scholarly journals Deformation monitoring and prediction for residential areas in the Panji mining area based on an InSAR time series analysis and the GM-SVR model

2019 ◽  
Vol 11 (1) ◽  
pp. 738-749
Author(s):  
Jinchao Li ◽  
Fei Gao ◽  
Jiaguo Lu ◽  
Tingye Tao
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Mining Area ◽  
Deformation Monitoring ◽  
Dynamic Monitoring ◽  
Ground Subsidence ◽  
Support Vector ◽  
Residential Areas ◽  
Mining Areas ◽  
Series Analysis

Abstract Underground coal mining activities often cause ground subsidence and damage to surface construction, which seriously threatens the lives and property of residents in mining areas. In this paper, the deformation of the Yang Juzhuang village, which is a residential area in the Huainan mining area (China), was monitored through an interferometric synthetic aperture radar (InSAR) time series analysis. The vertical displacements were detected using thirteen Sentinel-1A images that were acquired between December 2016 and May 2017. The validity and applicability of the method are verified by comparing the acquired images with the GPS measurement results. Because of the deformation characteristics of the mining area, a prediction model that is combined with a grey support vector machine regression (GM-SVR) is proposed, and the practical effects of the model are verified using the deformation monitoring results of the study area. The combination of this model and SBAS-InSAR provides rapid dynamic monitoring and enables the issuance of disaster warnings in the region.

scholarly journals Nationwide urban ground deformation monitoring in Japan using Sentinel-1 LiCSAR products and LiCSBAS

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yu Morishita
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Urban Areas ◽  
Ground Deformation ◽  
Processing System ◽  
Economic Loss ◽  
Deformation Monitoring ◽  
Ground Subsidence ◽  
Detection Mechanism ◽  
Series Analysis

AbstractGround subsidence in urban areas is a significant problem because it increases flood risk, damages buildings and infrastructure, and results in economic loss. Continual monitoring of ground deformation is important for early detection, mechanism understanding, countermeasure implementation, and deformation prediction. The Sentinel-1 satellite constellation has globally and freely provided frequent and abundant SAR data and enabled nationwide deformation monitoring through InSAR time series analysis. LiCSAR, an automatic Sentinel-1 interferometric processing system, has produced abundant interferograms with global coverage, and the products are freely accessible and downloadable through a web portal. LiCSBAS, an open source InSAR time series analysis package integrated with LiCSAR, enables users to obtain the deformation time series easily and quickly. In this study, spatially and temporally detailed deformation time series and velocities from the LiCSAR products using LiCSBAS for 73 major urban areas in Japan during 2014–2020 were derived. All LiCSBAS processing was automatically performed using predefined parameters. Many deformation signals with various temporal and spatial features, such as linear subsidence in Hirosaki, Kujyukuri, Niigata, and Kanazawa, episodic subsidence in Sanjo, annual vertical fluctuation in Hirosaki, Yamagata, Yonezawa, Ojiya, and Nogi, and linear uplift in Chofu were detected. Unknown small nonlinear uplift signals were found in Nara and Osaka in 2018. Complex postseismic deformations from the 2016 Kumamoto earthquake were also revealed. All the deformation data obtained in this study are available on an open repository and are expected to be used for further research, investigation, or interpretation. This nationwide monitoring approach using the LiCSAR products and LiCSBAS is easy to implement and applicable to other areas worldwide.

scholarly journals An Improved Demand Forecasting Model Using Deep Learning Approach and Proposed Decision Integration Strategy for Supply Chain

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Zeynep Hilal Kilimci ◽  
A. Okay Akyuz ◽  
Mitat Uysal ◽  
Selim Akyokus ◽  
M. Ozan Uysal ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Support Vector Regression ◽  
Historical Data ◽  
Demand Forecasting ◽  
Support Vector ◽  
Series Analysis ◽  
Integration Strategy ◽  
Forecasting System

Demand forecasting is one of the main issues of supply chains. It aimed to optimize stocks, reduce costs, and increase sales, profit, and customer loyalty. For this purpose, historical data can be analyzed to improve demand forecasting by using various methods like machine learning techniques, time series analysis, and deep learning models. In this work, an intelligent demand forecasting system is developed. This improved model is based on the analysis and interpretation of the historical data by using different forecasting methods which include time series analysis techniques, support vector regression algorithm, and deep learning models. To the best of our knowledge, this is the first study to blend the deep learning methodology, support vector regression algorithm, and different time series analysis models by a novel decision integration strategy for demand forecasting approach. The other novelty of this work is the adaptation of boosting ensemble strategy to demand forecasting system by implementing a novel decision integration model. The developed system is applied and tested on real life data obtained from SOK Market in Turkey which operates as a fast-growing company with 6700 stores, 1500 products, and 23 distribution centers. A wide range of comparative and extensive experiments demonstrate that the proposed demand forecasting system exhibits noteworthy results compared to the state-of-art studies. Unlike the state-of-art studies, inclusion of support vector regression, deep learning model, and a novel integration strategy to the proposed forecasting system ensures significant accuracy improvement.

scholarly journals Landslide displacement prediction using the GA-LSSVM model and time series analysis: a case study of Three Gorges Reservoir, China

2017 ◽  
Author(s):  
Tao Wen ◽  
Huiming Tang ◽  
Yankun Wang ◽  
Chengyuan Lin ◽  
Chengren Xiong
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Periodic Component ◽  
Economic Losses ◽  
Support Vector ◽  
Series Analysis ◽  
Trend Component ◽  
Geological Conditions ◽  
Component Displacement

Abstract. Predicting landslide displacement is challenging, but accurate predictions can prevent casualties and economic losses. Many factors can affect the deformation of a landslide, including the geological conditions, rainfall, and reservoir water level. Time series analysis was used to decompose the cumulative displacement of landslide into a trend component and a periodic component. Then the least squares support vector machine (LSSVM) model and genetic algorithm (GA) were used to predict landslide displacement, and we selected a representative landslide with step-like deformation as a case study. The trend component displacement, which is associated with the geological conditions, was predicted using a polynomial function, and the periodic component displacement which is associated with external environmental factors, was predicted using the GA-LSSVM model. Furthermore, based on a comparison of the results of the GA-LSSVM model and those of other models, the GA-LSSVM model was superior to other models in predicting landslide displacement, with the smallest root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results of the case study suggest that the model can provide good consistency between measured displacement and predicted displacement, and periodic displacement exhibited good agreement with trends in the major influencing factors.

scholarly journals GPS and InSAR Time Series Analysis: Deformation Monitoring Application in a Hydraulic Engineering Resettlement Zone, Southwest China

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Ruya Xiao ◽  
Xiufeng He
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Monitoring System ◽  
Land Surface ◽  
Southwest China ◽  
Deformation Monitoring ◽  
Hydraulic Engineering ◽  
Ground Movement ◽  
Series Analysis ◽  
Gps Monitoring

Booming development of hydropower in China has resulted in increasing concerns about the related resettlement issues. Both global positioning system (GPS) and persistent scatterer interferometric synthetic aperture radar (InSAR) time series analysis are applied to measuring the magnitude and monitoring the spatial and temporal variations of land surface displacement in Hanyuan, a hydraulic engineering resettlement zone, southwest China. The results from the GPS monitoring system established in Hanyuan match well the digital inclinometer results, suggesting that the GPS monitoring system can be employed as a complement to the traditional ground movement monitoring methods. The InSAR time series witness various patterns and magnitudes of deformation in the resettlement zone. Combining the two complementary techniques will overcome the limitations of the single method.

Sign in / Sign up

Export Citation Format

Share Document