پایش سطح تغذیه‌گرایی در دریاچه ارومیه با استفاده از الگوریتم‌های رگرسیون خطی چند متغیره و شبکه‌ عصبی مصنوعی مبتنی بر تصاویر ماهواره‌ای لندست-8 و سنتینل-2

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد مهندسی و مدیریت منابع آب، گروه مهندسی آب، دانشکده عمران و محیط زیست، دانشگاه تربیت مدرس.

2 استادیار گروه مهندسی آب، دانشکده عمران و محیط زیست، دانشگاه تربیت مدرس.

چکیده

پایش پیوسته غلظت کلروفیل و تعیین سطح تغذیه‌گرایی در دریاچه‌ها به منظور مدیریت کیفیت آب آن‌ها ضروری است. هدف این پژوهش مدل‎سازی غلظت کلروفیل-آ به عنوان متغیر کلیدی مرتبط با تغذیه‌گرایی در بخش شمالی دریاچه ارومیه با استفاده از تصاویر ماهواره‌های لندست-8 و سنتینل-2 و الگوریتم‌های رگرسیون خطی چند متغیره (MLR) و شبکه‌ عصبی مصنوعی (ANN) است. نتایج نشان داد در حالی که هر دو مدل مبتنی بر تصاویر لندست-8 (ANNLandsat -8 و MLRLandsat -8) از دقت بالایی در پایش غلظت کلروفیل-آ برخوردار بودند، عملکرد مدل‌های منتخب مبتنی بر تصاویر سنتینل-2 (ANNSentinel -2 و MLRSentinel -2) رضایت بخش نبودند. در هر دو سری مدل‌های کلروفیل-آ مبتنی بر داده‌های لندست-8 و سنتینل-2، مدل ANN (با یک لایه مخفی) نسبت به مدل MLR اندکی برتری داشت. با توجه به عملکرد مناسب مدل‌ منتخب ANNLandsat-8  از این مدل برای تحلیل الگوی تغییرات مکانی و زمانی غلظت کلروفیل-آ و سطح تغذیه‌گرایی در شمال دریاچه ارومیه استفاده شد. تحلیل الگوی تغییرات مکانی غلظت کلروفیل-آ در تمامی ماه‌ها، افزایش غلظت به سمت مرکز و نواحی عمیق شمال دریاچه و کاهش به سمت پل میان‌گذر را نشان داد. همچنین، میانگین غلظت کلروفیل-آ و سطح تغذیه‌‎گرایی در شمال دریاچه، از فوریه تا جولای به صورت قابل توجهی افزایش، از جولای تا سپتامبر کاهش و از سپتامبر تا اکتبر افزایش یافت. نتایج مدل منتخب (ANNLandsat -8)، نشان داد که شمال دریاچه در ماه‌های فوریه و سپتامبر سال 2016 در شرایط مزوتروفیک حاد و در ماه‌های جولای، آگوست و اکتبر در شرایط یوتروفیک خفیف قرار داشته است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Monitoring Trophic State of Lake Urmia Using Multiple Linear Regression and Artificial Neural Network Based on Landsat-8 and Sentinel-2 Satellite Images

نویسندگان [English]

  • Amirsepehr Shamloo 1
  • Somayeh Sima 2
1 M.Sc. Graduate of Engineering and Water Resource Management, Civil & Environmental Engineering Department, Tarbiat Modares University, Tehran, Iran.
2 Assistant Professor, Civil & nvironmental Engineering Department, Tarbiat Modares University, Tehran, Iran
چکیده [English]

Water quality management in inland lakes requires continuous monitoring of chlorophyll-a (Chl-a) concentration and trophic state. As a critical variable of eutrophication, concentration of Chl-a in the northern part of the Lake Urmia was modeled using Multiple Linear Regression (MLR) and Artificial Neural Networks (ANN) models developed based on Landsat-8 and Sentinel-2 satellite images. Based on Landsat-8 images both models (ANNLandsat-8, MLRLandsat-8) accurately estimated Chl-a concentration in the north of Lake Urmia, while models based on Sentinel-2 images (MLRSentinel-2 and ANNSentinel-2) showed poor performances. Moreover, the ANN models performed slightly better than MLR models based on both Landsat-8 and Sentinel-2 images. According to the better performance, the optimum ANNlandsat-8 model (with a hidden layer) was used to analyze the spatiotemporal variation of Chl-a concentration and the trophic state index (TSI). In the northern part of the Lake Urmia, analysis of the spatial pattern of Chl-a concentration showed an increase towards the central deeper parts and a decrease towards the causeway. Furthermore, the average concentration of Chl-a and TSI in the northern section of the lake increased significantly from February to July followed by a drop between July to September and then a rise between September and October. Based on the optimum ANNLandsat-8 model, northern Lake Urmia experienced acute mesotrophic conditions in February and September of 2016, and mild eutrophic conditions in July, August, and October.

کلیدواژه‌ها [English]

  • Trophic State
  • Chlorophyll-a
  • Carlson Trophic Index
  • Atmospheric Correction
Aizaki M (1981) Application of modified Carlson’s trophic state index to Japanese lake and its relationships to other parameters. related to trophic state. Res. Rep. National Institute for Environmental Studies, Japan 23:13-31
Alipour S (2006) Hydrogeochemistry of seasonal variation of Urmia Salt Lake, Iran. Saline Systems 2(1):1–19
Allan MG, Hicks BJ, and Brabyn L (2007). Remote sensing of water quality in the Rotorua lakes. CBER Contract Report
Alparslan E, Aydöner C, Tufekci V, and Tüfekci H (2007) Water quality assessment at Ömerli Dam using remote sensing techniques. Environmental Monitoring and Assessment 135(1):391–398
Azari TG (1991) Uromieh lake as a valuable source of Artemia for feeding sturgeon fry. The Journal of Faculty of Veterinary Medicine, Teheran Universiy 47:1–14
Bayati M and Danesh-Yazdi M (2021) Mapping the spatiotemporal variability of salinity in the hypersaline Lake Urmia using Sentinel-2 and Landsat-8 imagery. Journal of Hydrology 595:126032
Buma WG and Lee S-I (2020) Evaluation of sentinel-2 and landsat 8 images for estimating chlorophyll-a concentrations in lake Chad, Africa. Remote Sensing, MDPI 12(15):2437
Carlson RE (1977) A trophic state index for lakes 1. Limnology and oceanography. Wiley Online Library 22(2):361–369
Cawley GC and Talbot NLC (2003) Efficient leave-one-out cross-validation of kernel fisher discriminant classifiers. Pattern Recognition, Elsevier 36(11):2585–2592
Chavula G, Brezonik P, Thenkabail P, Johnson T, and Bauer M (2009) Estimating chlorophyll concentration in Lake Malawi from MODIS satellite imagery. Physics and Chemistry of the Earth, Parts A/B/C, Elsevier 34(13–16):755–760
Dahesht LE, Mustafayev Q, Mohebbi F, and Ahmadi R (2013) Relationship between Artemia population dynamics and chlorophyll a fluctuation in Urmia Lake (Iran). Brazilian Journal of Aquatic Science and Technology, Citeseer 17(2):1–6
Danesh-Yazdi M and Ataie-Ashtiani B (2019) Lake Urmia crisis and restoration plan: Planning without appropriate data and model is gambling. Journal of Hydrology 576:639–651
Darzi A and Sima S (2021) Monitoring spatiotemporal variation of Lake Urmia Surface Albedo using MODIS Satellite Data. Iran-Water Resources Research 17(2):190–203 (In Persian)
 Dehghanipour AH, Moshir Panahi D, Mousavi H, Kalantari Z, and Tajrishy M (2020) Effects of water level decline in Lake Urmia, Iran, on local climate conditions. Water, Multidisciplinary Digital Publishing Institute 12(8):2153
Dekker AG and Peters SWM (1993) The use of the thematic mapper for the analysis of eutrophic lakes: a case study in the Netherlands. International Journal of Remote Sensing, Taylor & Francis 14(5):799–821
Directive EUW (1991) Council Directive of 21. May 1991 concerning urban waste water treatment (91/271/EEC). European Journal of Communication 34:40
Dodds WK, Bouska WW, Eitzmann JL, Pilger TJ, Pitts KL, Riley AJ, Schloesser JT, and Thornbrugh DJ (2009) Eutrophication of US freshwaters: Analysis of potential economic damages. Environmental Science & Technology 43(1):12-19
Doxaran D, Froidefond J-M, and Castaing P (2002) A reflectance band ratio used to estimate suspended matter concentrations in sediment-dominated coastal waters. International Journal of Remote Sensing 23(23):5079–5085
Esmaeili Dahesht L, Negarestan H, Eimanifar A, Mohebbi F, and Ahmadi R (2010) The fluctuations of physicochemical factors and phytoplankton populations of Urmia Lake, Iran. Iranian Journal of Fisheries Sciences, Agricultural Research, Education and Extension Organization 9(3):361–381
Giardino C, Pepe M, Brivio PA, Ghezzi P, and Zilioli E (2001) Detecting chlorophyll, Secchi disk depth and surface temperature in a sub-alpine lake using Landsat imagery. Science of the Total Environment 268(1–3):19–29
Gordon HR and Wang M (1994) Retrieval of water-leaving radiance and aerosol optical thickness over the oceans with SeaWiFS: A preliminary algorithm. Applied optics. Optical Society of America 33(3):443–452
Guo Q, Wu X, Bing Q, Pan Y, Wang Z, Fu Y, Wang D, and Liu J (2016) Study on retrieval of chlorophyll-a concentration based on Landsat OLI Imagery in the Haihe River, China. Sustainability 8:758
Ha NTT, Koike K, Nhuan MT, Canh BD, Thao NTP, and Parsons M (2017a) Landsat 8/OLI two bands ratio algorithm for chlorophyll-a concentration mapping in hypertrophic waters: An application to West Lake in Hanoi (Vietnam). IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10(11):4919–4929
Ha NTT, Thao NTP, Koike K, and Nhuan MT (2017b) Selecting the best band ratio to estimate chlorophyll-a concentration in a tropical freshwater lake using sentinel 2A images from a case study of Lake Ba Be (Northern Vietnam). ISPRS International Journal of Geo-Information 6:290
Han L and Jordan KJ (2005) Estimating and mapping chlorophyll‐a concentration in Pensacola Bay, Florida using Landsat ETM+ data. International Journal of Remote Sensing, Taylor & Francis 26(23):5245–5254
Hellweger FL, Schlosser P, Lall U, and Weissel JK (2004) Use of satellite imagery for water quality studies in New York Harbor. Estuarine, Coastal and Shelf Science, Elsevier 61(3):437–448
Hoagland P and Scatasta S (2006) The economic effects of harmful algal blooms. Ecology of Harmful Algae, Springer, 391–402
Ilori CO, Pahlevan N, and Knudby A (2019) Analyzing performances of different atmospheric correction techniques for Landsat 8: application for coastal remote sensing. Remote Sensing 11:469
Iranian Water and Power Resources Development Company (IWPCO) (2018) Urmia Lake: Results of limnological and biological monitoring of main water body and satellite wetlands of Lake Urmia. Iranshenasi, Tehran, Iran (In Persian)
Jellison R and Melack JM (2001) Nitrogen limitation and particulate elemental ratios of seston in hypersaline Mono Lake, California, USA. Saline Lakes. Springer, 1–12
Jensen JR (2011) Sensoriamento remoto do ambiente: Uma perspectiva em recursos terrestres. Parêntese: São José dos Campos, Brasil (In Portuguese)
Kallio K (2000) Remote sensing as a tool for monitoring lake water quality. Hydrological and Limnological Aspects of Lake Monitoring, John Wiley & Sons, Ltd. Chichester, England 14:237
Kallio K, Kutser T, Hannonen T, Koponen S, Pulliainen J, Vepsäläinen J, and Pyhälahti T (2001) Retrieval of water quality from airborne imaging spectrometry of various lake types in different seasons. Science of the Total Environment, Elsevier 268(1–3):59–77
Karaoui I, Arioua A, Boudhar A, Hssaisoune M, El Mouatassime S, Ouhamchich KA, Elhamdouni D, Idrissi AEA, and Nouaim W (2019) Evaluating the potential of Sentinel-2 satellite images for water quality characterization of artificial reservoirs: The Bin El Ouidane Reservoir case study (Morocco). Meteorology Hydrology and Water Management, Research and Operational Applications 7(1):31–39
Karimi N, Bagheri MH, Hooshyaripor F, Farokhnia A and Sheshangosht S (2016) Deriving and evaluating bathymetry maps and stage curves for shallow lakes using remote sensing data. Water Resources Management, Springer 30(14):5003–5020
Kloiber SM, Brezonik PL, Olmanson LG, and Bauer ME (2002) A procedure for regional lake water clarity assessment using Landsat multispectral data. Remote sensing of Environment, Elsevier 82(1):38–47
Kutser T (2012) The possibility of using the Landsat image archive for monitoring long time trends in coloured dissolved organic matter concentration in lake waters. Remote Sensing of Environment, Elsevier 123:334–338
Kutser T, Kallio K, Eloheimo K, Hannonen T, Pyhälahti T, Koponen S, and Pulliainen J (1999) Quantitative monitoring of water properties with the airborne imaging spectrometer AISA. Proceedings of the Estonian Academy of Sciences: Biology, Ecology 48(1):25–36
LAILIA NL, Arafah F, Jaelani A, and PAMUNGKAS AD (2015) Development of water quality parameter retrieval algorithms for estimating total suspended solids and chlorophyll-A concentration using Landsat-8 imagery at Poteran island water. Remote Sensing and Spatial Information Sciences 2(2)
Lin J-L, Karangan A, Huang YM, and Kang S-F (2022) Eutrophication factor analysis using Carlson trophic state index (CTSI) towards non-algal impact reservoirs in Taiwan. Sustainable Environment Research, Springer 32(1):1–12
Lins RC, Martinez J-M, Motta Marques D Da, Cirilo JA and Fragoso CR (2017) Assessment of chlorophyll-a remote sensing algorithms in a productive tropical estuarine-lagoon system. Remote Sensing 9:516
Morel A and Prieur L (1977) Analysis of variations in ocean color 1. Limnology and Oceanography, Wiley Online Library 22(4):709–722
Ouma YO, Noor K, and Herbert K (2020) Modelling reservoir chlorophyll-a, TSS, and turbidity using Sentinel-2A MSI and Landsat-8 OLI satellite sensors with empirical multivariate regression. Journal of Sensors, Hindawi (شماره ولووم، ایشو و صفحا ندارد؟)
Parsinejad M, Rosenberg DE, Govarchin Ghale YA, Khazaei B, Null S, Raja O, Safaie A, Sima S, Sorooshian A, and Wurtsbaugh WA (2021) 40-Years of Lake Urmia restoration research: Synthesis and Next Steps. Science of the Total Environment, Elsevier (832), 1 August 2022, 155055
Prasad S, Saluja R, and Garg JK (2020) Assessing the efficacy of Landsat-8 OLI imagery derived models for remotely estimating chlorophyll-a concentration in the Upper Ganga River, India. International Journal of Remote Sensing, Taylor & Francis 41(7):2439–2456
Ramaswamy S, Rastogi R, and Shim K (2000) Efficient algorithms for mining outliers from large data sets. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, 427–438
Saberioon M, Brom J, Nedbal V, Souc̆ek P, and Císar̆ P (2020) Chlorophyll-a and total suspended solids retrieval and mapping using Sentinel-2A and machine learning for inland waters. Ecological Indicators, Elsevier 113:106236
Safavi S, Saghafian B, and Hosseini SA (2020) Characterizing flow pattern and salinity using the 3D MIKE 3 model: Urmia Lake case study. Arabian Journal of Geosciences, Springer 13(3):1–12
Sharma MP, Kumar A, and Rajvanshi S (2010) Assessment of trophic state of lakes: A case of Mansi Ganga Lake in India. Hydro Nepal: Journal of Water, Energy and Environment 6:65–72
Sima S, Rosenberg DE, Wurtsbaugh WA, Null SE and Kettenring KM (2021) Managing Lake Urmia, Iran for diverse restoration objectives: Moving beyond a uniform target lake level. Journal of Hydrology: Regional Studies, Elsevier 35:100812
Smith VH and Schindler DW (2009) Eutrophication science: Where do we go from here? Trends in Ecology & Evolution, Elsevier 24(4):201–207
Strömbeck N, Candiani G, Giardino C, and Zilioli E (2003) Water quality monitoring of Lake Garda using multi-temporal MERIS data. Proceedings of MERIS User Workshop
Sudheer KP, Chaubey I, and Garg V (2006) Lake water quality assessment from landsat thematic mapper data using neural network: an approach to optimal band combination selection1. JAWRA, Journal of the American Water Resources Association, Wiley Online Library 42(6):1683–1695
Sváb E, Tyler AN, Preston T, Présing M, and Balogh K V (2005) Characterizing the spectral reflectance of algae in lake waters with high suspended sediment concentrations. International Journal of Remote Sensing, Taylor & Francis 26(5):919–928
 
Swanson ER (1998) Trophic state index revisited. LakeLine 18(4):18–20
Tarh-e-Noandishan (2020) Hydrodynamic investigation of adding extra openings along the causeway of Lake Urmia. Tarh-e-Noandishan Consulting Company, Tehran, Iran (In Persian)
Toming K, Kutser T, Laas A, Sepp M, Paavel B, and Nõges T (2016) First experiences in mapping lake water quality parameters with Sentinel-2 MSI imagery. Remote Sensing 8:640
Torbick N, Hu F, Zhang J, Qi J, Zhang H, and Becker B (2008) Mapping chlorophyll-a concentrations in West Lake, China using Landsat 7 ETM+. Journal of Great Lakes Research, Elsevier 34(3):559–565
Vanhellemont Q and Ruddick K (2014) Turbid wakes associated with offshore wind turbines observed with Landsat 8. Remote Sensing of Environment, Elsevier 145:105–115
Wang F, Han L, Kung H and Van Arsdale RB (2006) Applications of Landsat‐5 TM imagery in assessing and mapping water quality in Reelfoot Lake, Tennessee. International Journal of Remote Sensing, Taylor & Francis 27(23):5269–5283
Watanabe F, Alcantara E, Rodrigues T, Rotta L, Bernardo N, and Imai N (2017) Remote sensing of the chlorophyll-a based on OLI/Landsat-8 and MSI/Sentinel-2A (Barra Bonita reservoir, Brazil). Anais da Academia Brasileira de Ciências. SciELO Brasil 90:1987–2000
Watanabe FS, Alcântara E, Rodrigues TW, Imai NN, Barbosa CC, and Rotta LH (2015) Estimation of chlorophyll-a concentration and the trophic state of the Barra Bonita Hydroelectric Reservoir using OLI/Landsat-8 Images. International Journal of Environmental Research and Public Health 12:10391-10417
Wong T-T (2015) Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, Elsevier 48(9):2839–2846
Wu M, Zhang W, Wang X, and Luo D (2009) Application of MODIS satellite data in monitoring water quality parameters of Chaohu Lake in China. Environmental monitoring and assessment, Springer 148(1):255–264
Yadav S, Yamashiki Y, Susaki J, Yamashita Y, and Ishikawa K (2019) Chlorophyll estimation of lake water and coastal water using Landsat-8 and Sentinel-2a Satellite. International Archives of the Photogrammetry, Remote Sensing, & Spatial Information Sciences
Zeinoddini M, Tofighi MA, and Vafaee F (2009) Evaluation of dike-type causeway impacts on the flow and salinity regimes in Urmia Lake, Iran. Journal of Great Lakes Research, Elsevier 35(1):13–22
Zhang T, Huang M, and Wang Z (2020) Estimation of chlorophyll-a Concentration of lakes based on SVM algorithm and Landsat 8 OLI images. Environmental Science and Pollution Research, Springer 27(13):14977–14990