Anterior|Próximo

Estudo do algoritmo de rede neural para inversão da concentração de clorofila-a a partir dos dados COCTS dos satélites HY-1C/1D

  • role： First author第一作者
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

  • Email：mywei@stu.xmu.edu.cn
  • Introduction：韦美怡，研究方向为海洋水色遥感。E-mail： mywei@stu.xmu.edu.cn
WEI Meiyi1,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

WU Jingyu1,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

ZHENG Lufei1,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

WANG Daosheng1,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

LEE Zhongping1,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

SHANG Shaoling1,  
  • Affiliation：

    National Satellite Ocean Application Service, Beijing 100081, China

YE Xiaomin2,  
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

LIN Gong1,  
  • role： Corresponding author通信作者
  • Affiliation：

    National Key Laboratory of Marine Biogeochemistry, Xiamen University, Xiamen 361102, China

  • Email：xlyu@xmu.edu.cn
  • Introduction：余小龙，研究方向为水色遥感机理与应用。E-mail： xlyu@xmu.edu.cn
YU Xiaolong1*

Resumo

A concentração de clorofila-a (Chl-a) em corpos d'água, como um parâmetro climático central, é de grande importância para a inversão remota precisa, fundamental para estudos globais do ciclo do carbono, monitoramento e gestão ambiental marinha. A série de satélites HY-1C/1D está equipada com o scanner de cor e temperatura da água do oceano (COCTS), permitindo o monitoramento global da cor do oceano em escala de quilômetros. O desenvolvimento de um algoritmo de inversão de alta precisão para Chl-a baseado em dados COCTS é uma condição essencial para apoiar pesquisas autônomas usando dados de satélite para monitoramento oceânico e estudos das mudanças climáticas. Este estudo, baseado em 2165 conjuntos de dados medidos globalmente, construiu um modelo de rede neural perceptron multicamadas (MLP-NN) baseado na reflectância multibanda (Rrs) do sensor COCTS HY-1C/1D e parâmetros ambientais, alcançando uma inversão de alta precisão da concentração global de Chl-a em corpos d'água. Através da análise de sensibilidade dos fatores de entrada, foi determinada a combinação ótima de entrada, incluindo reflectâncias Rrs nas bandas de 412, 443, 490, 520, 565 e 670 nm, latitude, mês, temperatura média da superfície do mar do mês anterior e parâmetros de radiação fotossinteticamente ativa climática do mês anterior. Os resultados da validação indicam que a raiz do erro quadrático médio (RMSD) da concentração estimada em logaritmo pelo modelo MLP-NN é 0,22, e a Mediana da Diferença Percentual Absoluta (MAPD) é 29,1%, representando uma redução de 0,1 e 16,9% respectivamente em comparação com o algoritmo comercial do índice de cor da água (OCI) da NASA. Uma validação adicional combinando dados de satélite e medidos revelou que o RMSD e o MAPD do Chl-a estimado pelo modelo MLP-NN foram reduzidos em 0,09 e 9,8% respectivamente em relação ao algoritmo OCI, demonstrando excelente robustez do algoritmo. Este estudo fornece um método inovador para satélites nacionais no campo de monitoramento ecológico marinho, aprimorando significativamente a capacidade de utilização das observações dos satélites HY-1C/1D para concentração global de Chl-a.

Palavras-chave

Clorofila-a (Chl-a); reflectância de sensoriamento remoto; algoritmo de inversão; satélites HY-1C/1D; rede neural; COCTS; cor da água oceânica

References

  1. 1.
    Arlot S and Celisse A. 2010. A survey of cross-validation procedures for model selection. Statistics Surveys, 4: 40-79
  2. 2.
    Behrenfeld M J, Boss E, Siegel D A and Shea D M. 2005. Carbon-based ocean productivity and phytoplankton physiology from space. Global Biogeochemical Cycles, 19(1): GB1006
  3. 3.
    Bilski J, Kowalczyk B, Marchlewska A and Zurada J M. 2020. Local Levenberg-Marquardt algorithm for learning feedforwad neural networks. Journal of Artificial Intelligence and Soft Computing Research, 10(4): 299-316
  4. 4.
    Cao Z G, Ma R H, Duan H T, Pahlevan N, Melack J, Shen M and Xue K. 2020. A machine learning approach to estimate chlorophyll-a from Landsat-8 measurements in inland lakes. Remote Sensing of Environment, 248: 111974
  5. 5.
    Carder K L, Chen F R, Lee Z P, Hawes S K and Kamykowski D. 1999. Semianalytic Moderate-Resolution Imaging Spectrometer algorithms for chlorophyll a and absorption with bio-optical domains based on nitrate-depletion temperatures. Journal of Geophysical Research: Oceans, 104(C3): 5403-5421
  6. 6.
    Carvalho L, McDonald C, de Hoyos C, Mischke U, Phillips G, Borics G, Poikane S, Skjelbred B, Solheim A L, Van Wichelen J and Cardoso A C. 2013. Sustaining recreational quality of European lakes: minimizing the health risks from algal blooms through phosphorus control. Journal of Applied Ecology, 50(2): 315-323
  7. 7.
    Catherine A, Escoffier N, Belhocine A, Nasri A B, Hamlaoui S, Yéprémian C, Bernard C and Troussellier M. 2012. On the use of the FluoroProbe®, a phytoplankton quantification method based on fluorescence excitation spectra for large-scale surveys of lakes and reservoirs. Water Research, 46(6): 1771-1784
  8. 8.
    Chen S G, Du K P, Lee Z P, Liu J Q, Song Q J, Xue C, Wang D S, Lin M S, Tang J W and Ma C F. 2021. Performance of COCTS in global ocean color remote sensing. IEEE Transactions on Geoscience and Remote Sensing, 59(2): 1634-1644
  9. 9.
    Chen X Y, Zhang J, Tong C, Liu R J, Mu B and Ding J. 2019. Retrieval algorithm of chlorophyll-a concentration in turbid waters from satellite HY-1C coastal zone imager data. Journal of Coastal Research, 90(SI): 146-155
  10. 10.
    Dierssen H M. 2010. Perspectives on empirical approaches for ocean color remote sensing of chlorophyll in a changing climate. Proceedings of the National Academy of Sciences of the United States of America, 107(40): 17073-17078
  11. 11.
    Dransfeld S, Tatnall A R, Robinson I S and Mobley C D. 2004. A comparison of Multi-layer Perceptron and multilinear regression algorithms for the inversion of synthetic ocean colour spectra. International Journal of Remote Sensing, 25(21): 4829-4834
  12. 12.
    Dunstan P K, Foster S D, King E, Risbey J, O’Kane T J, Monselesan D, Hobday A J, Hartog J R and Thompson P A. 2018. Global patterns of change and variation in sea surface temperature and chlorophyll a. Scientific Reports, 8: 14624
  13. 13.
    Hagan M T and Menhaj M B. 1994. Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6): 989-993
  14. 14.
    Han B, Jia D, Gao F, Guo K, Zhu J H, Li T J, Ma C F, Liu J Q and Zibordi G. 2023. Validation of L2A operational products of COCTS onboard HY-1C satellite across coastal waters in China and Europe. National Remote Sensing Bulletin, 27(1): 26-42
  15. 15.
    Hecht-Nielsen R. 1992. Theory of the backpropagation neural network//Wechsler H, ed. Neural Networks for Perception. San Diego: Academic Press: 65-93
  16. 16.
    Henson S A, Sarmiento J L, Dunne J P, Bopp L, Lima I, Doney S C, John J and Beaulieu C. 2010. Detection of anthropogenic climate change in satellite records of ocean chlorophyll and productivity. Biogeosciences, 7(2): 621-640
  17. 17.
    Holm-Hansen O, Lorenzen C J, Holmes R W and Strickland J D H. 1965. Fluorometric determination of chlorophyll. ICES Journal of Marine Science, 30(1): 3-15
  18. 18.
    Holm-Hansen O and Riemann B. 1978. Chlorophyll a determination: improvements in methodology. Oikos, 30(3): 438-447
  19. 19.
    Hu C M, Feng L, Lee Z P, Franz B A, Bailey S W, Werdell P J and Proctor C W. 2019. Improving satellite global chlorophyll a data products through algorithm refinement and data recovery. Journal of Geophysical Research: Oceans, 124(3): 1524-1543
  20. 20.
    Hu C M, Lee Z P and Franz B. 2012. Chlorophyll a algorithms for oligotrophic oceans: a novel approach based on three-band reflectance difference. Journal of Geophysical Research: Oceans, 117(C1): C01011
  21. 21.
    Hu Q W, Chen X Y, Bai Y, He X Q, Li T and Pan D L. 2023. Reconstruction of 3-D ocean chlorophyll a structure in the Northern Indian Ocean using satellite and BGC-Argo data. IEEE Transactions on Geoscience and Remote Sensing, 61: 4200513
  22. 22.
    Huot Y, Babin M, Bruyant F, Grob C, Twardowski M S and Claustre H. 2007. Does chlorophyll a provide the best index of phytoplankton biomass for primary productivity studies?. Biogeosciences Discussions, 4: 707-745
  23. 23.
    Jiang X W, He X Q, Lin M S, Gong F, Ye X M and Pan D L. 2019. Progresses on ocean satellite remote sensing application in China. Haiyang Xuebao, 41(10): 113-124
  24. 24.
    Kim T and Adali T. 2002. Fully complex multi-layer perceptron network for nonlinear signal processing. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 32(1): 29-43
  25. 25.
    Kim Y W, Kim T H, Shin J, Lee D S, Park Y S, Kim Y and Cha Y K. 2022. Validity evaluation of a machine-learning model for chlorophyll a retrieval using Sentinel-2 from inland and coastal waters. Ecological Indicators, 137: 108737
  26. 26.
    Laignel B, Vignudelli S, Almar R, Becker M, Bentamy A, Benveniste J, Birol F, Frappart F, Idier D, Salameh E, Passaro M, Menende M, Simard M, Turki E I and Verpoorter C. 2023. Observation of the coastal areas, estuaries and deltas from space. Surveys in Geophysics, 44(5): 1309-1356
  27. 27.
    Lee Z P, Carder K L and Arnone R A. 2002. Deriving inherent optical properties from water color: a multiband quasi-analytical algorithm for optically deep waters. Applied Optics, 41(27): 5755-5772
  28. 28.
    Lee Z P, Pahlevan N, Ahn Y H, Greb S and O’Donnell D. 2013. Robust approach to directly measuring water-leaving radiance in the field. Applied Optics, 52(8): 1693-1701
  29. 29.
    Li X L, Yang Y, Ishizaka J and Li X F. 2023. Global estimation of phytoplankton pigment concentrations from satellite data using a deep-learning-based model. Remote Sensing of Environment, 294: 113628
  30. 30.
    Li X Z, Su R G, Zhang C S and Shi X Y. 2019. A Chl-a prediction model based on support vector machine in Yangtze River estuaries and its adjacent sea areas. Periodical of Ocean University of China, 49(1): 69-76
  31. 31.
    Li Z F, Han B, Jia D and Zhu J H. 2022. Evaluation of remote sensing inversion algorithm and COCTS Inversion Algorithm for chlorophyll a concentration in the north South China Sea. Journal of Ocean Technology, 41(6): 1-7
  32. 32.
    Lin L, Liu D Y, Fu Q J, Guo X Y, Liu G L, Liu H and Wang S L. 2022. Seasonal variability of water residence time in the Subei Coastal Water, Yellow Sea: the joint role of tide and wind. Ocean Modelling, 180: 102137
  33. 33.
    Liu J Q, Ye X M, Song Q J, Ding J and Zou B. 2023. Products of HY-1C/D ocean color satellites and their typical applications. National Remote Sensing Bulletin, 27(1): 1-13
  34. 34.
    Morel A and Prieur L. 1977. Analysis of variations in ocean color1. Limnology and Oceanography, 22(4): 709-722
  35. 35.
    Mukherjee I and Routroy S. 2012. Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process. Expert Systems with Applications, 39(3): 2397-2407
  36. 36.
    Nazeer M, Ilori C O, Bilal M, Nichol J E, Wu W C, Qiu Z F and Gayene B K. 2021. Evaluation of atmospheric correction methods for low to high resolutions satellite remote sensing data. Atmospheric Research, 249: 105308
  37. 37.
    Nechad B, Ruddick K, Schroeder T, Oubelkheir K, Blondeau-Patissier D, Cherukuru N, Brando V, Dekker A, Clementson L, Banks A C, Maritorena S, Werdell P J, Sá C, Brotas V, Caballero de Frutos I, Ahn Y H, Salama S, Tilstone G, Martinez-Vicente V, Foley D, McKibben M, Nahorniak J, Peterson T, Siliò-Calzada A, Röttgers R, Lee Z, Peters M and Brockmann C. 2015. CoastColour Round Robin data sets: a database to evaluate the performance of algorithms for the retrieval of water quality parameters in coastal waters. Earth System Science Data, 7(2): 319-348
  38. 38.
    O'Reilly J E, Maritorena S, Mitchell B G, Siegel D A, Carder K L, Garver S A, Kahru M and McClain C. 1998. Ocean color chlorophyll algorithms for SeaWiFS. Journal of Geophysical Research: Oceans, 103(C11): 24937-24953
  39. 39.
    O'Reilly J E and Werdell P J. 2019. Chlorophyll algorithms for ocean color sensors-OC4, OC5 and OC6. Remote Sensing of Environment, 229: 32-47
  40. 40.
    Pahlevan N, Smith B, Schalles J, Binding C, Cao Z G, Ma R H, Alikas K, Kangro K, Gurlin D, Hà N, Matsushita B, Moses W, Greb S, Lehmann M K, Ondrusek M, Oppelt N and Stumpf R. 2020. Seamless retrievals of chlorophyll-a from Sentinel-2 (MSI) and Sentinel-3 (OLCI) in inland and coastal waters: a machine-learning approach. Remote Sensing of Environment, 240: 111604
  41. 41.
    Ritchie R J. 2006. Consistent sets of spectrophotometric chlorophyll equations for acetone, methanol and ethanol solvents. Photosynthesis Research, 89(1): 27-41
  42. 42.
    Rußwurm M, Klemmer K, Rolf E, Zbinden R and Tuia D. 2024. Geographic location encoding with spherical harmonics and sinusoidal representation networks. arXiv preprint arXiv: 2310.06743
  43. 43.
    Shahvaran A R, Kheyrollah Pour H and Van Cappellen P. 2024. Comparative evaluation of semi-empirical approaches to retrieve satellite-derived chlorophyll-a concentrations from nearshore and offshore waters of a large lake (Lake Ontario). Remote Sensing, 16(9): 1595
  44. 44.
    Shen C Y, Zhao H, Chen F J and Xiao H W. 2020. The distribution of aerosols and their impacts on chlorophyll-a distribution in the South China Sea. Journal of Geophysical Research: Biogeosciences, 125(6): e2019JG005490
  45. 45.
    Shi X H, Chen S G, Lin M S, Liu J Q, Ma C F, Song Q J, Xue C and Hu L B. 2023. Preliminary performance of the COCTS onboard HY-1D satellite in the global ocean. National Remote Sensing Bulletin, 27(4): 943-952
  46. 46.
    Smith B, Pahlevan N, Schalles J, Ruberg S, Errera R, Ma R H, Giardino C, Bresciani M, Barbosa C, Moore T, Fernandez V, Alikas K and Kangro K. 2021. A chlorophyll-a algorithm for Landsat-8 based on mixture density networks. Frontiers in Remote Sensing, 1: 623678
  47. 47.
    Sola J and Sevilla J. 1997. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transactions on Nuclear Science, 44(3): 1464-1468
  48. 48.
    Song Q J, Ma C F, Lin M S, Jiang X W, Wang L L, Xu P M, Tang J W, Chen P, Lu Y C, Wei J and Zhang K L. 2025. Advances in ocean color observation satellite technology. National Remote Sensing Bulletin, 29(6): 399-1425
  49. 49.
    Soomets T, Toming K, Paavel B and Kutser T. 2022. Evaluation of remote sensing and modeled chlorophyll-a products of the Baltic Sea. Journal of Applied Remote Sensing, 16(4): 046516
  50. 50.
    Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1): 1929-1958
  51. 51.
    Teng Y, Zou B and Ye X M. 2022. Study on the chlorophyll a concentration retrieved from HY-1C satellite coastal zone imager data. Haiyang Xuebao, 44(5): 25-34
  52. 52.
    Tran M D, Vantrepotte V, Loisel H, Oliveira E N, Tran K T, Jorge D, Mériaux X and Paranhos R. 2023. Band ratios combination for estimating chlorophyll-a from Sentinel-2 and Sentinel-3 in coastal waters. Remote Sensing, 15(6): 1653
  53. 53.
    Trombetta T, Vidussi F, Mas S, Parin D, Simier M and Mostajir B. 2019. Water temperature drives phytoplankton blooms in coastal waters. PLoS One, 14(4): e0214933
  54. 54.
    Valente A, Sathyendranath S, Brotas V, Groom S, Grant M, Jackson T, Chuprin A, Taberner M, Airs R, Antoine D, Arnone R, Balch W M, Barker K, Barlow R, Bélanger S, Berthon J F, Beşiktepe Ş, Borsheim Y, Bracher A, Brando V, Brewin R J W, Canuti E, Chavez F P, Cianca A, Claustre H, Clementson L, Crout R, Ferreira A, Freeman S, Frouin R, García-Soto C, Gibb S W, Goericke R, Gould R, Guillocheau N, Hooker S B, Hu C, Kahru M, Kampel M, Klein H, Kratzer S, Kudela R, Ledesma J, Lohrenz S, Loisel H, Mannino A, Martinez-Vicente V, Matrai P, McKee D, Mitchell B G, Moisan T, Montes E, Muller-Karger F, Neeley A, Novak M, O’Dowd L, Ondrusek M, Platt T, Poulton A J, Repecaud M, Röttgers R, Schroeder T, Smyth T, Smythe-Wright D, Sosik H M, Thomas C, Thomas R, Tilstone G, Tracana A, Twardowski M, Vellucci V, Voss K, Werdell J, Wernand M, Wojtasiewicz B, Wright S and Zibordi G. 2022. A compilation of global bio-optical in situ data for ocean colour satellite applications – version three. Earth System Science Data, 14(12): 5737-5770
  55. 55.
    Volpe G, Santoleri R, Vellucci V, d’Alcalà M R, Marullo S and d’Ortenzio F. 2007. The colour of the Mediterranean Sea: global versus regional bio-optical algorithms evaluation and implication for satellite chlorophyll estimates. Remote Sensing of Environment, 107(4): 625-638
  56. 56.
    Wang D S, Du K P, Chen S G, Xue C, Ye X M and Lee Z P. 2023. Construction of ocean color remote sensing data processing system based on open source code: taking HY-1C/D as an example. National Remote Sensing Bulletin, 27(1): 68-78
  57. 57.
    Wright S W, Jeffrey S W, Mantoura R F C, Llewellyn C A, Bjørnland T, Repeta D and Welschmeyer N. 1991. Improved HPLC method for the analysis of chlorophylls and carotenoids from marine phytoplankton. Marine Ecology Progress Series, 77(2/3): 183-196
  58. 58.
    Yang G Y, Ye X M, Xu Q, Yin X B and Xu S Y. 2023. Sea surface chlorophyll-a concentration retrieval from HY-1C satellite data based on residual network. Remote Sensing, 15(14): 3696
  59. 59.
    Yang N S, Shi H Z, Tang H and Yang X. 2022. Geographical and temporal encoding for improving the estimation of PM2.5 concentrations in China using end-to-end gradient boosting. Remote Sensing of Environment, 269: 112828
  60. 60.
    Ye X M, Liu J Q, Lin M S, Ding J, Zou B and Song Q J. 2021. Global ocean chlorophyll-a concentrations derived from COCTS onboard the HY-1C satellite and their preliminary evaluation. IEEE Transactions on Geoscience and Remote Sensing, 59(12): 9914-9926
  61. 61.
    Yu X L, Lee Z P, Shang Z H, Lin H and Lin G. 2021. A simple and robust shade correction scheme for remote sensing reflectance obtained by the skylight-blocked approach. Optics Express, 29(1): 470-486
  62. 62.
    Zhang T L, Fell F, Liu Z S, Preusker R, Fischer J and He M X. 2003. Evaluating the performance of artificial neural network techniques for pigment retrieval from ocean color in Case I waters. Journal of Geophysical Research: Oceans, 108(C9): 3286
  63. 63.
    Zhang T L and He M X. 2002. A method to retrieve the oceanic chlorophyll-a concentrations in case I water based on artificial neural network. Journal of Remote Sensing (in Chinese), 6(1): 40-44
  64. 64.
    Zhang Y, Shen F, Li R H, Li M Y, Li Z X, Chen S Y and Sun X R. 2024. AIGD-PFT: the first AI-driven global daily gap-free 4 km phytoplankton functional type data product from 1998 to 2023. Earth System Science Data, 16(10): 4793-4816
  65. 65.
    Zheng Q H, Yang M Q, Yang J J, Zhang Q R and Zhang X X. 2018. Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process. IEEE Access, 6: 15844-15869
  66. 66.
    Zhu B H, Yuan Y B and Hu J B. 2021. Spatial and temporal distribution characteristics of chlorophyll-a in the Eastern China seas based on field data. Jiangsu Science and Technology Information, 38(34): 74-80
  67. 67.
    Zhu Y F, Zhu L, Li J G, Chen Y J, Zhang Y H, Hou H Q, Ju X and Zhang Y Z. 2017. The study of inversion of chlorophyll a in Taihu based on GF-1 WFV image and BP neural network. Acta Scientiae Circumstantiae, 37(1): 130-137

Leia o texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website