ارزیابی کیفیت محیط زیستی با استفاده از ابزار سنجش از دور و شبکه های عصبی مصنوعی (مطالعه موردی: تبریز- رشت)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استاد/ گروه مهندسی آب، دانشکده مهندسی عمران، دانشگاه تبریز، تبریز.

2 دانش آموخته کارشناسی ارشد مهندسی منابع آب/گروه مهندسی آب، دانشکده عمران، دانشگاه تبریز، تبریز.

3 استادیار / گروه مهندسی آب، دانشکده مهندسی عمران، دانشگاه تبریز، تبریز.

چکیده

در مقاله حاضر، جهت ارزیابی کیفیت زیست‌محیطی برای 500 پیکسل در اطراف تبریز در استان آذربایجان‌شرقی و همچنین 500 پیکسل در اطراف رشت در استان گیلان در ایران که از لحاظ اقلیم با یکدیگر متفاوت می‌باشند، با استفاده از محاسبات‌نرم و سنجش از دور، اندیس زیست‌محیطی EBV(Eco-environment Background Value) ، جهت تعیین کیفیت زیست‌محیطی مناطق، مورد بررسی قرار‌گرفته‌است. برای مدل‌سازی، از شاخص‌های پوشش‌گیاهی، رطوبت‌خاک، درخشندگی، دمای‌سطح‌زمین و داده‌های رقومی ارتفاعی که با استفاده از ابزار ‌سنجش از دور تهیه شد و همچنین از داده‌های مربوط به بارش و دما به عنوان ورودی‌ به مدل شبکه عصبی مصنوعی back propagation سه لایه، بهره‌گیری شده‌است. میانگین داده‌های مربوط به 8‌سال گذشته برای شاخص‌های مذکور، یک‌بار به صورت فصلی برای چهار فصل و بار دیگر به‌صورت سالانه برای مناطق مورد بررسی در اطراف تبریز و رشت وارد شبکه شدند. نتیجه حاصل، نشان‌گر عملکرد بهتر شبکه برای منطقه تبریز در فصل بهار با RMSE=0.0219 و R=0.9961 می‌باشد. به نظر می‌رسد دلیل عملکرد بهتر شبکه برای تبریز در مقایسه با رشت را می‌توان ضعف ابزار سنجش از دور در بررسی مکان‌هایی همچون گیلان دانست که پوشش گیاهی متراکم و رطوبت جوی بالایی دارند. به‌نظر می‌رسد تراکم پوشش-گیاهی و رطوبت بالا مانع از بازتاب مناسب و بدون انحراف از سطح زمین می‌شود و در دریافت داده‌های مورد نیاز، اخلال ایجاد می‌کند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Eco-environmental Quality Evaluation Using Remote Sensing and Artificial Neural Network (Case Study: Tabriz-Rasht)

نویسندگان [English]

  • Vahid Nourani 1
  • Ehsan Foroumandi 2
  • Elnaz Sharghi 3
1 Prof., Department of Water Resources Eng., Faculty of Civil Engineering, University of Tabriz, Iran.
2 M.Sc. Graduate, Department of Water Resources Eng., Faculty of Civil Engineering, University of Tabriz, Iran.
3 Assistant Prof., Department of Water Resources Eng., Faculty of Civil Engineering, University of Tabriz, Iran.
چکیده [English]

In this study, to evaluate the eco-environment value of 500 pixels around the city of Tabriz in the East Azarbaijan Province, Iran, as well as 500 pixels around the city of Rasht in Gilan Province, Iran, which have different climates, the Eco-environment Background Value index (EBV) has been investigated using soft computations and remote sensing tools to determine the eco-environment value of the areas. For modeling, indicators including vegetation index, soil wetness index, Land Surface Temperature (LST), and Digital Elevation Model (DEM) data collected using remote sensing tools as well as data on precipitation and temperature obtained using ground-based weather stations were exploited as input into the three-layer back propagation based artificial neural network (BPANN) model. The average of the data for the past 8 years for these indicators, once seasonally for four seasons and once annually for the regions under study around Tabriz and Rasht, entered the network. The results indicated a better performance of the network for Tabriz region in the spring with root mean square error (RMSE) = 0.0219 and R = 0.9961. It seems that the better network performance for Tabriz compared to Rasht could be due to the weakness of the remote sensing tool in examining areas like Gilan, which has a dense vegetation and high atmospheric humidity. It seems that the high vegetation density and high humidity impede proper reflection without deviation from the land surface and disrupts the reception of the required data.

کلیدواژه‌ها [English]

  • Eco-environment value assessment
  • Remote sensing
  • Meteorological data
  • Artificial neural network
Chang JT, Wetzel PJ (1991) Effects of spatial variations of soil moisture and vegetation on the evolution of     a prestorm environment: A numerical case study. Monthly Weather Review 119(6):1368-1390
 Chavez PS (1996) Image-based atmospheric corrections-revisited and improved. Photogrammetric Engineering and Remote Sensing 62(9):1025-1035
 Elmore AJ, Mustard JF, Manning SJ, Lobell DB (2000) Quantifying vegetation change in semiarid environments: precision and accuracy of spectral mixture analysis and the normalized difference vegetation index. Remote Sensing of Environment 73(1):87-102
 Elshorbagy A, Simonovic SP, Panu US (2000) Performance evaluation of artificial neural networks for runoff prediction. Journal of Hydrologic Engineering 5(4):424-427
 Falorni G, Teles V, Vivoni ER, Bras RL, Amaratunga KS (2005) Analysis and characterization of the vertical accuracy of digital elevation models from the Shuttle Radar Topography Mission. Journal of Geophysical Research, Earth Surface 110(F2):1-20
 Goh ATC (1995) Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering 9(3):143-151
 Hornik K (1991) Approximation capabilities of multilayer feed forward networks. Neural Networks 4(2):251-257
 Hsu KL, Gupta HV, Sorooshian S (1995) Artificial neural network modeling of the rainfall‐runoff process. Water Resources Research 31(10):2517-2530
 Huang B, Wang S, Yang H (2009) City Eco. Environment Quality Assessment Based on GIS and RS. Journal of Tongji University (Natural Science) 6:20-28
 Lappalainen H, Honkela A (2000) Bayesian non-linear independent component analysis by multi-layer perceptrons. Advances in Independent Component Analysis 1:93-121
 Lillesand T, Kiefer RW, Chipman J (2014) Remote sensing and image interpretation. John Wiley & Sons
 Marsalek J, Maksimovic C, Zeman E, Price R (2013) Hydroinformatics tools for planning, design, operation and rehabilitation of sewer systems. Springer Science & Business Media 44
 Moisen GG, Frescino TS (2002) Comparing five modelling techniques for predicting forest characteristics. Ecological modeling 157(2):209-225
 Niu WY, Harris WM (1996) China: The forecast of its environmental situation in the 21st century. Journal of Environmental Management 47(2):101-114
 Noe RA, Hollenbeck JR, Gerhart B, Wright PM (2006) Employee separation and retention. Human Resource Management: Gaining a Competitive Advantage 5:425-456
 Pettorelli N, Vik JO, Mysterud A, Gaillard JM, Tucker CJ, Stenseth NC (2005) Using the satellite-derived NDVI to assess ecological responses to environmental change. Trends in Ecology and Evolution 20(9):503-510
 Rajaee T, Nourani V, Zounemat-Kermani M, Kisi O (2010) River suspended sediment load prediction: application of ANN and wavelet conjunction model. Journal of Hydrologic Engineering 16(8):613-627
 Schalkoff RJ (1997) Artificial neural networks. New York: McGraw-Hill.1
 Shi Z, Li H (2007) Application of artificial neural network approach and remotely sensed imagery for regional eco-environmental quality evaluation. Environmental Monitoring and Assessment 128(3):217-229
 Singh K, Deshpande NV, Sakalley B, Rajak SN, Kelsy J (1991) Satellite remote sensing for surface water assessment and management of Bhopal Lake-An integrated approach. Remote Sensing Applications, Centre MP Council of Science & Technology Bhopal, India
 Sobrino J Coll C, Caselles V (1991) Atmospheric correction for land surface temperature using NOAA-11 AVHRR channels 4 and 5. Remote Sensing of Environment 38(1):19-34
 Stein ML (2012) Interpolation of spatial data: some theory for kriging. Springer Science and Business Media
 Sun Z, Guo H, Li X, Lu L, Du X (2011) Estimating urban impervious surfaces from Landsat-5 TM imagery using multilayer perceptron neural network and support vector machine. Journal of Applied Remote Sensing 5(1):053501
 Tachikawa T, Kaku M, Iwasaki A, Gesch D, Oimoen M, Zhang Z, Abrams M (2011) ASTER global digital elevation model version 2–Summary of validation results August 31, 2011. Pasadena, California: Jet Propulsion Laboratory
 Toole DA, Siegel DA, Menzies DW, Neumann MJ, Smith RC (2000) Remote-sensing reflectance determinations in the coastal ocean environment: impact of instrumental characteristics and environmental variability. Applied Optics 39(3):456-469
 Wang L, Qu JJ, Zhang S, Hao X, Dasgupta S (2007) Soil moisture estimation using MODIS and ground measurements in eastern China. International Journal of Remote Sensing 28(6):1413-1418
 Wang W, Huang D, Wang XG, Liu YR, Zhou F (2010) Estimate soil moisture using trapezoidal relationship between remotely sensed land surface temperature and vegetation index. Hydrology and Earth System Sciences Discussions 7(6):8703-8740
 Ying X, Zeng GM, Chen GQ, Tang L, Wang KL, Huang DY (2007) Combining AHP with GIS in synthetic evaluation of eco-environment quality- A case study of Hunan Province, China. Ecological Modelling 209(2-4):97-109
 Zeng C, Shen H, Zhang L (2013) Recovering missing pixels for Landsat ETM+ SLC-off imagery using multi-temporal regression analysis and a regularization method. Remote Sensing of Environment 131(1):182-194
 Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 509(1):159-175
 Roy DP, Ju J, Kline K, Scaramuzza PL, Kovalskyy V, Hansen M, Zhang C (2010) Web-enabled Landsat Data (WELD): Landsat ETM+ composited mosaics of the conterminous United States. Remote Sensing of Environment 114(1):35-49
 Gazette S (2001) State environmental protection Administration of China. Chinese Environmental Statistical Gazette
 Zhang XL, You XX, Liu XS, Huang HG (2003) A study on forest ecological environment gradient with remote sensing, GIS and expert system. In Proceedings of the 2003 International Conference on Machine Learning and Cybernetics 4:2374-2378