Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
PreprintCited by 1Hydrology and Watershed Management StudiesHydrological Forecasting Using AIEnvironmental Monitoring and Data Management

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

A Spatially-Informed Interpolation Framework for Reconstructing Lake Area Time Series via Semantic Neighborhood Correlation

Open access
Liu, Chen·2025·Scientific Reports
DOI 10.21203/rs.3.rs-6437916/v1PMC PMC12241530

Preprint — published as 10.1038/s41598-025-09410-3 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Long-term, high-resolution records of lake surface area are essential for characterizing the spatiotemporal dynamics of inland water bodies. Although Synthetic Aperture Radar has substantially improved water extent detection under adverse conditions, optical remote sensing imagery remains the dominant data source owing to its higher spatial resolution. Nevertheless, optical data are frequently compromised by persistent cloud cover and sensor limitations, leading to substantial observational gaps. To effectively address this challenge, this study introduces a novel spatially-informed interpolation method termed Semantic Neighborhood Correlation-based Interpolation (SNCI), which leverages spatial correlations among hydrologically interconnected lakes to reconstruct missing lake area observations. By explicitly modeling the inherent hydrological and climatic coherence among neighboring lakes, SNCI provides robust, accurate, and scalable interpolations even in the presence of extensive temporal data losses. The method was evaluated on monthly lake area data from 54 lakes in the Wuhan region between 2000 and 2020, using the Global Surface Water dataset, and validated against high-resolution Dynamic World observations. Several representative lakes were analyzed in detail to assess SNCI’s robustness across diverse seasonal and interannual conditions. Compared with polynomial fitting, Random Forest, and Long Short-Term Memory, SNCI consistently achieves lower interpolation errors. In the case of East Lake, SNCI reduces mean absolute error by 50.1% and root mean square error by 28.3% relative to the best-performing baseline. Across all lakes, SNCI demonstrates superior accuracy and correlation, particularly under data-sparse conditions. These results underscore SNCI’s potential to enhance lake area reconstruction accuracy and support broader applications in hydrological modeling, environmental monitoring, and climate impact assessment.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-6437916/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Geographic location and hydrological structure of the study area. The region includes three Basins and features complex hydrological connectivity. Elevation data were derived from the SRTM digital elevation model34, while lake and river bodies were extracted from satellite observations. The red boundaries denote the spatial extent analyzed using the SNCI method.
Fig. 1 Geographic location and hydrological structure of the study area. The region includes three Basins and features complex hydrological connectivity. Elevation data were derived from the SRTM digital elevation model34, while lake and river bodies were extracted from satellite observations. The red boundaries denote the spatial extent analyzed using the SNCI method.CC BY · PubMed Central
Fig. 2 Geographic distribution, catchment boundaries, and surrounding land-use patterns of four selected lakes. (a) shows the locations of East Lake, South Lake, West Lake, and Five Lake, overlaid on a Sentinel-2 satellite image derived and visualized using Google Earth Engine (https://earthengine.google.com). Subfigures (b)–(f) present each individual lake along with its surrounding land cover types, derived from the SinoLC-1 land cover dataset42.
Fig. 2 Geographic distribution, catchment boundaries, and surrounding land-use patterns of four selected lakes. (a) shows the locations of East Lake, South Lake, West Lake, and Five Lake, overlaid on a Sentinel-2 satellite image derived and visualized using Google Earth Engine (https://earthengine.google.com). Subfigures (b)–(f) present each individual lake along with its surrounding land cover types, derived from the SinoLC-1 land cover dataset42.CC BY · PubMed Central
Fig. 3 Schematic workflow of the proposed SNCI-based lake area reconstruction framework. The diagram illustrates the three-stage process comprising lake area extraction and outlier removal, neighborhood correlation analysis, and SNCI-based interpolation.
Fig. 3 Schematic workflow of the proposed SNCI-based lake area reconstruction framework. The diagram illustrates the three-stage process comprising lake area extraction and outlier removal, neighborhood correlation analysis, and SNCI-based interpolation.CC BY · PubMed Central
Fig. 4 Schematic of the SNCI principle: missing values for a target lake are estimated using observations from temporally correlated neighboring lakes.
Fig. 4 Schematic of the SNCI principle: missing values for a target lake are estimated using observations from temporally correlated neighboring lakes.CC BY · PubMed Central
Fig. 5 Distribution of lake surface area data before and after outlier removal. The figure shows lake area distributions under three conditions: (1) raw data, (2) after initial screening using the GSW permanent water dataset, and (3) after further filtering via Boxplot analysis.
Fig. 5 Distribution of lake surface area data before and after outlier removal. The figure shows lake area distributions under three conditions: (1) raw data, (2) after initial screening using the GSW permanent water dataset, and (3) after further filtering via Boxplot analysis.CC BY · PubMed Central
Fig. 6 Summary of missing lake surface area records. (a) Time series completeness across all lakes, where blue bars indicate valid observations and white gaps denote missing values. (b) Histogram of missing months per lake, illustrating the spatial variability in data availability.
Fig. 6 Summary of missing lake surface area records. (a) Time series completeness across all lakes, where blue bars indicate valid observations and white gaps denote missing values. (b) Histogram of missing months per lake, illustrating the spatial variability in data availability.CC BY · PubMed Central
Fig. 7 Correlation heatmap of lake area dynamics in the Wuhan region. Warmer colors indicate stronger positive correlations in temporal area changes between lake pairs, while cooler tones highlight weak or negative relationships.
Fig. 7 Correlation heatmap of lake area dynamics in the Wuhan region. Warmer colors indicate stronger positive correlations in temporal area changes between lake pairs, while cooler tones highlight weak or negative relationships.CC BY · PubMed Central
Fig. 8 Highly correlated lake pairs centered on selected study lakes. The figure highlights neighboring lakes that exhibit strong temporal correlation in surface area change with several representative lakes, serving as potential candidates for SNCI-based interpolation.
Fig. 8 Highly correlated lake pairs centered on selected study lakes. The figure highlights neighboring lakes that exhibit strong temporal correlation in surface area change with several representative lakes, serving as potential candidates for SNCI-based interpolation.CC BY · PubMed Central
Fig. 9 Comparison of reconstructed monthly lake areas from 2017 to 2020 using three selected methods: RF, LSTM, and the proposed SNCI. These methods were chosen for visualization due to their superior numerical performance.
Fig. 9 Comparison of reconstructed monthly lake areas from 2017 to 2020 using three selected methods: RF, LSTM, and the proposed SNCI. These methods were chosen for visualization due to their superior numerical performance.CC BY · PubMed Central
Fig. 10 presents heatmap-based reconstructions of monthly lake area from 2000 to 2020 (left column), alongside the original, un-interpolated GSW-derived lake extents for the year 2018 (right column). The 2018 panels clearly reveal persistent data gaps—especially in winter months—caused by cloud cover and limited satellite observations, underscoring the need for robust interpolation techniques.
Fig. 10 presents heatmap-based reconstructions of monthly lake area from 2000 to 2020 (left column), alongside the original, un-interpolated GSW-derived lake extents for the year 2018 (right column). The 2018 panels clearly reveal persistent data gaps—especially in winter months—caused by cloud cover and limited satellite observations, underscoring the need for robust interpolation techniques.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 54

  1. Taylor, R. G. et al. Ground water and climate change. Nat. Clim. Change. 3, 322–329. 10.1038/nclimate1744 (2013). · DOI · Paper page
  2. Qin, B. et al. Environmental Issues of Lake Taihu, China. Developments Hydrobiology 3, 3–14 (Springer Netherlands). 10.1007/978-1-4020-6158-5_2 · DOI
  3. Song, C. et al. Remote Sensing of Alpine Lake Water Environment Changes on the Tibetan Plateau and Surroundings: A Review. ISPRS J. Photogrammetry Remote Sens. 92, 26–37. 10.1016/j.isprsjprs.2014.03.001 (2014). · DOI
  4. Jing, Y., Zhang, F. & Wang, X. Monitoring Dynamics and Driving Forces of Lake Changes in Different Seasons in Xinjiang Using Multi-Source Remote Sensing. Eur. J. Remote Sens. 51, 150–165. 10.1080/22797254.2017.1413955 (2017). · DOI
  5. Parmesan, C. Ecological and Evolutionary Responses to Recent Climate Change. Annu. Rev. Ecol. Evol. Syst. 37, 637–669. 10.1146/annurev.ecolsys.37.091305.110100 (2006). · DOI · Paper page
  6. Zhang, G. et al. An Inventory of Glacial Lakes in the Third Pole Region and their Changes in Response to Global Warming. Glob. Planet Change. 131, 148–157. 10.1016/j.gloplacha.2015.05.013 (2015). · DOI
  7. Crétaux, J. F. et al. Sols: A Lake Database to Monitor in the Near Real Time Water Level and Storage Variations from Remote Sensing Data. Adv. Space Res. 47, 1497–1507. 10.1016/j.asr.2011.01.004 (2011). · DOI · Paper page
  8. Avisse, N. et al. Monitoring Small Reservoirs' Storage with Satellite Remote Sensing in Inaccessible Areas. Hydrol. Earth Syst. Sci. 21, 6445–6459. 10.5194/hess-21-6445-2017 (2017). · DOI
  9. Marcé, R. et al. Automatic High Frequency Monitoring for Improved Lake and Reservoir Management. Environ. Sci. Technol. 50, 10780–10794. 10.1021/acs.est.6b01604 (2016). · DOI
  10. Ma, R. et al. A Half-Century of Changes in China's Lakes: Global Warming or Human Influence? Geophys. Res. Lett. 37, 24. 10.1029/2010gl045514 (2010). · DOI
  11. Xie, F. et al. Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 10, 3631–3640. 10.1109/jstars.2017.2686488 (2017). · DOI · Paper page
  12. Li, X. et al. Monitoring high spatiotemporal water dynamics by fusing MODIS, Landsat, water occurrence data and DEM. Remote Sens. Environ. 265, 112680. 10.1016/j.rse.2021.112680 (2021). · DOI
  13. DeVries, B. et al. Rapid and robust monitoring of flood events using Sentinel-1 and Landsat data on the Google Earth Engine. Remote Sens. Environ. 240, 111664. 10.1016/j.rse.2020.111664 (2020). · DOI · Paper page
  14. Li, J. et al. A robust large-scale surface water mapping framework with high spatiotemporal resolution based on the fusion of multi-source remote sensing data. Int. J. Appl. Earth Obs. Geoinf. 118, 103288. 10.1016/j.jag.2023.103288 (2023). · DOI
  15. Marzi, D. & Gamba, P. Inland water body mapping using multitemporal Sentinel-1 SAR data. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 14, 11789–11799. 10.1109/JSTARS.2021.3127748 (2021). · DOI
  16. Bioresita, F. et al. Fusion of Sentinel-1 and Sentinel-2 image time series for permanent and temporary surface water mapping. Int. J. Remote Sens. 40, 9026–9049. 10.1080/01431161.2019.1624869 (2019). · DOI
  17. Saghafi, M., Ahmadi, A. & Bigdeli, B. Sentinel-1 and Sentinel-2 data fusion system for surface water extraction. J. Appl. Remote Sens. 15, 014521. 10.1117/1.JRS.15.014521 (2021). · DOI
  18. Liu, C. et al. A review of optical and SAR image deep feature fusion in semantic segmentation. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 10.1109/JSTARS.2024.3424831 (2024). · DOI
  19. Li, L. et al. Global dominance of seasonality in shaping lake-surface-extent dynamics. Nature 10.1038/s41586-025-09046-3 (2025). · DOI
  20. Lam, N. S. Spatial Interpolation Methods: A Review. Am. Cartographer. 10, 129–150. 10.1559/152304083783914958 (1983). · DOI · Paper page
  21. Lu, G. Y. & Wong, D. W. An adaptive inverse-distance weighting spatial interpolation technique. Comput. Geosci. 34, 1044–1055. 10.1016/j.cageo.2007.07.010 (2008). · DOI · Paper page
  22. Oliver, M. A. & Webster, R. Kriging: a method of interpolation for geographical information systems. Int. J. Geographical Inform. Syst. 4, 313–332. 10.1080/02693799008941549 (1990). · DOI
  23. Zhao, X. et al. iforest: Interpreting random forests via visual analytics. IEEE Trans. Vis. Comput. Graph. 25, 407–416. 10.1109/TVCG.2018.2864475 (2018). · DOI
  24. Greff, K. et al. LSTM: A search space odyssey. IEEE Trans. Neural Networks Learn. Syst. 28, 2222–2232. 10.1109/TNNLS.2016.2582924 (2016). · DOI · Paper page
  25. Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Networks Learn. Syst. 32, 4–24. 10.1109/TNNLS.2020.2978386 (2020). · DOI · Paper page
  26. Li, W. et al. A Ground-Independent Method for Obtaining Complete Time Series of in Situ Evapotranspiration Observations. J. Hydrol. 632, 130888. 10.1016/j.jhydrol.2024.130888 (2024). · DOI
  27. Malekian, A. & Kazemzadeh, M. Spatio-Temporal Analysis of Regional Trends and Shift Changes of Autocorrelated Temperature Series in Urmia Lake Basin. Water Resour. Manage. 30, 785–803. 10.1007/s11269-015-1190-9 (2015). · DOI
  28. Miller, H. J. Tobler's First Law and Spatial Analysis. Ann. Assoc. Am. Geogr. 94, 284–289. 10.1111/j.1467-8306.2004.09402005.x (2004). · DOI · Paper page
  29. Siqueira, V. A. et al. Toward Continental Hydrologic–Hydrodynamic Modeling in South America. Hydrol. Earth Syst. Sci. 22, 4815–4842. 10.5194/hess-22-4815-2018 (2018). · DOI
  30. Goodchild, M. F. A geographer looks at spatial information theory. International Conference on Spatial Information Theory 1–13Springer Berlin Heidelberg, (2001). 10.1007/3-540-45424-1_1 · DOI
  31. Fotheringham, A. S., Brunsdon, C. & Charlton, M. Geographically weighted regression. Sage Handb. Spat. Anal. (Sage), 243–254. 10.4135/9780857020130.n13 (2009). · DOI
  32. Du, N., Ottens, H. & Sliuzas, R. Spatial Impact of Urban Expansion on Surface Water Bodies—a Case Study of Wuhan, China. Landsc. Urban Plann. 94, 175–185. 10.1016/j.landurbplan.2009.10.002 (2010). · DOI
  33. Yang, B. & Ke, X. Analysis on Urban Lake Change During Rapid Urbanization Using a Synergistic Approach: A Case Study of Wuhan, China. Phys. Chem. Earth Parts A/B/C. 89–90, 127–135. 10.1016/j.pce.2015.10.005 (2015). · DOI
  34. Rodriguez, E., Morris, C. S. & Belz, J. E. A global assessment of the SRTM performance. Photogrammetric Eng. Remote Sens. 72, 249–260. 10.14358/PERS.72.3.249 (2006). · DOI · Paper page
  35. Pekel, J. F. et al. High-Resolution Mapping of Global Surface Water and its Long-Term Changes. Nature 540, 418–422. 10.1038/nature20584 (2016). · DOI · Paper page
  36. Brown, C. F. et al. Dynamic World, Near Real-Time Global 10 M Land Use Land Cover Mapping. Sci. Data. 9, 1. 10.1038/s41597-022-01307-4 (2022). · DOI · Paper page
  37. Phiri, D. et al. Sentinel-2 Data for Land Cover/Use Mapping: A Review. Remote Sens. 12, 2291. 10.3390/rs12142291 (2020). · DOI
  38. Wang, X. et al. Improved Maps of Surface Water Bodies, Large Dams, Reservoirs, and Lakes in China. Earth Syst. Sci. Data. 14, 3757–3771. 10.5194/essd-14-3757-2022 (2022). · DOI
  39. Pi, X. et al. Mapping global lake dynamics reveals the emerging roles of small lakes. Nat. Commun. 13, 5777. 10.1038/s41467-022-33239-3 (2022). · DOI
  40. Gorelick, N. et al. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens. Environ. 202, 18–27. 10.1016/j.rse.2017.06.031 (2017). · DOI · Paper page
  41. Tamiminia, H. et al. Google Earth Engine for Geo-Big Data Applications: A Meta-Analysis and Systematic Review. ISPRS J. Photogrammetry Remote Sens. 164, 152–170. 10.1016/j.isprsjprs.2020.04.001 (2020). · DOI · Paper page
  42. Li, Z. et al. SinoLC-1: The first 1-meter resolution national-scale land-cover map of China created with the deep learning framework and open-access data. Earth System Science Data Discussions 1–38 (2023). (2023). 10.5194/essd-2023-87 · DOI
  43. Martinsen, K. T. & Sand-Jensen, K. Predicting water quality from geospatial lake, catchment, and buffer zone characteristics in temperate lowland lakes. Sci. Total Environ. 851, 158090 (2022). · DOI
  44. Schwertman, N. C., Owens, M. A. & Adnan, R. A. Simple More General Boxplot Method for Identifying Outliers. Comput. Stat. Data Anal. 47, 165–174. 10.1016/j.csda.2003.10.012 (2004). · DOI
  45. Alghushairy, O. et al. A Review of Local Outlier Factor Algorithms for Outlier Detection in Big Data Streams. Big Data Cogn. Comput. 5, 1. 10.3390/bdcc5010001 (2020). · DOI · Paper page
  46. Benesty, J. et al. Pearson Correlation Coefficient. Springer Topics in Signal Processing1–04 (Springer, 2009). 10.1007/978-3-642-00296-0_5 · DOI
  47. Long, D. et al. South-to-North Water Diversion stabilizing Beijing’s groundwater levels. Nat. Commun. 11, 3665. 10.1038/s41467-020-17428-6 (2020). · DOI
  48. Ran, J. et al. Contrasting Lake Changes in Tibet Revealed by Recent Multi-Modal Satellite Observations. Sci. Total Environ. 908, 168342. 10.1016/j.scitotenv.2023.168342 (2024). · DOI
  49. Yang, R. et al. Spatiotemporal Variations in Volume of Closed Lakes on the Tibetan Plateau and their Climatic Responses From 1976 to 2013. Clim. Change. 140, 621–633. 10.1007/s10584-016-1877-9 (2016). · DOI
  50. Li, X. et al. Climate change threatens terrestrial water storage over the Tibetan Plateau. Nat. Clim. Change. 12, 801–807. 10.1038/s41558-022-01443-0 (2022). · DOI · Paper page
  51. Bachman, P., Hjelm, R. D. & Buchwalter, W. Learning representations by maximizing mutual information across views. Advances Neural Inform. Process. Systems 32 (2019).
  52. Berndt, D. J. & Clifford, J. Using dynamic time warping to find patterns in time series. Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (1994).
  53. Zeng, H. et al. Nonlinear relationship between hepatic steatosis index and reversion to normal glucose regulation in Chinese adults with prediabetes. Sci. Rep. 15, 1–12. 10.1038/s41598-025-88314-8 (2025). · DOI
  54. Ding, M. et al. A framework of freshwater and saline lake typology classification through leveraging hydroclimate, spectral, and literature evidence. J. Hydrol. 632, 130704. 10.1016/j.jhydrol.2024.130704 (2024). · DOI

Metadata

Authors
Liu, C.
Affiliations
Wuhan University (CN)
Corresponding author
Liu, Chen
ORCID
Liu, Chen
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2025-07-15
Volume
15
Issue
1
Pages
24787-24787
ISSN
2045-2322 (ISSN-L)
DOI
10.21203/rs.3.rs-6437916/v1
PMC
PMC12241530
OpenAlex
W4412177594
Cited by
1
References
1
Citations by year
2026: 1
FWCI
0.25
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Environmental Science › Water Science and Technology › Hydrology and Watershed Management Studies
  • Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
  • Physical Sciences › Environmental Science › Management, Monitoring, Policy and Law › Environmental Monitoring and Data Management
Keywords
missing data interpolation, surface water extent, Global Surface Water dataset, Dynamic World, East Lake

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.