Geography and Human Relationships

Geography and Human Relationships

Improving Classification accuracy by combining multi-season images of Sentinel 1 and 2 in order to prepare a land use map in the cloud space of Google Earth Engine (Case study: Guilan province)

Document Type : Original Article

Authors
saeed rasti 1
mostafa mahdavifardnh 2
hadayat shaykh ghaderi 3
abuzar nasiri 4
nazanin zahra taktaz 5
1 Remote sensing and GIS, Faculty of Geography, University of Tehran, Iran
2 Gis university of planning and environmental sciences university of tabriz iran
3 remote sensing of geographi information system of kharazmi univercity of tehran iran
4 Geographi information system and remote sensing of firuozabad higher education center
5 remote sensing and gis faculty of rudaki.university of hormozgan of hormozgan iran
10.22034/gahr.2022.336692.1696
Abstract
Up-to-date and accurate land use maps have played an important role in the management and planning of developing countries. The purpose of this study, in addition to preparing an accurate map of land use in Gilan province, is to compare and evaluate the maps generated using multi-season radar and optical data and also to combination these data together to improve the classification map. In this regard, data with spatial resolution of 10 meters Sentinel 2 optics and VH radar polarization of Sentinel 1 in band C were processed and analyzed to produce land Use map in the new Google Earth Engine processing environment. Processing results showed that the use of Sentinel 1 and Sentinel 2 radar data alone has kappa coefficients of 0.72 and 0.84% and overall accuracy of 78.51 and 87.41%, respectively. While the simultaneous use of Sentinel 1 and Sentinel 2 data with the approach of combining data in the Google Earth engine environment achieved very good results. The map was prepared using a simultaneous multi-season combination of Sentinil 1 and 2 with kappa coefficient and overall accuracy of 0.97 and 97.77%, respectively. In this study, Bayer user pixels in Sentinel 1 images due to similarity of redistribution and in Sentinel 2 images due to spectral similarity, caused improper performance of the support vector machine classification algorithm in separating the Bayer class and the city. In general, the results of this study indicate that the simultaneous combination of Sentinel 1 and 2 data to improve the accuracy of classification algorithms for mapping can work very well and separate land classes with high ability.
Keywords
Land Use،" Google Earth Engine،" Sentinel 1،" Sentinel 2
Data Combination
  • Asner, G.P., 2001. Cloud cover in landsat observations of the Brazilian amazon. Int. J. Remote Sens. 22 (18), 3855–3862.
  • Baghdadi, N., El Hajj, M., Zribi, M., & Bousbih, S. (2017). Calibration of the water cloud model at C-band for winter crop fields and grasslands. Remote Sensing, 9(9), 969.
  • Borges, J., Higginbottom, T. P., Symeonakis, E., & Jones, M. (2020). Sentinel-1 and Sentinel-2 Data for Savannah Land Cover Mapping: Optimising the Combination of Sensors and Seasons. Remote Sensing, 12(23), 3862.
  • Carrasco, L., O’Neil, A. W., Morton, R. D., & Rowland, C. S. (2019). Evaluating combinations of temporally aggregated Sentinel-1, Sentinel-2 and Landsat 8 for land cover mapping with Google Earth Engine. Remote Sensing, 11(3), 288.
  • data of Sentinel 2-1 satellite (radar and optics) using Google Earth Engine system to map the area of ​​rice cultivation (Case study: Joybar city), the first international conference and the second national conference on new technologies and applications of geomatics, Tabriz (in Persian).
  • Dong, D., Wang, C., Yan, J., He, Q., Zeng, J., & Wei, Z. (2020). Combing Sentinel-1 and Sentinel-2 image time series for invasive Spartina alterniflora mapping on Google Earth Engine: a case study in Zhangjiang Estuary. Journal of Applied Remote Sensing, 14(4), 044504.
  • Fundamentals of Applied Remote Sensing, by the Canadian Remote Sensing Center (2005). Translated by Valizadeh Kamran, Khalil and Mahdavifard, Mustafa. (1398). First Edition, Satellite Publications (in persian).
  • Hirschmugl, M., Sobe, C., Deutscher, J., & Schardt, M. (2018). Combined use of optical and synthetic aperture radar data for REDD+ applications in Malawi. Land, 7(4), 116.
  • https://developers.google.com/earth-engine/guides/sentinel1#metadata-and-filtering
  • Jensen, J. R. (2015). Introductory Digital Image Processing: A Remote Sensing Perspective, 4th edition
  • Joshi, N., Baumann, M., Ehammer, A., Fensholt, R., Grogan, K., Hostert, P., Jepsen, M.R., Kuemmerle, T., Waske, B., 2016. A review of the application of optical and radar remote sensing data fusion to land use mapping and monitoring. Remote Sens. (Basel) 8 (1), 1–23.
  • Kumar, L., & Mutanga, O., 2018. Google Earth Engine applications since inception: Usage, trends,and potential. Remote Sensing, 10(10), 1509
  • Leinenkugel, P., Wolters, M.L., Kuenzer, C., Oppelt, N., Dech, S., 2014. Sensitivity analysis for predicting continuous fields of tree-cover and fractional land-cover distributions in cloud-prone areas. Int. J. Remote Sens. 35 (8), 2799–2821.
  • Lopes, M., Frison, P. L., Durant, S. M., Schulte to Bühne, H., Ipavec, A., Lapeyre, V., & Pettorelli, N. (2020). Combining optical and radar satellite image time series to map natural vegetation: savannas as an example. Remote Sensing in Ecology and Conservation, 6(3), 316-326.
  • Mahendra, WK., Jamaluddin, II., Kamal, M. (2020). Mangroves Change Detection using Support Vector Machine Algorithm on Google Earth Engine (A Case Study in Part of Gulf of Bone, South Sulawesi, Indonesia). The 40th Asian Conference on Remote Sensing, 1.
  • Mahmoudzadeh, Hassan and Mahdavifard, Mostafa and Aziz Moradi, Majid and Zanjani Thani, Maliheh, 1399, Modeling the physical development of the city by combining the capabilities of Google Earth Engine (GEE) and artificial neural network (MLP) Case study: Tabriz, https (in Persian).
  • Mather, P. M., & Koch, M. (2011). Computer processing of remotely-sensed images: an introduction. John Wiley & Sons.
  • McFeeters, S. K. (1996). The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International journal of remote sensing, 17(7), 1425-1432.
  • Rouse, J. W., Haas, R. H., Schell, J. A., Deering, D. W., 1974. Monitoring Vegetation Systems in the Great
  • Mohammadi, A., Karimzadeh, S., Valizadeh Kamran, K., & Matsuoka, M. (2020). Extraction of land information, future landscape changes and seismic hazard assessment: A case study of Tabriz, Iran. Sensors, 20(24), 7010.
  • Noureddini, Seyed Ahmad Reza, Foundation, Amiraslam. (1399). Capability of supervised algorithms in preparing land cover maps at local scale (Case study: Guilan province. Quarterly Journal of Environmental Science and Technology, 22 (6), 295-309. Doi: 10.22034 / jest.2021.25422.3481 (in Persian).
  • Plains with ERTS, 3rd Earth Resource Technology Satellite (ERTS) Symposium, 1, 48-62.
  • Saah, D., Tenneson, K., Matin, M., Uddin, K., Cutter, P., Poortinga, A., ... & Chishtie, F. (2019). Land cover mapping in data scarce environments: challenges and opportunities. Frontiers in Environmental Science, 7, 150.
  • Shetaii, S. H., & Abdi, O. (2008). Mapping of land use in mountainous regions of Zagros using ETM+ data. Journal of Agricultural Sciences and Natural Resources, 57, 129-138.
  • Sim, C. K., Abdullah, K., Jafri, M. Z. M., & San Lim, H. (2013, July). Combination of radar and optical remote sensing data for land cover/use mapping. In 2013 IEEE International Conference on Space Science and Communication (IconSpace) (pp. 224-227). IEEE.
  • Steinhausen, M. J., Wagner, P. D., Narasimhan, B., & Waske, B. (2018). Combining Sentinel-1 and Sentinel-2 data for improved land use and land cover mapping of monsoon regions. International journal of applied earth observation and geoinformation, 73, 595-604.
  • Steinhausen, M. J., Wagner, P. D., Narasimhan, B., & Waske, B. (2018). Combining Sentinel-1 and Sentinel-2 data for improved land use and land cover mapping of monsoon regions. International journal of applied earth observation and geoinformation, 73, 595-604.
  • Veloso, A., Mermoz, S., Bouvet, A., Le Toan, T., Planells, M., Dejoux, J. F., & Ceschia, E. (2017). Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote sensing of environment, 199, 415-426.
  • Wagner, P.D., Waske, B., 2016. Importance of spatially distributed hydrologic variables for land use change modeling. Environ. Model. Softw. 83, 245–254.
  • Wagner, Paul D., et al., 2017. Comparing the Effects of Dynamic versus Static Representations of Land Use Change in Hydrologic Impact Assessments. Environ. Modell. Softw. 1–9.
  • Walker, W. (2014). Introduction to RADAR Remote Sensing for Vegetation Mapping and Monitoring. A Ph. D. presentation: Woods Hole Research Center.
  • Whyte, A., Ferentinos, K. P., & Petropoulos, G. P. (2018). A new synergistic approach for monitoring wetlands using Sentinels-1 and 2 data with object-based machine learning algorithms. Environmental Modelling & Software, 104, 40-54.
  • Zhen, J., Liao, J., & Shen, G. (2018). Mapping mangrove forests of Dongzhaigang nature reserve in China using Landsat 8 and Radarsat-2 polarimetric SAR data. Sensors, 18(11), 4012.
Geography and Human Relationships
Volume 5, Issue 3 - Serial Number 19
Autumn 2022
Pages 357-373

  • Receive Date 09 April 2022
  • Accept Date 05 May 2022