Changes In Time Series Research Articles

Refined composite multiscale fluctuation-based dispersion Lempel–Ziv complexity for signal analysis

Dispersion Lempel–Ziv complexity (DLZC) and multiscale DLZC (MDLZC) are very recently introduced complexity indicators to quantify the dynamic change of time series in acoustics signals. They introduce the mapping steps of dispersion entropy (DE), which can effectively identify time series with different characteristics, but ignore the fluctuation information and have poor stability. In order to overcome these shortcomings, this paper firstly adds fluctuation information to DLZC and proposes fluctuation-based DLZC (FDLZC) as an alternative to the classical time series complexity index, followed by introducing an improved coarse-graining operation to propose the refined composite multiscale FDLZC (RCMFDLZC), which increases the number of features and also ensures the stability of FDLZC, and finally select the subsequence containing the most information by the minimum redundancy maximum relevance (mRMR) feature selection algorithm for subsequent experiments. The experimental results show that the extracted RCMFDLZC features have the strongest separability and better clustering effect in both bearing fault signals and ship radiated noise signals, and the RCMFDLZC-based signal analysis method also has higher recognition rate compared with other methods in bearing fault diagnosis and ship signal classification.

A combined Gaussian process regression and one-dimensional least squares harmonic method for tidal current prediction

Predictions of tidal currents are required for various activities in the maritime industry, including marine power exploitation, operational forecasting, and coastal engineering. In addition to the conventional least squares harmonic method (LSHM) and numerical simulation, a machine learning algorithm has recently been developed and applied for predicting tidal currents in time series. Gaussian Process Regression (GPR) is one of the most important machine learning algorithms due to its ability to process time-series data. In this paper, we propose a combined one-dimensional LSHM and GPR method for predicting depth-averaged current velocity vectors according to time-series changes of water surface elevation due to tide. LSHM firstly decomposes water surface elevation time series into a number of possible constituents (i.e., amplitudes, phase-lags) according to known tidal frequencies. For each of the contributing constituents, GPR is then applied to produce the corresponding current generator using known tidal current as training data. The training data are generated by numerical simulations representing different coastal settings. The predicted tidal current is calculated according to the previously trained GPR model. As a comparison, we also generated tidal current predictions using a conventional two-dimensional LSHM. It is found that the tidal currents predicted using the sequence of computations proposed in this paper show comparable results with slightly better accuracy than conventional two-dimensional LSHM. The results from this study could provide an alternative method of tidal current prediction, minimising the need for the laborious re-runs of numerical simulations and lengthy current observations, as well as removing the requirement to carry out a two-dimensional analysis of the tidal current using LSHM.

Emergence of heartbeat frailty in advanced age I: perspectives from life-long EKG recordings in adult mice

The combined influences of sinoatrial nodal (SAN) pacemaker cell automaticity and its response to autonomic input determine the heart’s beating interval variability and mean beating rate. To determine the intrinsic SAN and autonomic signatures buried within EKG RR interval time series change in advanced age, we measured RR interval variability before and during double autonomic blockade at 3-month intervals from 6 months of age until the end of life in long-lived (those that achieved the total cohort median life span of 24 months and beyond) C57/BL6 mice. Prior to 21 months of age, time-dependent changes in intrinsic RR interval variability and mean RR interval were relatively minor. Between 21 and 30 months of age, however, marked changes emerged in intrinsic SAN RR interval variability signatures, pointing to a reduction in the kinetics of pacemaker clock mechanisms, leading to reduced synchronization of molecular functions within and among SAN cells. This loss of high-frequency signal processing within intrinsic SAN signatures resulted in a marked increase in the mean intrinsic RR interval. The impact of autonomic signatures on RR interval variability were net sympathetic and partially compensated for the reduced kinetics of the intrinsic SAN RR interval variability signatures, and partially, but not completely, shifted the EKG RR time series intervals to a more youthful pattern. Cross-sectional analyses of other subsets of C57/BL6 ages indicated that at or beyond the median life span of our longitudinal cohort, noncardiac, constitutional, whole-body frailty was increased, energetic efficiency was reduced, and the respiratory exchange ratio increased. We interpret the progressive reduction in kinetics in intrinsic SAN RR interval variability signatures in this context of whole-body frailty beyond 21 months of age to be a manifestation of “heartbeat frailty.”

Model for estimating statistical characteristics of the pre-stroke warehouse process based on average monthly temperatures analysis

The possibilities of an improved autoregression model and an integrated moving average (ARMAS) for the analysis of non-stationary data and the identification of long-term trends in the processes under study are considered. The proposed model can be used to study the observed processes in various areas of human activity: the analysis of the observed trajectories of the movement of aircraft, in particular unmanned aerial vehicles, meteorological processes that reflect the state of the atmosphere. The mathematical apparatus developed in the article was used to analyze changes in the atmospheric temperature time series observed for a long time, the average annual temperatures were estimated, followed by sliding smoothing with a low-frequency filter.
 It is shown that the removal of the seasonal component in the ARPSS model eliminates or distorts significantly the trend and has little effect on the stationary component of the ARPSS process. The operation of de-trending has little effect on the properties of the seasonal component and the stationary component of the process. To assess the trend, the mean annual temperatures were preliminarily obtained. The use of moving averaging, which removes the seasonal component from the average monthly temperatures, makes it possible to find a weak long-term trend. The results obtained in the work can be used to analyze medium-term and long-term changes in atmospheric phenomena, to refine the results obtained by traditional methods of processing results and methods of mathematical statistics, as well as in other areas of human activity.

Geochemical evolution of a sublacustrine hydrothermal vent system: Temporal constraints imposed by reactive transport modeling

Studies of heat and mass transport in hydrothermal systems are challenging owing to the complex feedback that exists between chemical and physical processes. Taking full advantage of the existing geochemical framework recently recognized for sublacustrine vent fluids in the Stevenson Island Deep Hole, Yellowstone Lake, here we apply a multiphase reactive transport model, coupling hydraulic and thermal effects, to simulate time series changes in mineralization associated with venting of vapor-dominated hydrothermal fluids. This distinctive region of the lake floor is characterized by a series of overlapping depressions hosting sites of active venting. Model results show that the addition of high enthalpy steam enriched in CO2 and H2S, creates acidic and reducing conditions, while heating entrained lake water and coexisting sediment to temperatures in excess of 174 °C. The diatomaceous silica-rich substrate is predicted to dissolve, being replaced largely by pyrite, quartz, and kaolinite, in good agreement with the observed vent mineralization and fluid chemistry. Data suggest that vent-related mineral dissolution and transformation processes occur rapidly, on the order of 1 ka for the spatial scale of the modeled-up flow zone considered. The accuracy of time series changes predicted however, is explicitly linked to a number of physical and chemical factors imposed on the model, including source fluid, flow rate and gas enrichment, and sediment thermal conductivity, permeability, and reactive surface area, as well as mineral reaction rate data for primary and secondary alteration phases. When combined with robust field observations, as is the case here, reactive transport models can elucidate important, if not fundamental, controls on the temporal and spatial evolution of the geochemistry of modeled system, challenging chemical, and physical conditions notwithstanding.

A combined model based on sparrow search optimized BP neural network and Markov chain for precipitation prediction in Zhengzhou City, China

Abstract Simulation and prediction of precipitation time series changes are important for revealing global climate change patterns and understanding surface hydrological processes. However, precipitation is influenced by a variety of factors together, showing the characteristics of nonlinear variation patterns. Given that backpropagation (BP) neural network has a strong mapping ability for nonlinear fitting, we consider using BP neural network for precipitation prediction, then use Sparrow Search Algorithm (SSA) to optimize BP network initial threshold and weight information to improve the efficiency of precipitation prediction. To further enhance model predictive performance, the Markov model is employed to predict the residual series of the SSA-BP model, so as to finally construct a combined SSA-BP-Markov model of precipitation. In this paper, the model is used to simulate the rainfall prediction in Zhengzhou City, Henan Province, China, and to compare and analyze with the other traditional models. The empirical prediction results show that the SSA-BP-Markov model is more accurate and the convergence of the algorithm is better. The model provides a new way of thinking for precipitation prediction and is also useful for predicting precipitation in other regions.

Fully integrated photoacoustic microscopy and photoplethysmography of human in vivo

Photoacoustic microscopy (PAM) is used to visualize blood vessels and to monitor their time-dependent changes. Photoplethysmography (PPG) measures hemodynamic time-series changes such as heart rate. However, PPG’s limited visual access to the dynamic changes of blood vessels has prohibited further understanding of hemodynamics. Here, we propose a novel, fully integrated PAM and photoplethysmography (PAM-PPG) system to understand hemodynamic features in detail. Using the PAM-PPG system, we simultaneously acquire vascular images (by PAM) and changes in the blood volume (by PPG) from human fingers. Next, we determine the heart rate from changes in the PA signals, which match well with the PPG signals. These changes can be measured if the blood flow is not blocked. From the results, we believe that PAM-PPG could be a useful clinical tool in various clinical fields such as cardiology and endocrinology.

Financial Data Anomaly Discovery Using Behavioral Change Indicators

In this article we present an approach to financial data analysis and anomaly discovery. In our view, the assessment of performance management requires the monitoring of financial performance indicators (KPIs) and the characteristics of changes in KPIs over time. Based on this assumption, behavioral change indicators (BCIs) are introduced to detect and evaluate the changes in traditional KPIs in time series. Three types of BCIs are defined: absolute change indicators (BCI-A), relative change indicators (ratio indicators BCI-RE), and delta change indicators (D-BCI). The technique and advantages of using BCIs to identify unexpected deviations and assess the nature of KPI value changes in time series are discussed and illustrated in case studies. The architecture of the financial data analysis system for financial data anomaly detection is presented. The system prototype uses the Camunda business rules engine to specify KPIs and BCI thresholds. The prototype was successfully put into practice for an analysis of actual financial records (historical data).

RECURRENT NEURAL NETWORK FOR MONITORING MOUSE EMBRYONIC STEM CELL COLONY IN VITRO USING TIME-LAPSE FLUORESCENCE MICROSCOPY IMAGES

Embryonic stem cells represent a cellular resource for basic biological studies and used as medically relevant cells in vitro. Time-lapse fluorescence microscopy images taken during cell culture are frequently used to monitor time-series morphology changes and status transitions of embryonic stem cell (ESC) colonies, and to select culture medium for maintaining ESCs in undifferentiated or early differentiated stages. Recurrent Neural Network (RNN)-based prediction of time-lapse images generated in future culture can be an effective method for monitoring. Because status transitions of ESC colonies are usually complete in a few consecutive frames of time-lapse images, this study proposes a Long Short-Term Memory (LSTM) structure that incorporates a few new images taken from incubators to learn the newest colony morphology and status for a new RNN training and thus generate predicted time-lapse images. Image processing procedures of entropy, bi-lateral filter and convex-hull calculations are implemented to extract colony regions on the images. Morphology changes and status transitions are then calculated using the extracted ESC colonies. The experiment results show predicted time-lapse images in 5h future and the colony morphology and status transition calculation give accurate visualization and quantitative analyses to monitor the mouse ESCs in vitro at the undifferentiated or early differentiated stages.

Dynamic Copulas for Monotonic Dependence Change in Time Series

Dynamic Copulas for Monotonic Dependence Change in Time Series

Spatial and temporal characteristics of surface soil moisture in a disturbed coal mining area of Chinese Loess Plateau.

Soil water content is an important variable in hydrology and many related disciplines. It affects runoff from precipitation, groundwater recharge, and evapotranspiration. This research used the coal mining area of the Changhe River Basin in the Loess Plateau as a study and using SAR (Synthetic Aperture Radar) data, the surface soil water in 24 days (From Jan 25, 2018 to Dec 10, 2019) was estimated using a radar signal change detection algorithm. The temporal and spatial variation characteristics of surface soil water inside and outside the disturbed area were compared and analyzed. An empirical orthogonal function (EOF) analysis method was used to analyze the potential temporal and spatial variation of surface soil water, and to detect the regional soil water variation under coal mining disturbances to better understand the different potential modes of spatial variation of soil water in the unobserved time. The results showed that the average surface soil water content in the study area changed with season, showing a dry-wet-dry variation. Moreover, it was significantly affected by precipitation factors, and its response to precipitation had a hysteresis effect. From the perspective of spatial variation, the influence of coal mining disturbance on surface soil moisture was not obvious. From the perspective of time series change, moving from wet to dry conditions, the soil in the disturbed area dried faster than the soil in the undisturbed area after soil wetted. When moving from drying to wetting, the soil in the disturbed area was quickly wetted. The EOF analysis showed that most observed spatial variability of soil moisture was stable in time. The study was conducted in a disturbed area and an undisturbed area for single EOF analysis, and the results showed that the EOF mode of the disturbed area was closer to that of the whole study area. By comparing the two subregions and the entire study area, it was found that the changes of correlation values were related to soil texture, bulk density, altitude and slope, indicating that the soil texture of the two subregions may be different at different elevations, and may also be related to the change of the original soil structure in the disturbed area. Overall, the EOF mode of the disturbed area determined the EOF mode of the entire study area.

Estimating Time-Series Changes in Social Sensitivity for COVID-19 @ Twitter in Japan

The global outbreak of COVID-19 is now putting enormous pressure on society to change our traditional social behavior. Government officials are also forced to make short-term decisions based on limited information for public health, and investor sentiment about the infection situation in each country has a significant impact on the stock market. In this paper, we attempt to visualize the time series of indexed social sentiment in Japan under the COVID-19 pandemic by using a neural network approach, and clarify changes in the sensitivity of citizens to the coronavirus. The sentiment was classified for Twitter tweets that matched the keywords for which the government was asked to restrict action, and sentiment trends were identified for the period from before the outbreak to the fifth wave of infection in Tokyo, Sapporo, Osaka, and Fukuoka. The indices obtained show a correlation with the number of infected cases by region and with national and local events, and in global cities such as Tokyo and Osaka as they experienced waves of infections and emergency declarations, sensitivity gradually became paralyzed, and parallel trends in sentiment waveforms were observed among regions.

Simulated sea levels during 1948–2009 in a global ocean-sea ice model for OMIP

This paper assesses the ability of the State Key Laboratory of Atmospheric Science and Geophysical Fluid Dynamics of the Institute of Atmospheric Physics (LASG/IAP) Climate System Ocean Model version 3 (LICOM3) to simulate sea levels. For the time series of global changes, most of the global mean steric sea level (SSL) changes were dominated by thermosteric sea level (TSSL) changes in the upper 700 m, with a relatively small contribution from halosteric sea level (HSSL). LICOM3 can reproduce the observed dynamic sea level (DSL) in most regions to reflect the spatial patterns of regional changes. Deviations between LICOM3 and observations were mainly concentrated in the western boundary current and the tropical eastern Pacific. The departure in the western boundary current was primarily related to the model resolution. LICOM3 could not depict DSL changes in the high latitudes where the mesoscale eddies were active. The excessive negative trend in the tropical eastern Pacific was mainly caused by the trend error in the CORE-II forcing products. For the sea level variability, the analysis results of different DSL periods showed that the LICOM3 model could simulate interannual and decadal variability and the satellite altimeter period trend. At least 50 years of data were used to separate the decadal variability and long-term trend. The decadal variability had no significant effect on the 50-year long-term trend change in the DSL in the tropical western Pacific.Analysis of sea level component contributions showed that the changes in global time series, spatial patterns, and sea level variability mainly resulted from the change in TSSL. The TSSL changes in the upper 700 m could roughly reflect the TSSL changes for the whole depth, except for the North Atlantic and the Southern Ocean. In the Atlantic, the contribution of HSSL was comparable to and compensated by TSSL. When compared with reanalysis, the simulation generated differences in the Southern Ocean and North Atlantic. The linear trend of TSSL simulated by LICOM3 was much stronger than that simulated by reanalysis. The deviation of the Southern Ocean may be related to the CORE-II forcing product. The lack of observations in the Southern Ocean led to the uncertainty of the CORE-II forcing product.

Sequential detection of a temporary change in multivariate time series

In this work, we aim to provide a new and efficient recursive detection method for temporarily monitored signals. Motivated by the case of the propagation of an event over a field of sensors, we assumed that the change in the statistical properties in the monitored signals can only be temporary. Unfortunately, to our best knowledge, existing recursive and simple detection techniques such as the ones based on the cumulative sum (CUSUM) do not consider the temporary aspect of the change in a multivariate time series. In this paper, we propose a novel simple and efficient sequential detection algorithm, named Temporary-Event-CUSUM (TE-CUSUM). By combining with a new adaptive way to aggregate local CUSUM variables from each data stream, we empirically show that the TE-CUSUM has a very good detection rate in the case of an event passing through a field of sensors in a very noisy environment.

Calculating the Coverage Rate of a Transportation-Based Flood Warning Dissemination System in Brisbane

There is a growing need to introduce warning dissemination systems in disaster-prone regions to improve the coverage of information distribution. In this study, a warning dissemination system was designed in which disaster information transmitted by a global navigation satellite system (GNSS) is received by terrestrial infrastructure, such as sirens and public transportation, converted into audio messages, and delivered automatically. The originality of the designed system lies in its appropriate integration of existing satellite systems and terrestrial infrastructure, making the system potentially applicable in many regions. First, we evaluated the effectiveness of the designed system in distributing audio messages using public buses in Brisbane, Australia, where large floods occur frequently. Real-time location information for public buses was acquired in the format of General Transit Feed Specification (GTFS), which is currently used in many countries. Time-series changes in the coverage rate relative to both the flood inundation zone and population were calculated using a geographic information system (GIS). The simulation results showed that the system could reach 60% of the flood inundation zone and 70% of the population on a holiday, indicating that the designed system could be effectively adapted to the target area. The coverage rate was found to peak during 15:00–16:00, with minimum rates observed late at night and early in the morning. These results will allow the development of an effective disaster management plan. In the future, this system will be evaluated in other regions using the same calculation process.

Detecting Outlier Machine Instances Through Gaussian Mixture Variational Autoencoder With One Dimensional CNN

Today&#x0027;s large datacenters house a massive number of machines, each of which is being closely monitored with multivariate time series (e.g., CPU idle, memory utilization) to ensure service quality. Detecting outlier machine instances with multivariate time series is crucial for service management. However, it is a challenging task due to the multiple classes and various shapes, high dimensionality, and lack of labels of multivariate time series. In this article, we propose DOMI, a novel unsupervised model that combines Gaussian mixture VAE with 1D-CNN, to <b>d</b>etect <b>o</b>utlier <b>m</b>achine <b>i</b>nstances. Its core idea is to capture the normal patterns of machine instances by learning their latent representations that consider the shape characteristics, reconstruct input data by the learned representations, and apply reconstruction probabilities to determine outliers. Moreover, DOMI interprets the detected outlier instance based on the reconstruction probability changes of univariate time series. Extensive experiments have been conducted on the dataset collected from 1821 machines with a 1.5-month-period, which are deployed in ByteDance, a top global content service provider. DOMI achieves the best F1-Score of 0.94 and AUC score of 0.99, significantly outperforming the best performing baseline method by 0.08 and 0.03, respectively. Moreover, its interpretation accuracy is up to 0.93.

A Novel Framework for Urban Flood damage Assessment

In the current study, a novel method is proposed to analyze the simultaneous impacts of non-stationarity in hydrological time series and land-use changes in urban areas to predict future floods and probable damage. For this purpose, rainfall frequency and land-use changes analyses were conducted for two time periods (first: 1979–2009 and second: 1979–2019), and the results were compared. Then, hydrologic modeling of the catchment was carried out using the HEC-HMS model, and obtained hydrographs were fed to the HEC-RAS2D model for estimating flood inundation areas. Using the financial information of assets and their damage functions, flood damages related to these two periods were evaluated through the HEC-FIA model. The results indicated that in the low return periods (e.g., 2-year flood), the damage in the second period was decreased with respect to the first one but increased for the return periods of 5 to 100 years. In the surface runoff, a 4.65% increase due to land-use change and a 12% increase due to rainfall non-stationarity signed the important role the hydrologic condition plays compared to land-use changes in flood modeling. Moreover, flood damage showed a 136% increase on average, and among the two studied factors, the non-stationarity of rainfalls is considerably more effective on flood intensification. All the points show that the studied socio-hydrological system is completely dynamic.

조경수의 생산 관리를 위한 식재 수종 및 규모의 시계열 분석 - 수도권 민간건설 아파트 단지를 중심으로 -

This study was conducted to understand the change time-series of landscape trees planted in apartment complexes and to predict the demand for pine trees among landscape trees. From 2003 to 2020, the average number of trees used in apartment complexes in the Seoul metropolitan area were 51, and various types of trees were used in the late 2010s compared to the mid-to-late 2000s. The average planting quantity was 149,567trees/1 complex, and the time series change was not noticeable. Comparing evergreen trees and deciduous trees, there was a difference between the planted species and the planted quantity. Compared to evergreen trees, deciduous trees were planted with relatively diverse species. Evergreen trees were planted in large quantities, with fewer varieties than deciduous trees. The types of trees and shrubs consist of a ratio of 6:4, and shrubs accounted for 97.6% of the total planting volume. Compared to the amount of planting, the varieties of trees planted are not diverse. When analyzing the planting status of pine trees with high preference and use value of landscaping trees, the planting volume tends to increase, and in particular, the planting ratio of large pine trees is increasing. Predicting the demand for pine tree planting in apartment complexes will continue to increase the amount of planting, especially with special trees with a root diameter of 40 cm or more. In response to these changes in demand for landscaping trees, a strategy is required to discover and produce various plant materials. In particular, since the demand for large pine trees is continuously expected to increase, production management should be carried out so that pine trees with the shape and specifications required by the market can be supplied.

Categorization and Visualization of Issue Tickets to Support Understanding of Implemented Features in Software Development Projects

Background: In most software projects, new members must comprehend the features already implemented since they are usually assigned during the project period. They often read software documents (e.g., flowcharts and data models), but such documents tend not to be updated after they are created. Herein we focus on tickets issued because they are created as a project evolves and include the latest information of the implemented features. Aim: The purpose of this paper is to clarify the way of helping new members understand the implemented features of a project by using tickets. Methodology: We propose a novel method to categorize tickets by clustering and visualizing the characteristics of each category via heatmapping and principal component analysis (PCA). Our method estimates the number of categories and categorizes issue tickets (tickets) automatically. Moreover, it has two visualizations. Ticket lifetime visualization shows the time series change to review tickets quickly, while ticket feature visualization shows the relationships among ticket categories and keywords of ticket categories using heatmapping and PCA. Results: To evaluate the effectiveness of our method, we implemented a case study. Specifically, we applied our method to an industrial software development project and interviewed the project members and external experts. Furthermore, we conducted an experiment to clarify the effectiveness of our method compared with a non-tool-assist method by letting subjects comprehend the target project, which is the same as that of the case study. These studies confirm our method supports experts’ and subjects’ comprehension of the project and its features by examining the ticket category lifetimes and keywords. Implication: Newcomers during project onboarding can utilize tickets to comprehend implemented features effectively if the tickets are appropriately structured and visualized. Conclusions: The original contribution of this paper is the proposal of the project feature comprehension method by visualizing the multi-dimensional nature of requirements in an organized and structured way based on available tickets and the result of its application to the industrial project.

Inter-Comparison of Four Models for Detecting Forest Fire Disturbance from MOD13A2 Time Series

Many models for change point detection from time series remote sensing images have been developed to date. For forest ecosystems, fire disturbance detection models have always been an important topic. However, due to a lack of benchmark datasets, it is difficult to determine which model is appropriate. Therefore, we collected and generated a benchmark dataset specifically for forest fire disturbance detection, named CUG-FFireMCD1. The CUG-FFireMCD1 contains a total of 132 pieces of MODIS MOD13A2 time series, and each time series contains at least one fire disturbance. The occurrence time for a forest fire disturbance was determined using the National Cryosphere DesertDataCenter(NCDC) website, and the precise latitude and longitude coordinates were determined using the FireCCI51 dataset. In addition, we selected four commonly used time series change detection models and validate the advantages and limitations of the four models through dataset analysis. Finally, we use the detection results of the models and their applicable scenarios to label the additional change points. The four models we used are breaks for additive season and trend (BFAST), Prophet, continuous change detection and classification (CCDC), and Landsat-based detection of trends in disturbance and recovery (LandTrendR). The experiments show that the BFAST outperformed the other three models in forest fire disturbance detection from MOD13A2 time series, with the successful-detection-proportion rate of 96.2% with the benchmark dataset. The detection effect of the Prophet model is not as good as that of BFAST, but it also performs well, with the successful-detection-proportion rate of 87.9%. The detection results of CCDC and LandTrendR are similar, and the detection success rate is lower than that of BFAST and Prophet, but their detection results can be used as data support for labeling work. However, to apply them perfectly to MOD13A2 time series change detection, it is best to do some model adaptation. In summary, the CUG-FFireMCD1 data were verified using different types of time series change detection models, and the change points we marked are credible. The CUG-FFireMCD1 will surely provide a reliable benchmark for model optimization and the accuracy verification of remote sensing time series change detection.