual variations, the nine kinds of extreme precipitation are classified into four categories: the category 1 is the very wet days (R95P), the extremely wet days (R99P), the maximum 1-day precipitation amount (RX1day) and the maximum 5-day precipitation amount (RX5day). The category 2 is the number of heavy precipitation days (R10day), the number of very heavy precipitation days (R20day) and the simple daily intensity index (SDII). The category 3 and 4 is the consecutive wet days (CWDday) and the consecutive dry days (CDDday), respectively. For the extreme precipitations in the category 1, the abrupt change point from less to more values occurs in 1991 in summer. Three abrupt change points, from less to more in 1972 and 2009, and from more to less in 1994 occur in spring. For the extreme precipitations in the category 2, the abrupt change point from less to more values occurs in 1993 in summer. Three abrupt change points, from less to more in 1965 and 2010, and from more to less in 1990 occur in spring. Annually and seasonally, the abrupt changes occur in early 2010s for CWDday which has clearly been more and for CDDday which has clearly been less. In addition, CWDday occurs abrupt change points from less to more in 1966 and from more to less in1983 in spring. The variations of these extreme precipitations have significant periodic oscillations of 3–5 years, quasi-8 years or 8–14 years. During 1961–1994, 1995–2009 and 2010–2018 three stages, the changes of the annual and most seasonal R95P, R99P, R10day, R20day and SDII are consistent with those of precipitation. The values in the latter stage are increasing compared with those in the former stage. The changes of RX1day, RX5day, CWDday and CDDday have their own characteristics.

scholarly journals Change Point Enhanced Anomaly Detection for IoT Time Series Data

Water ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 1633
Author(s):  
Elena-Simona Apostol ◽  
Ciprian-Octavian Truică ◽  
Florin Pop ◽  
Christian Esposito
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Change Point ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Change Point Detection ◽  
Change Points ◽  
Series Data ◽  
Prediction And Forecasting ◽  
Point Detection

Due to the exponential growth of the Internet of Things networks and the massive amount of time series data collected from these networks, it is essential to apply efficient methods for Big Data analysis in order to extract meaningful information and statistics. Anomaly detection is an important part of time series analysis, improving the quality of further analysis, such as prediction and forecasting. Thus, detecting sudden change points with normal behavior and using them to discriminate between abnormal behavior, i.e., outliers, is a crucial step used to minimize the false positive rate and to build accurate machine learning models for prediction and forecasting. In this paper, we propose a rule-based decision system that enhances anomaly detection in multivariate time series using change point detection. Our architecture uses a pipeline that automatically manages to detect real anomalies and remove the false positives introduced by change points. We employ both traditional and deep learning unsupervised algorithms, in total, five anomaly detection and five change point detection algorithms. Additionally, we propose a new confidence metric based on the support for a time series point to be an anomaly and the support for the same point to be a change point. In our experiments, we use a large real-world dataset containing multivariate time series about water consumption collected from smart meters. As an evaluation metric, we use Mean Absolute Error (MAE). The low MAE values show that the algorithms accurately determine anomalies and change points. The experimental results strengthen our assumption that anomaly detection can be improved by determining and removing change points as well as validates the correctness of our proposed rules in real-world scenarios. Furthermore, the proposed rule-based decision support systems enable users to make informed decisions regarding the status of the water distribution network and perform effectively predictive and proactive maintenance.

Testing for long memory in the presence of a general trend

2001 ◽  
Vol 38 (04) ◽  
pp. 1033-1054 ◽  
Author(s):  
Liudas Giraitis ◽  
Piotr Kokoszka ◽  
Remigijus Leipus
Keyword(s):  
Long Memory ◽  
Change Point ◽  
General Trend ◽  
Quantitative Description ◽  
Stationary Sequence ◽  
Change Points ◽  
Asymptotic Size ◽  
Short Memory ◽  
The Impact ◽  
Do So

The paper studies the impact of a broadly understood trend, which includes a change point in mean and monotonic trends studied by Bhattacharyaet al.(1983), on the asymptotic behaviour of a class of tests designed to detect long memory in a stationary sequence. Our results pertain to a family of tests which are similar to Lo's (1991) modifiedR/Stest. We show that both long memory and nonstationarity (presence of trend or change points) can lead to rejection of the null hypothesis of short memory, so that further testing is needed to discriminate between long memory and some forms of nonstationarity. We provide quantitative description of trends which do or do not fool theR/S-type long memory tests. We show, in particular, that a shift in mean of a magnitude larger thanN-½, whereNis the sample size, affects the asymptotic size of the tests, whereas smaller shifts do not do so.

scholarly journals Multi-periodic climate dynamics: spectral analysis of long-term instrumental and proxy temperature records

2013 ◽  
Vol 9 (1) ◽  
pp. 447-452 ◽  
Author(s):  
H.-J. Lüdecke ◽  
A. Hempelmann ◽  
C. O. Weiss
Keyword(s):  
Pearson Correlation ◽  
Temperature Drop ◽  
Ice Cores ◽  
Climate Dynamics ◽  
Fluctuation Analysis ◽  
Harmonic Decomposition ◽  
The Mean ◽  
Temperature Records ◽  
Instrumental Records

Abstract. The longest six instrumental temperature records of monthly means reach back maximally to 1757 AD and were recorded in Europe. All six show a V-shape, with temperature drop in the 19th and rise in the 20th century. Proxy temperature time series of Antarctic ice cores show this same characteristic shape, indicating this pattern as a global phenomenon. We used the mean of the six instrumental records for analysis by discrete Fourier transform (DFT), wavelets, and the detrended fluctuation analysis (DFA). For comparison, a stalagmite record was also analyzed by DFT. The harmonic decomposition of the abovementioned mean shows only six significant frequencies above periods over 30 yr. The Pearson correlation between the mean, smoothed by a 15-yr running average (boxcar) and the reconstruction using the six significant frequencies, yields r = 0.961. This good agreement has a > 99.9% confidence level confirmed by Monte Carlo simulations. It shows that the climate dynamics is governed at present by periodic oscillations. We find indications that observed periodicities result from intrinsic dynamics.

scholarly journals Analysis on the Variation of Hydro-Meteorological Variables in the Yongding River Mountain Area Driven by Multiple Factors

2021 ◽  
Vol 13 (16) ◽  
pp. 3199
Author(s):  
Kaijie Niu ◽  
Qingfang Hu ◽  
Yintang Wang ◽  
Hanbo Yang ◽  
Chuan Liang ◽  
...  
Keyword(s):  
Abrupt Change ◽  
Change Points ◽  
Meteorological Variables ◽  
Main Stream ◽  
Mountain Area ◽  
Runoff Series ◽  
Annual Scale ◽  
The Yongding River ◽  
Hydrological Station ◽  
Yongding River

In recent decades, strong human activities have not only brought about climate change including both global warming and shifts in the weather patterns but have also caused anomalous variations of hydrological elements in different basins all around the world. Studying the mechanisms and causes of these hydrological variations scientifically is the basis for the management of water resources and the implementation of ecological protection. Therefore, taking the Yongding River mountain area as a representative watershed in China, the changes of different observed and simulated hydro-meteorological variables and their possible causes are analyzed on an inter-annual scale based on ground based observations and remotely sensed data of hydrology, meteorology and underlying surface characteristics from 1956 to 2016. The results show that the annual natural runoff of Guanting hydrological station in the main stream of the Yongding River, Cetian hydrological station and Xiangshuibao hydrological station in the tributary of the Yongding River all have a significant decreasing trend and abrupt changes, and all the abrupt change points of the annual natural runoff series of the three hydrological stations appear in the early 1980s. On the inter-annual scale, the water balance model with double parameters is unable to effectively simulate the natural surface runoff after the abrupt change points. The annual average precipitation after the abrupt change points decreases by no more than 10%, compared with that before the abrupt change points. However, the precipitation from July to August, which is the main runoff-production period, decreases by more than 25%, besides the intra-annual temporal distribution of precipitation becoming uniform and a significant decrease in effective rainfall, which is the source of the runoff. Meanwhile, the NDVI in the basin show an increasing trend, while the groundwater level and land water storage decrease significantly. These factors do not lead only to the continuous reduction of the annual natural runoff in the Yongding River mountain area from 1956 to 2016, but also result in significant changes of the hydro-meteorological relationship in the basin.

scholarly journals Closed-Form Estimation of Multiple Change-Point Models

2013 ◽  
Author(s):  
Greg Jensen
Keyword(s):  
Time Series ◽  
Linear Regression ◽  
Change Point ◽  
Marginal Likelihood ◽  
Stationary Time Series ◽  
Change Points ◽  
Model Complexity ◽  
Marginal Model ◽  
General Strategy ◽  
Change Point Models

Identifying discontinuities (or change-points) in otherwise stationary time series is a powerful analytic tool. This paper outlines a general strategy for identifying an unknown number of change-points using elementary principles of Bayesian statistics. Using a strategy of binary partitioning by marginal likelihood, a time series is recursively subdivided on the basis of whether adding divisions (and thus increasing model complexity) yields a justified improvement in the marginal model likelihood. When this approach is combined with the use of conjugate priors, it yields the Conjugate Partitioned Recursion (CPR) algorithm, which identifies change-points without computationally intensive numerical integration. Using the CPR algorithm, methods are described for specifying change-point models drawn from a host of familiar distributions, both discrete (binomial, geometric, Poisson) and continuous (exponential, Gaussian, uniform, and multiple linear regression), as well as multivariate distribution (multinomial, multivariate normal, and multivariate linear regression). Methods by which the CPR algorithm could be extended or modified are discussed, and several detailed applications to data published in psychology and biomedical engineering are described.

Sign in / Sign up

Export Citation Format

Share Document