Abstract
Water transparency is a key indicator of water quality as it reflects the turbidity and eutrophication in lakes and reservoirs. To carry out remote sensing monitoring of water transparency rapidly and intelligently, deep learning technology was used to construct a new retrieval model, namely, point-centered regression convolutional neural network (PSRCNN) suitable for Sentinel 2 and Landsat 8 images. The impact of input feature variables on the accuracy of the inversion model was examined, and the performance of an optimized PSRCNN model was also assessed. This model was applied to remote sensing images of three shallow lakes in the eastern China plain acquired in summer. The PSRCNN model, constructed using five identical bands from Landsat 8 and Sentinel 2 images and 20 band combinations as the input variables, the input window size of 5 × 5 pixels, proves a good predictive ability, with a verification accuracy of R2 = 0.85, the root mean squared error (RMSE) = 13.0 cm, and the relative predictive deviation (RPD) = 2.58. After the sensitive spectral analysis of water transparency, the band combinations that had correlation coefficients higher than 0.6 were selected as the new input feature variables to construct an optimized PSRCNN model (PSRCNNopt) for water transparency. The PSRCNNopt model has an excellent predictive ability, with a verification accuracy of R2 = 0.89, RMSE = 11.48 cm, and RPD =3.0. It outperforms the commonly retrieval models (band ratios, random forest, support vector machine, etc.), with higher accuracy and robustness. Spatial variations in water transparency of three lakes from the retrieval results by PSRCNNopt model are consistent with the field observations.
Similar content being viewed by others
Data availability
Data and material access are not available.
References
Ai B, Wen Z, Wang ZH, Wang RF, Su DP, Li CM, Yang FL (2020) Convolutional neural network to retrieve water depth in marine shallow water area from remote sensing images. IEEE J Sel Top Appl Earth Obs Remote Sens 13:2888–2898
Bonansea M, Ledesma M, Bazán R, Ferral A, German A, O'Mill P, Rodriguez C, Pinotti L (2019) Evaluating the feasibility of using Sentinel-2 imagery for water clarity assessment in a reservoir. J S Am Earth Sci 95:102265
Bonansea M, Bazan R, Ledesma C, Rodriguez C, Pinotti L (2015) Monitoring of regional lake water clarity using Landsat imagery. Hydrol Res 46(5):661–670
Bowers DG, Roberts EM, Hoguane AM, Fall KA, Massey GM, Friedrichs CT (2020) Secchi disk measurements in turbid water. J Geophys Res Oceans 125(5). https://doi.org/10.1029/2020JC016172
Cazzanigaa I, Bresciani M, Colombo R, Della Bella V, Padula R, Giardino C (2019) A comparison of Sentinel-3-OLCI and Sentinel-2-MSI-derived Chlorophyll-a maps for two large Italian lakes. Remote Sens Lett 10(10):978–987
Chang NN, Luo L, Wang XC, Song J, Han JX, Ao D (2020) A novel index for assessing the water quality of urban landscape lakes based on water transparency. Sci Total Environ 735:139351
Chen J, Han QJ, Chen YL, Li YD (2019) A Secchi depth algorithm considering the residual error in satellite remote sensing reflectance data. Remote Sens 11:1948
Dosovitskiy A, Springenberg JT, Tatarchenko M, Brox T (2017) Learning to generate chairs, tables and cars with convolutional networks. IEEE Trans Pattern Anal Mach Intell 39(4):692–705
Feng L, Hou XJ, Zheng Y (2019) Monitoring and understanding the water transparency changes of fifty large lakes on the Yangtze Plain based on long-term MODIS observations. Remote Sens Environ 221:675–686
Franz BA, Bailey SW, Kuring N, Werdell PJ (2015) Ocean color measurements with the Operational Land Imager on Landsat-8: implementation and evaluation in SeaDAS. J Appl Remote Sens 9(1):096070
Keller S, Maier PM, Riese FM, Norra S, Holbach A, Borsig N, Wilhelms A, Moldaenke C, Zaake A, Hinz S (2018) Hyperspectral data and machine learning for estimating CDOM, chlorophyll a, diatoms, green algae and turbidity. Int J Environ Res Public Health 15:1881
Krizhevsky A, Sutskever H, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Comminications of the ACM 60(6):80–90
Lee ZP, Shang SL, Hu CM, Du KP, Weidemann A, Hou WL, Lin JF, Lin G (2015) Secchi disk depth: A new theory and mechanistic model for underwater visibility. Remote Sens Environ 169:139–149
Ligi M, Soomets T, Toming K, Casal G (2016) Remote sensing of black lakes and using 810 nm reflectance peak for retrieving water quality parameters of optically complex waters. Remote Sens 8(6):497
Mamun M, Kim JJ, Alam MA, An KG (2019) Prediction of algal chlorophyll-a and water clarity in monsoon-region reservoir using machine learning approaches. Water. 12(1):30
Mandanici E, Bitelli G (2016) Preliminary comparison of Sentinel-2 and Landsat 8 Imagery for a combined use. Remote Sens 8(12):1014
Mccullough IM, Loftin CS, Sader SA (2012) Combining lake and watershed characteristics with Landsat TM data for remote estimation of regional lake clarity. Remote Sens Environ 12:109–115
Mobley CD (1999) Estimation of the remote-sensing reflectance from above-surface measurements. Appl Opt 38:7442–7455
Page BP, Olmanson LG, Mishra DR (2019) A harmonized image processing workflow using Sentinel-2/MSI and Landsat-8/OLI for mapping water clarity in optically variable lake systems. Remote Sens Environ 231:111284
Pyo JC, Duan HT, Baek S, Kim MS, Jeon T, Kwon YS, Lee H, Cho KH (2019) A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery. Remote Sens Environ 233:111350
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv 11(06434):1–7
Rodrigues G, Potes M, Costa MJ, Novais MH, Penha AM, Salgado R, Morais MM (2020) Temporal and spatial variations of Secchi depth and diffuse attenuation coefficient from Sentinel-2 MSI over a large reservoir. Remote Sens 12:768
Ruddick KG, Ovidio F, Rijkeboer M (2000) Atmospheric correction of SeaWiFS imagery for turbid coastal and inland waters. Appl Opt 39(6):879–912
Saeys W, Mouazen AM, Ramon H (2005) Potential for onsite and online analysis of pig manure using visible and near infrared reflectance spectroscopy. Biosyst Eng 91(4):393–402
Shen M, Duan HT, Cao ZG, Xue K, Qi TC, Ma JG, Liu D, Song KS, Huang CL, Song XY (2020) Sentinel-3 OLCI observations of water clarity in large lakes in eastern China: implications for SDG 6.3.2 evaluation. Remote Sens Environ 247:111950
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1). https://doi.org/10.1186/s40537-019-0197-0
Soria-Perpinya X, Urrego EP, Pereira-Sandoval M, Ruiz-Verdu A, Soria JM, Delegido J, Vicente E, Moreno J (2020) Monitoring water transparency of a hypertrophic lake (the Albufera of València) using multitemporal Sentinel-2 satellite images. Limnetica 39(1):373–386
Teubner K, Teubner IE, Pall K, Kabas W, Dokulil MT (2020) New emphasis on water transparency as socio-ecological indicator for urban water: bridging ecosystem service supply and sustainable ecosystem health. Front Environ Sci 8:573724 1-22
Toming K, Kutser T, Laas A, Sepp M, Paavel B, Noges T (2016) First experiences in mapping lake water quality parameters with Sentinel-2 MSI imagery. Remote Sens 8(8):640
Tyler, John E (1968) The Secchi disc. Limnol Oceanogr 13(1):1–6
Vanhellemont Q, Ruddic K (2018) Atmospheric correction of metre-scale optical satellite data for inland and coastal water applications. Remote Sens Environ 216:586–597
Vundo A, Matsushita B, Jian DL, Gondwe M, Hamzah R, Setiawan F, Fukushima T (2019) An overall evaluation of water transparency in Lake Malawi from MERIS Data. Remote Sens 11:279. https://doi.org/10.3390/rs11030279
Wang HH, Wang J, Cui YH, Yan SJ (2021) Consistency of suspended particulate matter concentration in turbid water retrieved from Sentinel-2 MSI and Landsat-8 OLI sensors. Sensors 21(5):1662
Wang L, Scott KA, Xu L, Clausi DA (2016) Sea ice concentration estimation during melt from Dual-Pol SAR scenes using deep convolutional neural networks: a case study. IEEE Trans Geosci Remote Sens 54(8):4524–4533
Wang SL, Li JS, Zhang B, Lee Z, Spyrakos E, Feng L, Liu C, Zhao HL, Wu YH, Zhu LP, Jia LM, Wan W, Zhang FF, Shen Q, Tyler AN, Zhang XF (2020) Changes of water clarity in large lakes and reservoirs across China observed from long-term MODIS. Remote Sens Environ 247:111949
Xu X, Huang X, Zhang Y, Yu D (2018) Long-term changes in water clarity in Lake Liangzi determined by remote sensing. Remote Sens 10(9):1441
Yang X, Cui HB, Liu XS, Wu QG, Zhang H (2020) Water pollution characteristics and analysis of Chaohu Lake basin by using different assessment methods. Environ Sci Pollut Res 27:18168–18181
Yim I, Shin J, Lee H, Park S, Nam G, Kang T, Cho KH, Cha Y (2020) Deep learning-based retrieval of cyanobacteria pigment in inland water for in-situ and airborne hyperspectral data. Ecol Indic 110:105879
Yip HD, Johansson J, Hudson JJ (2015) A 29-year assessment of the water clarity and chlorophyll-a concentration of a large reservoir: investigating spatial and temporal changes using Landsat imagery. J Great Lakes Res 14(S2):34–44
Yuan QQ, Shen HF, Li TW, Li ZW, Li SW, Jiang Y, Xu HZ, Tan WW, Yang QQ, Wang JW, Gao JH, Zhang LP (2020) Deep learning in environmental remote sensing: achievements and challenges. Remote Sens Environ 241:111716
Zhang YL, Wu ZX, Liu ML, He JB, Shi K, Wang MZ, Yu ZM (2014) Thermal structure and response to long-term climatic changes in Lake Qiandaohu, a deep subtropical reservoir in China. Limnol Oceanogr 59(4):1193–1202
Zhou GH, Tang JW, Tian GL, Li J, Liu Q (2009) Uncertainty analysis of inland water quality remote sensing: a review. Adv Earth Science 24(02):150–158 (In Chinese)
Zhu XX, Tuia D, Mou L, Xia GS, Zhang L, Xu F, Fraundorfer F (2017) Deep learning in remote sensing: a review. IEEE Trans Geosci Remote Sens Mag 5(4):8–36
Zolfaghari K, Duguay CR (2016) Estimation of Water Quality Parameters in Lake Erie from MERIS Using Linear Mixed Effect Models. Remote Sens 8(6):473
Funding
This research was funded by the National Natural Science Foundation of China, grant numbers 41401022, 41861002, and 41801332.
Author information
Authors and Affiliations
Contributions
Conceptualization: Yuhuan Cui and Jie Wang
Methodology: Zhongnan Yan
Software: Zhongnan Yan and Shuang Hao
Validation: Yuhuan Cui and Youcun Liu
Formal analysis: Yuhuan Cui
Investigation: Shuang Hao, Jie Wang, and Youcun Liu
Resources: Jie Wang and Youcun Liu
Data curation: Shuang Hao
Writing—original draft preparation: Yuhuan Cui
Writing—review and editing: Jie Wang
Visualization: Jie Wang
Supervision: Yuhuan Cui
Project administration: Jie Wang
Funding acquisition: Yuhuan Cui and Shuang Hao
All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Ethical approval and consent to participate
Not applicable
Consent for publication
Not applicable
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible Editor: Philippe Garrigues
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
The information of input feature variables used in the PSRCNNopt model
Feature types | Feature variables | Correlation coefficient |
---|---|---|
Original Bands | Rrs (442) | 0.140 |
Rrs (559) | −0.183 | |
Rrs (665) | −0.598 | |
Rrs (492) | −0.485 | |
Rrs (864) | −0.015 | |
Band ratios | Rrs (442)/Rrs (492) | 0.76 |
Rrs (442)/Rrs (559) | 0.839 | |
Rrs (442)/Rrs (665) | 0.683 | |
Rrs (492)/Rrs (442) | −0.731 | |
Rrs (492)/Rrs (559) | 0.807 | |
Rrs (559)/Rrs (442) | −0.788 | |
Rrs (559)/Rrs (492) | −0.763 | |
Rrs (665)/Rrs (442) | −0.615 | |
Band subtraction | Rrs (442)-Rrs (492) | 0.731 |
Rrs (442)-Rrs (559) | 0.83 | |
Rrs (442)-Rrs (665) | 0.619 | |
Rrs (492)-Rrs (559) | 0.821 |
Rights and permissions
About this article
Cite this article
Cui, Y., Yan, Z., Wang, J. et al. Deep learning–based remote sensing estimation of water transparency in shallow lakes by combining Landsat 8 and Sentinel 2 images. Environ Sci Pollut Res 29, 4401–4413 (2022). https://doi.org/10.1007/s11356-021-16004-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-021-16004-9