بررسی تغییرات ماده آلی محلول رنگی (CDOM) با استفاده از الگوریتم SVM و تصاویر ماهواره لندست 8 در منابع آبهای سطحی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته کارشناسی ارشد مهندسی سنجش از دور دانشگاه آزاد اسلامی واحد تهران جنوب، تهران، ایران

2 استادیار گروه مهندسی نقشه برداری، دانشگاه آزاد، واحد تهران جنوب، تهران، ایران

چکیده

 
ماده آلی محلول رنگی (CDOM)1 یکی از اجزای اصلی DOM2 در آب‌های سطحی است و شاخصی مهم در کیفیت آب، وضعیت بیوشیمی و محتوای مواد مغذی است و نقش مهمی در چرخه کربن در آب‌های سطحی دارد. در این پژوهش به تحلیل ماده آلی محلول رنگی (CDOM) در دریاچه‌ها با استفاده از تصاویر لندست 8 در سال‌های 2013 تا 2016 در دریاچه‌های شمال سیبری پـرداخته شــده است. از مــدل بهینه رگرسیون بـردار پشتیبان (GA-SVR) برای انتخاب مناسب‌ترین باند در تعیین ضریب جذب CDOM استفاده شده است و با استفاده از مدل ماشین بردار پشتیان (SVM) به ‌منظور طبقه‌بندی و مقایسه تغییرات میزان  (ضریب جذب CDOM در طیف 440 نانومتر) نقشه مکانی پراکندگی CDOM در سال‌های
2014 و 2015 بدست آمده است. بر اساس نتایج حاصله، با توجه به
ضریب همبستگی (71/0= ) و میزان خطاها  ( 610/1MSE=،
 0775/1RMSE= و  9464/0MAE=) نتیجه گرفته شد که استفاده از نسبت باندهای سبز به قرمز در ماهواره‌ی لندست 8 مناسب‌ترین انتخاب برای تعیین ماده آلی محلول رنگی در طول موج 440 نانومتر در منطقه مطالعاتی است. نقشه پراکندگی نمایانگر افزایش مقدار ماده آلی محلول رنگی در دریاچه‌های شمال- شرقی منطقه در سال 2015 نسبت به سال 2014 است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Survey of Changes in Colored Dissolved Organic Matter (CDOM) Using SVM Algorithm and Landsat 8 Satellite Images in Surface Water Resources

نویسندگان [English]

  • Mohammad Momeni Esfahani 1
  • Amir Shahrokh Amini 2
1 M.Sc., Department of Surveying Engineering, Islamic Azad University, South Tehran Branch, Tehran, Iran
2 Associate Professor, Department of surveying Engineering, Islamic Azad University South Tehran Branch, Tehran, Iran
چکیده [English]

Colored dissolved organic matter (CDOM), one of the main constituents of DOM in surface water, is an important indicator of water quality, the biochemical status, and the nutritious material content and plays an important role in the carbon cycle of surface water. In this study, we have analyzed colored dissolved organic matter (CDOM) in lakes using Landsat 8 images in the period of 2013 to 2016 in the watershed area of North Siberia. The support vector regression model was used for selecting the most desirable band in determining the CDOM absorption coefficient, and using the support vector machine model to classify and compare the changes in the amount of〖 α〗_CDOM (440), the CDOM scatter plots for the years of 2014 and 2015 were obtained. Based on the results, regarding the correlation coefficient (R2=0/71) and the amount of errors (MSE=1/60 m-1, RMSE=1/0775 m-1, and MAE=0/9464 m-1), it was concluded that the application of green/red band ratio in Landsat 8 satellite was the most desirable choice for measuring colored dissolved organic matter at a wavelength of 440 nm in watershed resources of North Russia. The scatter plot indicates an increase in colored dissolved organic matter in the lakes in the northeast of the area in 2015 compared to 2014.

کلیدواژه‌ها [English]

  • Colored Dissolved Organic Matter
  • SVR
  • SVM
  • Landsat 8
Babin M, Stramski D, Ferrari GM, Claustre H, Bricaud A, Obolensky G, and Hoepffner N (2003) Variations in the light absorption coefficients of phytoplankton, nonalgal particles, and dissolved organic matter in coastal waters around Europe. Journal of Geophysical Research: Oceans, Wiley Online Library 108(C7)
Brezonik PL, Olmanson LG, Finlay JC, and Bauer ME (2015) Factors affecting the measurement of CDOM by remote sensing of optically complex inland waters. Remote Sensing of Environment, 157:199–215
Budac D and Wan P (1992) Photodecarboxylation: Mechanism and synthetic utility. Journal of Photochemistry and Photobiology A: Chemistry 67(2):135–166
Ferrari GM and Tassan S (1992) Evaluation of the influence of yellow substance absorption on the remote sensing of water quality in the Gulf of Naples: a case study. International Journal of Remote Sensing 13(12):2177–2189
Häder D-P, Kumar HD, Smith RC, and Worrest RC (2007) Effects of solar UV radiation on aquatic ecosystems and interactions with climate change. Photochemical & Photobiological Sciences, Royal Society of Chemistry 6(3):267–285
Jansson M (1998) Nutrient limitation and bacteria-Phytoplankton interactions in humic lakes. Aquatic Humic Substances, Springer 177–195
Johannessen SC and Miller WL (2001) Quantum yield for the photochemical production of dissolved inorganic carbon in seawater. Marine Chemistry 76(4):271–283
Karabashev GS, Khanaev SA, and Kuleshov AF (1993) On the variability of yellow substance in the Skagerrak and the Kattegat. Oceanologica acta. Gauthier-Villars 16(2):115–125
Kheireddine M, Ouhssain M, Calleja ML, Morán XAG, Sarma YVB, Tiwari SP, and Jones BH (2018) Characterization of light absorption by Chromophoric Dissolved Organic Matter (CDOM) in the upper layer of the Red Sea. Deep Sea Research Part I: Oceanographic Research Papers, Elsevier 133:72–84
Kutser T, Alikas K, Kothawala DN, and Köhler SJ (2015) Impact of iron associated to organic matter on remote sensing estimates of lake carbon content. Remote Sensing of Environment 156:109–116
Kutser T, Pierson DC, Kallio KY, Reinart A, and Sobek S (2005) Mapping lake CDOM by satellite remote sensing. Remote Sensing of Environment 94(4):535–540
Kutser T, Tranvik L, and Pierson DC (2009) Variations in colored dissolved organic matter between boreal lakes studied by satellite remote sensing. Journal of Applied Remote Sensing, International Society for Optics and Photonics 3(1):33538
Kutser T, Verpoorter C, Paavel B, and Tranvik LJ (2015) Estimating lake carbon fractions from remote sensing data. Remote Sensing of Environment 157:138–146
Lv Z, Tang B, Zhou Y, and Zhou C (2016) A novel method for mechanical fault diagnosis based on variational mode decomposition and multikernel support vector machine. Shock and Vibration, Hindawi 2016
Moss B (2012) Cogs in the endless machine: lakes, climate change and nutrient cycles: A review. Science of the Total Environment, Elsevier 434:130–142
Nelson NB and Siegel DA (2013) The global distribution and dynamics of chromophoric dissolved organic matter. Annual Review of Marine Science, Annual Reviews 5:447–476
Opsahl SP and Zepp RG (2001) Photochemically‐induced alteration of stable carbon isotope ratios (δ13C) in terrigenous dissolved organic carbon. Geophysical Research Letters, Wiley Online Library 28(12):2417–2420
Opsahl S and Benner R (1998) Photochemical reactivity of dissolved lignin in river and ocean waters. Limnology and Oceanography 43(6):1297–1304
Organelli E, Bricaud A, Antoine D, and Matsuoka A (2014) Seasonal dynamics of light absorption by Chromophoric Dissolved Organic Matter (CDOM) in the NW Mediterranean Sea (BOUSSOLE site). Deep Sea Research Part I: Oceanographic Research Papers. Elsevier 91:72–85
Ruescas AB, Hieronymi M, Mateo-Garcia G, Koponen S, Kallio K, and Camps-Valls G (2018) Machine learning regression approaches for Colored Dissolved Organic Matter (CDOM) retrieval with S2-MSI and S3-OLCI simulated data. Remote Sensing, Multidisciplinary Digital Publishing Institute 10(5):786
Siegel DA, Maritorena S, Nelson NB, Hansell DA, and Lorenzi‐Kayser M (2002) Global distribution and dynamics of colored dissolved and detrital organic materials. Journal of Geophysical Research: Oceans 107(C12):21
Slonecker ET, Jones DK and Pellerin BA (2016) The new Landsat 8 potential for remote sensing of colored dissolved organic matter (CDOM). Marine Pollution Bulletin 107(2):518–527
Tassan S (1988) The effect of dissolved “yellow substance” on the quantitative retrieval of chlorophyll and total suspended sediment concentrations from remote measurements of water colour. Remote Sensing 9(4):787–797
Tranvik LJ (1992) Allochthonous dissolved organic matter as an energy source for pelagic bacteria and the concept of the microbial loop. Dissolved organic matter in lacustrine ecosystems, Springer, 107–114
Tu J V (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of Clinical Epidemiology 49(11):1225–1231
Vähätalo A V, Salonen K, Salkinoja-Salonen M, and Hatakka A (1999) Photochemical mineralization of synthetic lignin in lake water indicates enhanced turnover of aromatic organic matter under solar radiation. Biodegradation 10(6):415–420
Vapnik VN (1995) The nature of statistical learning. Theory, Springer
Yu H and Kim S (2012) SVM tutorial-classification, regression and ranking. Handbook of Natural computing 1:479–506
Yuan S-F and Chu F-L (2006) Support vector machines-based fault diagnosis for turbo-pump rotor. Mechanical Systems and Signal Processing 20(4):939–952