تعیین دامنه تغییرکاربری اراضی استان البرز با استفاده از داده‌های راداری و نوری سنتینل در سامانه گوگل ارث انجین

نوع مقاله : پژوهشی

نویسندگان

1 استادیار پژوهش، موسسه تحقیقات خاک و آب کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

2 محقق، موسسه تحقیقات خاک و آب کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

چکیده

نقشه­های دقیق کاربری اراضی نقش مهمی در تولید اطلاعات  مورد نیاز مدیریت منابع اراضی دارند. در سال‌های اخیر استفاده از داده­های دقیق، فنّاوری و روش­های به‌روز، منجر به تولید اطلاعات ارزشمندی در زمینه استخراج داده­های سنجش‌ازدور در حوزه­های مختلف علوم طبیعی شده است. هدف از این مطالعه بررسی تغییرات کاربری اراضی استان البرز در یک دوره پنج‌ساله  با استفاده تصاویر ماهواره­ای با قدرت تفکیک مکانی  بالا و روش­های نوین است. بدین منظور نقشه کاربری اراضی استان مورد مطالعه برای دو دوره 1397 و 1402 با چهار کلاس کاربری اراضی شامل بایر، اراضی زراعی، آب و عوارض انسان‌ساخت بر روی اراضی از تلفیق تصاویر نوری و راداری سنتینل و استفاده از داده­های کمکی مانند شاخص­های پوشش­گیاهی و مدل رقومی ارتفاع و با استفاده از الگوریتم جنگل تصادفی تهیه شد. بر همین اساس تعداد 57 تصویر سنتینل- 2 و 15 تصویر سنتینل- 1 برای دوره اول و 78 تصویر سنتینل- 2 و 23 تصویر سنتینل- 1 برای دوره دوم در محیط گوگل ارث انجین پردازش شد. صحت کلی و ضریب کاپا برای دوره اول به ترتیب 92/4 درصد و 0/89 و برای دوره دوم 94/5 درصد و 0/9 محاسبه شد. نتایج نشان داد که اراضی زراعی در طی این دوره به میزان 29/38 کیلومترمربع کاهش داشته است و در مقابل اراضی انسان‌ساخت 21/4 کیلومترمربع رشد داشته است. همچنین، اراضی بایر در دوره پنج‌ساله 6/2 کیلومترمربع افزایش داشته است که تغییرات آن مرتبط با دشت­های جنوبی منطقه مورد مطالعه است که قبلاً تحت کشت بوده­اند و در دوره دوم تبدیل به اراضی بایر شده­اند. به­منظور تعیین جهت توسعه اراضی انسان‌ساخت، لایه اراضی شهری سال 1402 بر روی نقشه کاربری اراضی سال 1397 قرار داده شد و به این ترتیب میزان تغییر کاربری هر کدام از کلاس­ها به کاربری انسان‌ساخت مشخص شد. نتایج نشان داد که تقریباً 55 درصد از اراضی انسان‌ساخت در این دوره بر روی اراضی زراعی توسعه پیدا نموده­اند که بیانگر تغییر کاربری 11/74 کیلومترمربعی اراضی زراعی به کاربری انسان‌ساخت است. با توجه به اینکه تغییر کاربری اراضی زراعی یکی از چالش­های مهم در کشور ما است، تهیه چنین نقشه­هایی کمک زیادی به مدیریت به‌منظور حفظ و صیانت از اراضی کشاورزی بویژه در حاشیه کلان‌شهرها می­کند.

کلیدواژه‌ها


عنوان مقاله [English]

Using Sentinel radar and optical data in the Google Earth Engine platform to determine the extent of land use changes in Alborz Province

نویسندگان [English]

  • Rasoul Kharazmi 1
  • Zahra MohammadEsmail 2
  • Mansour Chatrenour 2
1 Assistant Prof., Soil and Water Research Institute, Agricultural Research Education and Extension Organization (AREEO), Tehran, Iran
2 Researcher, Soil and Water Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran
چکیده [English]

Land cover (LC) maps play a key role in generating accurate data for land resource management. The recent developments in accurate data utilization as well as novel technologies and methods have led to the generation of valuable information useful in extracting remote sensing datasets for application in different fields. In this study, use was made of high-resolution satellite images and up-to-date methodologies to assess LC changes over five-year periods in Alborz Province. To achieve this, LC maps of the study area with the four major land classes of barren, cultivated, and built-up lands as well as water bodies were generated for the two time periods of 2009 and 2023 by combining optical and radar Sentinel images as well as such supplemental data as vegetation indices and Digital Elevation Model (DEM) using the random forest (RF) algorithm. For this purpose, 57 sentinel-2 and 15 sentinel-1 images were exploited for the first time period and 78 Sentinel-2 and 23 Sentinel-1 images for the second within the Google Earth Engine (GEE) cloud computing platform. The overall accuracy values obtained for the two periods were 92.4% and 94.5%, respectively, while the corresponding Kappa coefficients were 0.89 and0.9. The results showed a decrease of 29.38 KM2 in cropland and an increase of 21.4 KM2 in Built-Up areas over the past five years. Additionally, barren lands increased by 2.6 KM2 over the five-year period, with these changes primarily associated with the southern plains of the study area, which had changed from cultivated to barren land during the second period. In order to determine the trends in increasing built-up areas, the urban land map of the second period was laid on the land use classification obtained for the first period, whereby the extent of changes in each class was determined. The results showed that approximately 55% of the Built-up development had occurred on croplands, indicating a change of 11.74 KM2 of the cultivated land into Built-pp one. Hence, cropland loss in favor of human built-up land forms a major challenge in IRAN . Obviously, the maps thus prepared might serve as great contributions to land management thereby controlling the growth of human built-up lands, especially in the outskirts of metropolises.

کلیدواژه‌ها [English]

  • Land use Change
  • Remote Sensing
  • Random Forest
  • Satellite Imagery
  • Machine Learning
  1. Abdullah, A.Y.M., Masrur, A., Adnan, M.S.G., Baky, M., Al, A., Hassan, Q.K., Dewan, A. 2019. Spatio-Temporal Patterns of Land Use/Land Cover Change in the Heterogeneous Coastal Region of Bangladesh between 1990 and 2017. Remote Sensing, 11, 790. https://doi.org/10.3390/rs11070790
  2. Abera, T.A., Vuorinne, I., Munyao, M., Pellikka, P.K. and Heiskanen, J., 2022. Land cover map for multifunctional landscapes of Taita Taveta County, Kenya, based on Sentinel-1 radar, Sentinel-2 optical, and topoclimatic data. Data, 7(3): 36. 

https://doi.org/10.3390/data7030036

  1. Ahangarha, M, Saadat Seresht, M, Shahhoseini, R, Seyyedi, S.T., 2020. Crop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images. Journal of Geomatics Science and Technology, 10 (2): 79-89 (In Persian)
  2. Amani, M., Ghorbanian, A., Ahmadi, S.A., Kakooei, M., Moghimi, A., Mirmazloumi, S.M., Moghaddam, S.H.A., Mahdavi, S., Ghahremanloo, M., Parsian, S. and Wu, Q., 2020. Google earth engine cloud computing platform for remote sensing big data applications: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 5326-5350. https://doi.org/10.1109/JSTARS.2020.3021052
  3. Amani, M., Salehi, B., Mahdavi, S., Brisco, B., 2018. Spectral analysis of wetlands using multi-source optical satellite imagery. ISPRS J. Photogramm. Remote Sens. 144: 19-36. https://doi.org/10.1016/j.isprsjprs.2018.07.005 Awad, M.M., Alawar, B. and Jbeily, R., 2019. A new crop spectral signatures database interactive tool (CSSIT). Data, 4(2): 77. https://doi.org/10.3390/data4020077
  4. Deiss, L., Margenot, A.J., Culman, S.W. and Demyan, M.S., 2020. Tuning support vector machines regression models improves prediction accuracy of soil properties in MIR spectroscopy. Geoderma, 365: 114227. https://doi.org/10.1016/j.geoderma.2020.114227
  5. GaoC., 1996. NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space. Remote sensing of environment. 58(3):257-66.

https://doi.org/10.1016/S00344257 (96)00067-3

  1. Ghayour, L.; Neshat, A.; Paryani, S.; Shahabi, H.; Shirzadi, A.; Chen,W.; Al-Ansari, N.; Geertsema, M.; Pourmehdi Amiri, M.; Gholamnia, M., 2021. Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms. Remote Sens, 13, 1349.

 https://doi.org/10.3390/rs13071349

  1. Ghorbanian, A., Kakooei, M., Amani, M., Mahdavi, S., Mohammadzadeh, A. and Hasanlou, M., 2020. Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples. ISPRS Journal of Photogrammetry and Remote Sensing, 167: 276-288. https://doi.org/10.1016/j.isprsjprs.2020.07.013
  2. Gurung, R.B., Breidt, F.J., Dutin, A. and Ogle, S.M., 2009. Predicting Enhanced Vegetation Index (EVI) curves for ecosystem modeling applications. Remote Sensing of Environment, 113(10): 2186-2193. https://doi.org/10.1016/j.rse.2009.05.015
  3. Holtgrave, A.K., Röder, N., Ackermann, A., Erasmi, S. and Kleinschmit, B., 2020. Comparing Sentinel-1 and-2 data and indices for agricultural land use monitoring. Remote Sensing, 12(18): 2919. https://doi.org/10.3390/rs12182919
  4. Hu B, Xu Y, Huang X, Cheng Q, Ding Q, Bai L, Li Y., 2021. Improving urban land cover classification with combined use of sentinel-2 and sentinel-1 imagery. ISPRS International Journal of Geo-Information, 10(8):533. https://doi.org/10.3390/ijgi10080533
  5. Huang, S., Tang, L., Hupy, J.P., Wang, Y. and Shao, G., 2021. A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forestry Research, 32(1): 1-6.

https://doi.org/10.1007/s11676-020-01155-1

  1. Immitzer, M., Vuolo, F., Atzberger, C., 2016. First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Remote Sens, 8: 166. https://doi.org/10.3390/rs8030166
  2. Kasaei zadegan, A.S., 2014. Drought analysis of Alborz province with SPI method, 1th international conference of Geographic science, Abadeh (In Persian).
  3. Kharazmi, R., Panidi, E.A. and Karkon, V.M., 2016. Assessment of dry land ecosystem dynamics based on time series of satellite images. Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 13(5): 214-223 (In Russian).
  4. Kharazmi, R., Tavili, A., Rahdari, M.R., Chaban, L., Panidi, E. and Rodrigo-Comino, J., 2018. Monitoring and assessment of seasonal land cover changes using remote sensing: A 30-year (1987–2016) case study of Hamoun Wetland, Iran. Environmental monitoring and assessment, 190: 1-23. https://doi.org/10.1007/s10661-018-6726-z
  5. Koskinen, J., Leinonen, U., Vollrath, A., Ortmann, A., Lindquist, E., d'Annunzio, R., Pekkarinen, A., Käyhkö, N., 2019. Participatory mapping of forest plantations with Open Foris and Google Earth Engine. ISPRS Journal of Photogrammetry and Remote Sensing, 148:63-74. https://doi.org/10.1016/j.isprsjprs.2018.12.011
  6. Laban, N., Abdellatif, B., Ebeid, H.M., Shedeed, H.A. and Tolba, M.F., 2019. Machine learning for enhancement land cover and crop types classification. Machine learning paradigms: theory and application, 71-87. https://doi.org/10.1007/978-3-030-02357-7_4
  7. Madasa, A., Orimoloye, I.R. and Ololade, O.O., 2021. Application of geospatial indices for mapping land cover/use change detection in a mining area. Journal of African Earth Sciences, 175: 104108. https://doi.org/10.1016/j.jafrearsci.2021.104108
  8. Mohammad esmaeil,Z., 2010. Monitoring land use\ land cover changes in karaj by applying remote sensing. Iranian journal of soil research (formerly soil and water sciences), 24(1): 81-88 (In Persian).
  9. Mullissa, A., Vollrath, A., Odongo-Braun, C., Slagter, B., Balling, J., Gou, Y., Gorelick, N. and Reiche, J., 2021. Sentinel-1 SAR backscatter analysis ready data preparation in google earth engine. Remote Sensing, 13(10): 1954. https://doi.org/10.3390/rs13101954
  10. Nasiri, V., Deljouei, A., Moradi, F., Sadeghi, S.M.M. and Borz, S.A., 2022. Land use and land cover mapping using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A comparison of two composition methods. Remote Sensing, 14(9): 1977. https://doi.org/10.3390/rs14091977
  11. Navidi, M.N., Asadi Rahmani, H., Chatrenour, M., Kharazmi, R., Jamshidi, M., Ziaee Javid, A., MohamadEsmaeil, Z., ebrahimi meymand, F, 2023. Changes in Agricultural Land Use as a Threat to Food Security, Land Management Journal, 11(2): 229-248 (In Persian).
  12. Piao, Y.; Jeong, S.; Park, S.; Lee, D., 2021. Analysis of Land Use and Land Cover Change Using Time-Series Data and Random Forest in North Korea. Remote Sensing, 13, 3501. https://doi.org/10.3390/rs13173501
  13. Polykretis, C., Grillakis, M.G., Alexakis, D.D., 2020. Exploring the impact of various spectral indices on land cover change detection using change vector analysis: A case study of Crete Island, Greece. Remote Sensing, 12(2): 319. https://doi.org/10.3390/rs12020319
  14. Rufin, P., Frantz, D., Ernst, S., Rabe, A., Griffiths, P., Özdo˘gan, M., Hostert, P., 2019. Mapping Cropping Practices on a National Scale Using Intra-Annual Landsat Time Series Binning. Remote Sensing, 11, 232. https://doi.org/10.3390/rs11030232
  15. Sang, X., Guo, Q., Wu, X., Xie, T., He, C., Zang, J., Qiao, Y., Wu, H. and Li, Y., 2021. The effect of DEM on the land use/cover classification accuracy of landsat OLI images. Journal of the Indian Society of Remote Sensing, 49: 1507-1518.

https://doi.org/10.1007/s12524-021-01318-5

  1. Schulz, D., Yin, H., Tischbein, B., Verleysdonk, S., Adamou, R. and Kumar, N., 2021. Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel. ISPRS Journal of Photogrammetry and Remote Sensing, 178, pp.97-111. https://doi.org/10.1016/j.isprsjprs.2021.06.005
  2. Shafizadeh-Moghadam, H., Minaei, F., Talebi-khiyavi, H., Xu, T. and Homaee, M., 2022. Synergetic use of multi-temporal Sentinel-1, Sentinel-2, NDVI, and topographic factors for estimating soil organic carbon. Catena, 212: 106077.

https://doi.org/10.1016/j.catena.2022.106077

  1. Shojaeeian, A., Mokhtari Chelche, S., Keshtkar, L., Soleymani rad, E., 2015. Comparing the Performance of Parametric and NonparametricMethods in Land Cover Classification using Landsat-8 Satellite Images (Case study: A part of Dezful city), Scientific- Research Quarterly of Geographical Data (SEPEHR), 24(93): 53-64 (In Persian).
  2. Solórzano, J.V., Mas, J.F., Gao, Y. and Gallardo-Cruz, J.A., 2021. Land use land cover classification with U-net: Advantages of combining sentinel-1 and sentinel-2 imagery. Remote Sensing, 13(18): 3600. https://doi.org/10.3390/rs13183600
  3. Teluguntla, P., Thenkabail, P.S., Oliphant, A., Xiong, J., Gumma, M.K., Congalton, R.G., Yadav, K., Huete, A., 2018. A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform. ISPRS J. Photogramm. Remote Sens. 144: 325–340.

https://doi.org/10.1016/j.isprsjprs.2018.07.017

  1. Thanh Noi, P., Kappas, M., 2017. Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for and Cover Classification Using Sentinel-2 Imagery. Sensors, 18, 18. https://doi.org/10.3390/s18010018
  2. Valero-Carreras, D., Aparicio, J. and Guerrero, N.M., 2021. Support vector frontiers: A new approach for estimating production functions through support vector machines. Omega, 104: 102490. https://doi.org/10.1016/j.omega.2021.102490
  3. Yang, J., Xu, J., Lv, Y., Zhou, C., Zhu, Y. and Cheng, W., 2023. Deep learning-based automated terrain classification using high-resolution DEM data. International Journal of Applied Earth Observation and Geoinformation, 118: 103249.

 https://doi.org/10.1016/j.jag.2023.103249

  1. Zha, Y., Gao, J. and Ni, S., 2003. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International journal of remote sensing, 24(3): 583-594. https://doi.org/10.1080/01431160304987