Integrating Sentinel 1 and 2 Satellite Data with Spectral Indices to Improve Classification Methods (Anzali Wetland)

Document Type : Original Article

Authors

1 Department of Natural Environment, Environmental Research Institute, University Jihad of Gilan Province, Rasht, Iran

2 Department of Water Resources Monitoring, Environmental Research Institute, University Jihad of Gilan Province, Rasht, Iran

3 Department of Waste Process, Environmental Research Institute, University Jihad of Gilan Province, Rasht, Iran

Abstract

Introduction: Technical limitations in classifying heterogeneous wetland environments, characterized by diverse vegetation cover, land use, and species diversity, often lead to interference in classification results and reduced accuracy in differentiating vegetation classes within wetland ecosystems. There is limited research available to improve classification methods in wetland environments. The main objective of this study is to investigate the combination of multi-spectral and radar data in improving the classification methods of wetland environments and to provide a method for fine separation of different plant covers in these biodiversity environments. In order to better examine the changes of the spectral index during a year, the open-source system of Google Earth Engine is used so that the spectral behavior of the phenomena during the year can be accurately studied.
Material and Methods: In this study, a combination of Sentinel-1 and Sentinel-2 data was used as the first data series, and a combination of Sentinel-2 data with spectral indices such as NDVI, SAVI, and mNDWI was used as the second data series. The best image for each season (summer, autumn, winter, and spring) from 2016 to 2022 was selected to create classification maps and examine detailed changes in the wetland. For image classification, training areas were selected based on field sampling, combining satellite imagery and Google Earth images. Classification was performed using three supervised algorithms: Support Vector Machine, Artificial Neural Network, and Maximum Likelihood. Also, the index map was prepared in the Google Earth Engine system and the indices were calculated using the ready-made products available in this system and were reviewed monthly for one year. To ensure the classification and to evaluate the classification accuracy, the most common accuracy estimation parameters, overall accuracy, producer accuracy, user accuracy and Kappa coefficient were used.
Results and Discussion: The results indicated that the combination of Sentinel-1 and Sentinel-2 data yielded better results compared to the combination of Sentinel-2 data with spectral indices. The overall accuracy and Kappa coefficient for the four periods were 92.99%, 87.43%, 83.80%, and 97.90% (in 2016, 2017, January 2022, and July 2022, respectively) when using the combination of Sentinel-1 and Sentinel-2 data, which were significantly higher than the results obtained with the combination of Sentinel-2 data and spectral indices. Furthermore, the combination of Sentinel-1 and Sentinel-2 data resulted in better detection of water bodies and lotus habitats within the wetland. NDVI, SAVI and mNDWI have a high correlation in examining the changes, so that an increasing trend was observed in the first six months of the year and a decreasing trend in the second six months, and the trend of vegetation and water changes is the same.
Conclusion: Due to the complexity of wetland spatial structures and existing threats, identifying land cover types is challenging. This study demonstrates the use of multi-temporal Sentinel-1 and Sentinel-2 data to comprehensively assess wetland characteristics. The accuracy assessment for the four study periods from 2016 to 2022 using three classification algorithms, Support Vector Machine, Maximum Likelihood, and Artificial Neural Network, showed that the combination of Sentinel-2 and Sentinel-1 data outperformed the combination of Sentinel-2 data with spectral indices in terms of overall accuracy and Kappa coefficient. Among the three algorithms used, the Maximum Likelihood algorithm consistently achieved the highest overall accuracy and Kappa coefficient compared to the other two algorithms.

Keywords

References

Abdoli Laktasarai, M. and Haghigi Khammami, M., 2021. Comparison of classification methods of support vector machine and artificial neural network in the preparation of land use map (case study: Bojag National Park). Environmental Research and Technology. 8(8), 47. 20.1001.1.26763060.1399.5.8.7.7
Abdoli, M. and Panahandeh, M., 2020. Investigating the trends of Anzali wetland connected domain coverage using remote sensing techniques and DPSIR conceptual framework. Environmental Sciences. 18(4), 125-140. doi: 10.52547/envs.18.4.125.
Adeli, S., Salehi, B., Mahidanpari, M., Quackenbush, L.J. and Chapman, B., 2022. Moving Toward L-band NASA-ISRO sAR mission (NISAR) dense time series: multipolarization object-based classification of wetlands using two machine learning algorithms. Earth and Space Science. 8(1), 1-18. https://doi.org/10.1029/2021EA001742
Al-Doski, J., Mansor, S.B., Ng, H., San, P. and Khuzaimah, Z., 2020. Land cover mapping using remote sensing data. American Journal of Geographic Information System. 9(1), 33-45. doi: 10.5923/j.ajgis.20200901.04.
Alibakhshi, Z., Alikhah Asl, M. and Rezavani, M., 2015. Preparing mighan wetland Land-use mapping in 2013: Using supervised and fuzzy classification methods. Human and Environment. 13(1), 11-21.
Atarchi, S., Gheysari, M., Hamzeh, S., and Alavi Panah, S. K., 2021. Land Cover Classification of Anzali Wetland Using Fusion of Sentinel 1 and ALOS/PALSAR 2 I.mages. Iranian journal of Ecohydrology. 8(3), 611-622. doi: 10.22059/ije.2021.320301.1478.
Berberoglu, S., Curran, P.J., Lloyd, C.D. and Atkinson, P.M., 2007. Texture classification of Mediterranean land cover. International Journal of Applied Earth Observation and Geoinformation. 9(3), 322-334. https://doi.org/10.1016/j.jag.2006.11.004.
Bishop, C., 2006. Pattern recognition and machine learning. Springer google schola, 2, 35-42.
Blaschke, T., Lang, S., and Hay, G. (Eds.)., 2008. Object-based image analysis: spatial concepts for knowledge-driven remote sensing applications. Springer Science & Business Media, 817. DOI:10.1007/978-3-540-77058-9.
Bonyad, A.A., and Hajighaderi, T., 2007. Producing Natural Forest Maps of the Zanjan by Usi ng ETM+ Data of Landsat 7 Satellite (In Persian), Science and Technology of Agriculture and Natural Resource, Water and Soil Science. 11(42), 627-638. 20.1001.1.22518517.1386.11.42.51.0.
Cortes, C., and Vapnik, V., 1995. Support-vector networks. Machine learning, 20, 273-297. https://doi.org/10.1023/A:1022627411411.
Dargahian, F., and Mosivand, Y., 2022. Investigating the natural and human factors affecting the changes in the land use classes of Shadgan‌ Wetland. Ecohydrology. 9 (1), 111-126. doi: 10.22059/ije.2022.332440.1567.
Dong, D., Wang, C., Yan, J., He, Q., Zeng, J., and 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) 044504-044504. DOI:10.1117/1.JRS.14.044504.
Ehsani, A. H., and Shakeryari, M., 2018. Determining the optimal method for classification and mapping of land use/land cover through comparison of artificial neural network and support vector machine algorithms using satellite data (Case study: International Hamoun wetland). Journal of Environmental Science and Technology. 20(4), 193-208. doi: 10.22034/jest.2019.13711
Fatemi, S. B., and Rezaei., Y., 2022. Principles of Remote Sensing. Azade Press. 350.
Felegari, S. Sharifi, A. Moravej, K., Amin, M., Golchin, A., Muzirafuti, A., and Zhao, N. 2021. Integration of sentinel 1 and sentinel 2 satellite images for crop mapping. Applied Sciences. 11(21), 10104. https://doi.org/10.3390/app112110104.
Ghahraman, A., and Atar, F., 2011. Anzali Wetland in Danger of Death (An Ecologic- Floristic Research). Journal of Environmental Studies. 28(17), 1-38. DOI: 10.22059/IJE.2021.320301.1478.
Goodfellow, I., Bengio, Y., and Courville, A., 2016. Deep learning. MIT press. www.deeplearningbook.org.
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., and Moore, R., 2017. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote sensing of Environment. 202, 18-27. https://doi.org/10.1016/j.rse.2017.06.031.
Hu, T., Liu. J., Zheng, G., Zhang, D., and Huang, K. 2020. Evaluation of historical and future wetland degradation using remote sensing imagery and land use modeling. Land Degradation & Development. 31(1), 65-80. https://doi.org/10.1002/ldr.3429.
Huang, C., Wylie, B., Yang, L., Homer, C., and Zylstra, G., 2002. Derivation of a tasselled cap transformation based on Landsat 7 at-satellite reflectance. International journal of remote sensing. 23(8), 1741-1748. https://doi.org/10.1080/01431160110106113.
Imani, J., Ebrahimi, A., Gholonejad, B., and Tahmasebi, P., 2018. Comparison of NDVI and SAVI in three plant communities with different sampling intensity (Case Study: Choghakhour Lake Rangelands in Charmahal & Bakhtiri). Iranian Journal of Range and Desert Research, 25(1), 152-169. doi: 10.22092/ijrdr.2018.116233.
Javedankherad, E.,  Esmaeili Sari, A., and Bahramifar, N., 2011. Investigation of Persistent Organic Pollutants Residue in Sediments of International Anzali Wetland, Iran. Journal of Environmental studies. 37(57), 1-10. https://doi.org/10.1080/01431160110106113.
Ju, Y., and Bohrer, G., 2022. Classification of wetland vegetation based on NDVI time series from the HLS dataset. Remote Sensing. 14(9), 2107.  https://doi.org/10.3390/rs14092107.
Lu, Dengsheng., Mausel P., Brondizio., E and Moran, E., 2004. Change detection techniques, International journal of remote sensing. 25(12), 2365-2401. DOI:10.1080/0143116031000139863.
Melendez-Pastor. I., Navarro-Pedreno. J., Gómez, I., and Koch, M., 2010. Detecting drought induced environmental changes in a Mediterranean wetland by remote sensing. Applied Geography. 30(2), 254-262. https://doi.org/10.1016/j.apgeog.2009.05.006.
Mohammadi, A., Sarab, A., Jafari, M., and Jafari, A., 2010. Investigating the amount of chlorophyll changes in forest land based on NDVI index, case study: central areas of Gilan province. Application of Remote Sensing and Geographic Information System in Planning. 1(2), 7-15.
Mondal, A., Kundu, S., Chandniha, S. K., Shukla, R., and Mishra, P. K., 2012. Comparison of support vector machine and maximum likelihood classification technique using satellite imagery. International Journal of Remote Sensing and GIS. 1(2), 116-123. https://www.researchgate.net/publication/280316746_Comparison_of_support_vector_machine_and_maximum_likelihood_classification_technique_using_satellite_imagery.
Nouredini,  S.A.R., and Bonyad, A.A., 2017. Investigation of Atmospheric Correction Methods in Estimation of Forest Canopy Density of Guilan Province Using Vegetation Indices of Landsat 8 Data. Iranian Journal of remote Sensing & GIS. 9(1), 93-110. http://gisj.sbu.ac.ir/article/download/20118/6513.
Pamungkas, S., 2023. Analysis of Vegetation Index for Ndvi Evi-2 And Savi for Mangrove Forest Density Using Google Earth Engine in Lembar Bay Lombok Island. In IOP Conference Series: Earth and Environmental Science. 1127(1), 012034, IOP Publishing. DOI: 10.1088/1755-1315/1127/1/012034.
Rasti, S., Mahdavi Fard, M., Sheikh Qadri, H., Nasiri, A., and Tektaz, N. Z., 2022. Improving classification accuracy by combining multi-seasonal images of Sentinel 1 and 2 in order to prepare a land use map in the cloud space of Google Earth Engine (case study: Gilan province). Geography and Human Relations. 5 (3), 357-373. doi: 10.22034/gahr.2022.336692.1696
Ruiz L. F. C., Guasselli L. A., Simioni J. P. D., Belloli T. F., and Fernandes P. C. B., 2021. Object-based classification of vegetation species in a subtropical wetland using Sentinel-1 and Sentinel-2A images. Science of Remote Sensing. 3, 100017. https://doi.org/10.1016/j.srs.2021.100017.
Sarkheil, H., Rezaei, H. R., Rayegani, B., Khorramdin, S., and Rahbari, SH., 2021. Fuzzy dynamic system analysis of pollution accumulation in the Anzali wetland using empirical-nonlinear aspects of an economically-socio-environmental interest conflict. Environmental Challenges. 2, 100025. https://doi.org/10.1016/j.envc.2021.100025.
Sefidian, S., SalmanMahini, A., R., Mirkarimi, S., H., and Mirkarimi, N., Ali., 2015. Vegetation classification based on wetland index with the help of remote sensing and ground sampling (case study: Algal International Wetland). Wetland Ecobiology. 7 (2), 5-22. https://jweb.ahvaz.iau.ir/article-1-317-en.html.
Shah Hoseini, R., Azizi, K., Zarei, A., and Moradi, F., 2022. Object-Oriented Classification of Urban Areas Using a Combination of Sentinel-1 and Sentinel-2 Images. Iranian Journal of Remote Sensing & GIS, 14(3), 105-121. doi: 10.52547/gisj.14.3.105
Tavares, P. A., Beltrão, N. E. S., Guimarães, U. S., and Teodoro, A. C., 2019. Integration of sentinel-1 and sentinel-2 for classification and LULC mapping in the urban area of Belém, eastern Brazilian Amazon. Sensors. 19(5), 1140. https://doi.org/10.3390/s19051140.
Vizzari. M., 2022. PlanetScope Sentinel-2 and Sentinel-1 Data Integration for Object-Based Land Cover Classification in Google Earth Engine. Remote Sensing. 14(11), 2628.  https://doi.org/10.3390/rs14112628.
Wang, S., Chen, W., Xie, S. M., Azzari, G., and Lobell, D. B., 2020. Weakly supervised deep learning for segmentation of remote sensing imagery. Remote Sensing. 12(2), 207. https://doi.org/10.3390/rs12020207.
Wu, N., Shi, R., Zhuo, W., Zhang, C., Zhou, B., Xia, Z., and Tian, B., 2021. A classification of tidal flat wetland vegetation combining phenological features with Google Earth Engine. Remote Sensing. 13(3), 443. https://doi.org/10.3390/rs13030443.
Xu, H., 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing. 27(14), 3025–3033. DOI:10.1080/01431160600589179.
Yang, C., Zhang, C., Li, Q., Liu, H., Gao, W., Shi, T., and Wu, G. 2020. Rapid urbanization and policy variation greatly drive ecological quality evolution in Guangdong-Hong Kong-Macau Greater Bay Area of China: A remote sensing perspective. Ecological Indicators. 115, 106373. https://doi.org/10.1016/j.ecolind.2020.106373.
Environmental Sciences
Volume 22, Issue 3
2024
Pages 389-406

Files

Share

How to cite

Statistics