Abstract
Dynamic monitoring data of the groundwater level form an important basis to understand the current state of groundwater development and utilization, which is required to plan its sustainable exploitation. The dynamic data of groundwater level are typical space-time series data with the characteristics of nonlinear strong space-time correlation. However, because of the influences of human or natural factors, long-term monitoring data of the groundwater level are often incomplete to varying degrees. Consequently, the efficiency and accuracy of traditional data in-filling methods for the missing groundwater level data are low. Additionally, restoration methods based on spatio-temporal geostatistics and machine learning are not sufficiently comprehensive to consider spatio-temporal correlations, which results in low restoration accuracy. Therefore, this study was based on an analysis of the characteristics and the missing status of the groundwater level dynamic monitoring data of the pore confined aquifer III of Nantong City, east coast of China. Both the universal Kriging (UK) interpolation method and the support vector regression (SVR) method were used for spatial missing correction and temporal missing correction, respectively. A separable spatial-temporal missing correction coupling model of groundwater level monitoring data was constructed and named UK-SVR. The reliabilities and accuracies of UK-SVR, UK, SVR, and K-nearest neighbor were evaluated by a cross-validation algorithm. The results showed that UK-SVR achieved higher accuracy than other single data-infilling models.
Similar content being viewed by others
References
Aydilek IB, Arslan A (2013) A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm. Inf Sci 233:25–35
Bao XL, Gao H, Hu LP (2016) Comparative study of various imputation methods in dealing with longitudinal missing data. Chinese Journal of Health Statistics 33(1):45–48
Bashir F, Wei HL (2018) Handling missing data in multivariate time series using a vector autoregressive model-imputation (VAR-IM) algorithm. Neurocomputing 276:23–30
De Iaco S, Maggio S, Palma M, Posa D (2012) Towards an automatic procedure for modeling multivariate space-time data. Comput Geosci 41:1–11
Delbari M, Afrasiab P, Jahani S (2013) Spatial interpolation of monthly and annual rainfall in northeast of Iran. Meteorog Atmos Phys 122(1–2):103–113
Essam D, Ahmed M, Abouelmagd A, Soliman F (2019) Monitoring temporal variations in groundwater levels in urban areas using ground penetrating radar. Sci Total Environ 703:134986
Heuvelink GBM, Griffith DA (2010) Space-time Geostatistics for geography: a case study of radiation monitoring across parts of Germany. Geogr Anal 42(2):161–179
Jeong J, Park E, Chen H, Kim KY, Han WS, Suk H (2020) Estimation of groundwater level based on the robust training of recurrent neural networks using corrupted data. J Hydrol 582:124512
Jeong J, Park E, Han WS, Kim KY, Oh J, Ha K, Yoon H, Yun ST (2017) A method of estimating sequential average unsaturated zone travel times from precipitation and water table level time series data. J Hydrol 554:570–581
Jovein EB, Hosseini SM (2017) Predicting saltwater intrusion into aquifers in vicinity of deserts using spatio-temporal kriging. Environ Monit Assess 189(2):81
Keblouti M, Ouerdachi L, Boutaghane H (2012) Spatial interpolation of annual precipitation in Annaba-Algeria-comparison and evaluation of methods. Energy Procedia 18:468–475
Lachin JM (2016) Fallacies of last observation carried forward analyses. Clinical Trials 13(2):161–168
Li XC (2012) Expectation maximization method for parameter estimation of image statistical model. Journal of Image and Graphics 17(6):619–629
Li Y, Wang LN (2014) Research of spatio-temporal interpolation algorithm based on time series. Computer science 41((6)):414–416+424
Liu TH, Wei HK, Zhang KJ (2018) Wind power prediction with missing data using Gaussian process regression and multiple imputation. Appl Soft Comput 71:905–916
Long J, Zhang LM, Shen JQ, Zhou BQ, Mao YL, Qiu LX, Xing SH (2014) Spatial interpolation of soil organic matter in farmlands in areas complex in landform. Acta Pedol Sin 51(6):1270–1281
Mao QX, Li XS (2005) Comparison between multiple imputation and ad hoc methods in simulated longitudinal data with missing values. Modern Preventive Medicine 32(4):310–312
Nishanth KJ, Ravi V (2016) Probabilistic neural network based categorical data imputation. Neurocomputing 218:17–25
Niu WJ, Zhu DP, Chen QM (2001) Research of universal Kriging. Computer engineering and applications 13:73–75+99
Park E, Kim KY, Ding G, Kim K, Han WS, Kim Y, Kim N (2011) A delineation of regional hydraulic conductivity based on water table fluctuation. J Hydrol 399(3–4):235–245
Porcu E, Gregori P, Mateu J (2006) Nonseparable stationary anisotropic space-time covariance functions. Stoch Env Res Risk A 21(2):113–122
Seo Y, Kim S, Singh VP (2015) Estimating spatial precipitation using regression kriging and artificial neural network residual kriging (RKNNRK) hybrid approach. Water Resour Manag 29(7):2189–2204
Tapoglou E, Karatzas GP, Trichakis LC, Varouchakis EA (2014) A spatio-temporal hybrid neural network-Kriging model for groundwater level simulation. J Hydrol 519:3193–3203
Tareen ADK, Nadeem MSA, Kearfott KJ, Abbas K, Khawaja MA, Rafique M (2019) Descriptive analysis and earthquake prediction using boxplot interpretation of soil radon time series data. Appl Radiat Isot 154:108861
Teegavarapu RSV (2014) Missing precipitation data estimation using optimal proximity metric-based imputation, nearest-neighbour classification and cluster-based interpolation methods. Hydrol Sci J 59(11):2009–2026
Theodossiou N, Latinopoulos P (2006) Evaluation and optimisation of groundwater observation networks using the Kriging methodology. Environ Model Softw 21(7):991–1000
Varouchakis EA, Kolosionis K, Karatzas GP (2016) Spatial variability estimation and risk assessment of the aquifer level at sparsely gauged basins using geostatistical methodologies. Earth Sci Inform 9(4):437–448
Wang L, Li GC, Qiao XW, Wang ZL, Ma T (2012a) An adaptive UFK algorithm based on maximum likelihood principle and expectation maximization algorithm. Acta Automat Sin 38(7):1200–1210
Wang PH, Jiang GH, Yuan DX, Tang QJ, Qiang Z (2019) Characteristics and cause of spatial and temporal variability of karst groundwater level’s response to rainfall. Adv Water Sci 30(1):56–64
Wang Q, Shang YM, Feng R, Wu KN (2012b) Study on location sampling for monitoring the quality of arable land based on variation functions: case studies in Zhongjiang country and Daxing district. China Land Sciences 26(8):80–86
Wei MH, Liu WJ, Bai FG, Zhang M (2016) Progress in the research of environment monitoring of groundwater at home and abroad. Environment Protection Science 42(5):15–18
Xiang JS, Wen BP, Gao YL, Ye ZN (2018) Effects of frequency and interval of groundwater monitoring on the inversion coefficients of permeability of materials of a landslide. Hydrogeology & engineering geology 45((5)):86–92+100
Yan YH, Zhou ZH (2017) Introduction to network layout of national groundwater monitoring project. Journal of China Hydrology 37(05):74–78
Yang GL, Song F, Lu CP, Wu HC, Zhao LQ (2019) Application of national groundwater monitoring project data in monthly report of groundwater dynamics. Journal of China hydrology 39((05)):45–49+24
Yang L, Wang Y (2015) Survey for various cross-validation estimators of generalization error. Application research of. Computer 32((5), 1287):–1290+1297
Yang SH, Zhang HT, Guo L, Ren Y (2015) Spatial interpolation of soil organic matter using regression Kriging and geographically weighted regression Kriging. Chin J Appl Ecol 26(6):1649–1656
Yang Y, Christakos G (2015) Uncertainty assessment of heavy metal soil contamination mapping using spatiotemporal sequential indicator simulation with multi-temporal sampling points. Environ Monit Assess 187(9):571
Yates F (1933) The analysis of replicated experiments when the field results are incomplete. The Empire Journal of Experimental Agriculture 1:129–142
Yoon H, Hyun Y, Ha K, Lee KK, Kim GB (2016) A method to improve the stability and accuracy of ANN- and SVM-based time series models for long-term groundwater level predictions. Comput Geosci 90:144–155
Yoon H, Jun SC, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396(1):128–138
Yozgatligil C, Aslan S, Iyigun C, Batmaz I (2013) Comparison of missing value imputation methods in time series: the case of Turkish meteorological data. Theor Appl Climatol 112(1–2):143–167
Zhang ZH (2016) Missing data imputation: focusing on single imputation. Annals of Translational Medicine 4(1)
Zhong J, Liu RH (2012) An improved KNN method based on density to realize text categorization. Computer Engineering and Applications 48(2):142–144
Zhou HY, Gómez-Hernández JJ, Li LP (2014) Inverse methods in hydrogeology: evolution and recent trends. Adv Water Resour 63:22–37
Zhu JF, Zhang SA, Dai N, Yang D, Ding Y (2017) Application of groundwater resources monitoring and analysis technology. Journal of China Hydrology 37(03):58–62
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: H. Babaie
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
He, L., Chen, S., Liang, Y. et al. Infilling the missing values of groundwater level using time and space series: case of Nantong City, east coast of China. Earth Sci Inform 13, 1445–1459 (2020). https://doi.org/10.1007/s12145-020-00489-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-020-00489-y