کاهش ابعاد داده‌های سنجش از دوری به منظور برآورد کربن آلی خاک

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه ژئودزی مهندسی نقشه برداری، دانشگاه تفرش، تفرش، ایران

چکیده

توزیع مواد آلی در خاک، بر فعالیت بیولوژیکی، در دسترس بودن مواد مغذی، ساختمان خاک و خاکدانه‌ها و ظرفیت نگهداری آب و بر مدیریت خاک بسیار موثر است. در این پژوهش به بررسی ارتباط بازتاب طیفی خاک با استفاده از داده‌های ماهواره لندست 8 و همچنین داده‌های ارتفاعی SRTM و کربن آلی خاک پرداخته شده است. در روش پیشنهادی، انعکاس طیفی باندهای ماهواره لندست 8 در کنارشاخص‌‌های گیاهی  و ویژگی‌‌های توپوگرافی با هدف تعیین شاخص‌‌های موثر بر کربن آلی خاک، مورد بررسی قرار گرفته است. برای این منظور ، از شبکه عصبی جهت ارتباط بین داده‌های سنجش از دوری و کربن آلی خاک استفاده شده است. جهت پیاده‌سازی روش پیشنهادی از 100 نمونه خاک در استان آذربایجان شرقی استفاده شده است. مقادیر شاخص های آماریRMSE ، R2 و RRMSE به ترتیب 0/404، 0/254 و 46/597 بدست آمده و روش شبکه عصبی در مقایسه با روش‌‌های رگرسیون خطی و رگرسیون بردار پشتیبان خطی به دقت بالاتری دست یافت. در ادامه الگوریتم ژنتیک جهت کاهش ابعاد وتعیین شاخص های بهینه، افزایش دقت و کاهش پیچیدگی محاسبات پیشنهاد شد. این الگوریتم با حذف شاخص های اضافی، منجر به افزایش دقت مدل سازی کربن آلی خاک می شود. در این مرحله مقادیر شاخص های آماری RMSE ، R2 و RRMSE با مقادیر 0/279، 0/718 و 27/116 بهبود یافت. همچنین به منظور بررسی کارایی الگوریتم ژنتیک، الگوریتم آنالیز مولفه‌‌های اصلی نیز بر روی داده‌ها پیاده سازی شد و نتایج مقایسه نشان داد که الگوریتم ژنتیک در کاهش ابعاد همراه با افزایش دقت موفق بوده است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Dimension reduction of the remote sensing data to estimate soil organic carbon

نویسندگان [English]

  • Niusha Mozafari
  • Hadiseh Sadat Hasani
  • Marzieh Jafari
Department of Geodesy and Surveying Engineering, Tafresh University, Tafresh, Iran
چکیده [English]

Soil is a very complex phenomenon that includes organic materials, minerals, water, and air. The distribution of organic matter in the soil has a profound effect on biological activity, nutrient availability, soil and soil seed structure, and water holding capacity, and soil management in general. In this research, the relation between soil spectral reflectance using the Landsat 8 satellite data as well as the SRTM Elevation data and soil organic carbon has been investigated. In the proposed method, spectral reflection of data in the main bands of the Landsat 8 satellite is investigated and processed. In addition to the main bands, vegetation and lighting indices, and topographic features have been studied. In this study, a method for selecting effective indexes in increasing the accuracy of soil organic carbon modeling is presented. For this purpose, in the first step of modeling, Linear regression, Support Vector Machine regression, and Neural Network methods have been used for the connection between remote sensing data and soil organic carbon. To implement the proposed method, 100 soil samples in East Azerbaijan province have been used. According to RMSE and R2 statistical indices, which are the basis for evaluating the models, the neural network model was selected as the final model, and with the values of RMSE = 0.404, R2= 0.254, and RRMSE=46.597 is more accurate than the regression method. Due to the importance of dimensionality to increase accuracy and reduce the complexity of calculations, a genetic algorithm was proposed in this study. This efficient algorithm increases the accuracy of soil organic carbon modeling and eliminates additional indicators. After applying the genetic algorithm (GA) to the neural network model, we were able to achieve better accuracy, and the values of the baseline statistical indices were changed to RMSE = 0.279, R2 = 0.718, and RRMSE=27.116. Also, to check the efficiency of the genetic algorithm, the PCA algorithm was also implemented on the data and the comparison results showed that the genetic algorithm was successful in reducing dimensions along with increasing accuracy.

کلیدواژه‌ها [English]

  • Remote Sensing
  • Soil Organic Carbon
  • Neural Network
  • Dimension Reduction
  • Genetic Algorithm

مراجع

[1] S. Ellis, T. Mellor, Soils and environment, Routledge, 2002.
[2] R. Lal, Challenges and opportunities in soil organic matter research, European Journal of Soil Science, 60(2) (2009) 158-169.
[3] F. Chen, D.E. Kissel, L.T. West, W. Adkins, Field‐scale mapping of surface soil organic carbon using remotely sensed imagery, Soil Science Society of America Journal, 64(2) (2000) 746-753.
[4] M. Ladoni, H.A. Bahrami, S.K. Alavipanah, A.A. Norouzi, Estimating soil organic carbon from soil reflectance: a review, Precision Agriculture, 11 (2010) 82-99.
[5] X. He, L. Yang, A. Li, L. Zhang, F. Shen, Y. Cai, C. Zhou, Soil organic carbon prediction using phenological parameters and remote sensing variables generated from Sentinel-2 images, Catena, 205 (2021) 105442.
[6] G.S. Bhunia, P. Kumar Shit, H.R. Pourghasemi, Soil organic carbon mapping using remote sensing techniques and multivariate regression model, Geocarto International, 34(2) (2019) 215-226.
[7] H. Jenny, Factors of soil formation: a system of quantitative pedology, Courier Corporation, 1994.
[8] H. Emami, Investigation the effects of aspect and degree of slope on soil quality in the South East of Mashhad, Journal of Water and Soil Conservation, 23(2) (2016) 301-310, (in Persian).
[9] J. Kumhálová, F. Kumhála, M. Kroulík, Š. Matějková, The impact of topography on soil properties and yield and the effects of weather conditions, Precision Agriculture, 12 (2011) 813-830.
[10] S. Singh, Understanding the role of slope aspect in shaping the vegetation attributes and soil properties in Montane ecosystems, Tropical Ecology, 59(3) (2018) 417-430.
[11] S. Jakšić, J. Ninkov, S. Milić, J. Vasin, M. Živanov, D. Jakšić, V. Komlen, Influence of slope gradient and aspect on soil organic carbon content in the region of Niš, Serbia, Sustainability, 13(15) (2021) 8332.
[12] P.H. Walker, Contributions to the understanding of soil and landscape relationships, Soil Research, 27(4) (1989) 589-605.
[13] R.C. Dalal, R.J. Henry, Simultaneous determination of moisture, organic carbon, and total nitrogen by near infrared reflectance spectrophotometry, Soil Science Society of America Journal, 50(1) (1986) 120-123.
[14] F. Pierson, D. Mulla, Aggregate stability in the Palouse region of Washington: effect of landscape position, Soil Science Society of America Journal, 54(5) (1990) 1407-1412.
[15] W. Cheng, R. Virginia, S.F. Oberbauer, C.T. Gillespie, J.F. Reynolds, J. Tenhunen, Soil nitrogen, microbial biomass, and respiration along an arctic toposequence, Soil Science Society of America Journal, 62(3) (1998) 654-662.
[16] C.f. Garten, W.M. Post, P.J. Hanson, L.W. Cooper, Forest soil carbon inventories and dynamics along an elevation gradient in the southern Appalachian Mountains, Biogeochemistry, 45 (1999) 115-145.
[17] M. Cox, P.D. Gerard, M. Wardlaw, M. Abshire, Variability of selected soil properties and their relationships with soybean yield, Soil Science Society of America Journal, 67(4) (2003) 1296-1302.
[18] K.J. Forsberg, A. Reyes, B. Wang, E.M. Selleck, M.O. Sommer, G. Dantas, The shared antibiotic resistome of soil bacteria and human pathogens, science, 337(6098) (2012) 1107-1111.
[19] H. Khademi, H. Khayyer, Landscape-scale Variability of Selected Surface Soil Quality Attributes in a Rangeland in Semirom Area, Isfahan University of Technology-Journal of Crop Production and Processing, 8(2) (2004) 59-74, (in Persian).
[20] H. Ghayoumi Mohammadi, M. Ramesht, N. Toumanian, M. Moayeri, Space and spatial view in soil and geomorphology studies, Geography and Environmental Planning, 35(3) (2009) 1-20 (in Persian).
[21] M.-J. Ebrahimi, H. Bashari, M. Bassiri, M. Borhani, A. Mohajeri, Evaluating vegetation and soil physico-chemical characteristics changes along a grazing gradient using non-metric multi-dimensional scaling analysis (Case study: Morchehkhort rangelands-Isfahan), Rangeland, 11(1) (2017) 106-115, (in Persian).
[22] H. Aïchi, Y. Fouad, C. Walter, R.V. Rossel, Z.L. Chabaane, M. Sanaa, Regional predictions of soil organic carbon content from spectral reflectance measurements, Biosystems engineering, 104(3) (2009) 442-446.
[23] H. Bartholomeus, M.E. Schaepman, L. Kooistra, A. Stevens, W. Hoogmoed, O. Spaargaren, Spectral reflectance based indices for soil organic carbon quantification, Geoderma, 145(1-2) (2008) 28-36.
[24] O.L. Montgomery, AN INVESTIGATION OF THE RELATIONSHIP BETWEEN SPECTRAL REFLECTANCE AND THE CHEMICAL, PHYSICAL AND GENETIC CHARACTERISTICS OF SOILS, Purdue University, 1976.
[25] M.F. Baumgardner, L.F. Silva, L.L. Biehl, E.R. Stoner, Reflectance properties of soils, Advances in agronomy, 38 (1986) 1-44.
[26] S.G. Bajwa, L. Tian, D. Bullock, K. Sudduth, N. Kitchen, H. Palm, Soil characterization in agricultural fields using hyperspectral image data, in:  2001 ASAE Annual Meeting, American Society of Agricultural and Biological Engineers, 1998, pp. 1.
[27] R. Saxena, K. Vermal, R. Srivastava, A. Av, A. Shiwalkar, S. Londhel, Spectral reflectance properties of some dominant soils occurring on different altitudinal zones in Uttaranchal Himalayas, Agropedology, 13(2) (2003) 35-43.
[28] D.G. Sullivan, J. Shaw, D. Rickman, IKONOS imagery to estimate surface soil property variability in two Alabama physiographies, Soil Science Society of America Journal, 69(6) (2005) 1789-1798.
[29] G. Debaene, J. Niedzwiecki, A. Pecio, Visible and near-infrared spectrophotometer for soil analysis: preliminary results, Polish Journal of Agronomy, (03) (2010).
[30] D. Žížala, R. Minařík, T. Zádorová, Soil organic carbon mapping using multispectral remote sensing data: Prediction ability of data with different spatial and spectral resolutions, Remote Sensing, 11(24) (2019) 2947.
[31] T. Angelopoulou, N. Tziolas, A. Balafoutis, G. Zalidis, D. Bochtis, Remote sensing techniques for soil organic carbon estimation: A review, Remote Sensing, 11(6) (2019) 676.
[32] N. Pouladi, A. Gholizadeh, V. Khosravi, L. Borůvka, Digital mapping of soil organic carbon using remote sensing data: A systematic review, Catena, 232 (2023) 107409.
[33] X. Zhang, Q. Sun, J. Li, Optimal band selection for high dimensional remote sensing data using genetic algorithm, in:  Second International Conference on Earth Observation for Global Changes, SPIE, 2009, pp. 522-528.
[34] F. Samadzadegan, H.S. Hasani, Determination of Optimum SVMs Based on Genetic Algorithm in Classification of Hyperspectral Imagery, Journal of Information and Communication Technology, 4(13) (2019) 9-23, (in Persian).
[35] S. Ranjbar, M. Akhoondzadeh, Volumetric soil moisture estimation using Sentinel 1 and 2 satellite images, Journal of Geospatial Information Technology, 7(4) (2020) 215-232, (in Persian).
[36] S.A. Mohamed, M.M. Metwaly, M.R. Metwalli, M.A. AbdelRahman, N. Badreldin, Integrating Active and Passive Remote Sensing Data for Mapping Soil Salinity Using Machine Learning and Feature Selection Approaches in Arid Regions, Remote Sensing, 15(7) (2023) 1751.
[37] J. Yuan, Z. Niu, Evaluation of atmospheric correction using FLAASH, in:  2008 International Workshop on Earth Observation and Remote Sensing Applications, IEEE, 2008, pp. 1-6.
[38] T.R. Loveland, J.R. Irons, Landsat 8: The plans, the reality, and the legacy, Remote Sensing of Environment, 185 (2016 ) 1-6.
نشریه مهندسی عمران امیرکبیر
دوره 56، شماره 5
1403
صفحه 589-606

فایل ها

هم رسانی

ارجاع به این مقاله

آمار