تفکیک محصولات زراعی با استفاده از ترکیب تصاویر سنتینل-1 و 2 در استان اردبیل

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد گروه سنجش از دور و سیستم اطلاعات جغرافیایی، دانشکدة علوم انسانی، دانشگاه تربیت مدرس، تهران، ایران

2 دانشیارگروه سنجش از دور و سیستم اطلاعات جغرافیایی، دانشکدة علوم انسانی، دانشگاه تربیت مدرس، تهران، ایران

چکیده

سابقه و هدف: شناسایی و نقشه کردن محصولات زراعی اطلاعات مهمی برای مدیریت زمین‌های کشاورزی و برآورد سطح زیر کشت محصولات زراعی فراهم می‌کند.
تصاویر اپتیک و راداری، منابع ارزشمندی برای طبقه‌بندی زمین‌های کشاورزی است. ویژگی‌های مستخرج از تصاویر اپتیک حاوی اطلاعاتی در مورد امضای بازتابی محصولات مختلف است. در مقابل، یک تصویر راداری فراهم‌کنندة اطلاعاتی در مورد خصوصیات ساختاری و سازوکارهای پراکنش محصولات است. ترکیب این دو منبع قادر به ایجاد یک مجموعه دادة مکمل با تعداد چشمگیری از ویژگی‌های زمانی طیفی، بافت و قطبیده برای طبقه‌بندی زمین‌های کشاورزی است.
مواد و روش‌ها: این پژوهش به بررسی اهمیت باندهای لبه‌قرمز برای تفکیک محصولات زراعی شامل گندم، جو، یونجه، لوبیا، باقلا، کتان، ذرت، چغندر قند و سیب‌زمینی با استفاده از روش جنگل تصادفی و ماشین بردار پشتیبان می‌پردازد. بدین منظور سری زمانی تصاویر سنتینل-1 و 2 در سال 2019 از شمال غرب شهر اردبیل در پلتفرم ارت انجین فراخوانی شد. ترکیب‌های متفاوت باندها برای بررسی تأثیرات اطلاعات طیفی و زمانی، شاخص‌های گیاهی و اطلاعات بازپراکنش برای طبقه‌بندی محصولات بررسی شد. با استفاده از روش انتخاب ویژگی جنگل تصادفی ویژگی­های مهم شناسایی و به‌عنوان ورودی الگوریتم جنگل تصادفی و ماشین بردار پشتیبان معرفی شدند.
نتایج و بحث :
جنگل تصادفی برای تمامی سناریوها بهترین نتیجه را به دست آورد. نتایج نشان داد افزودن طول ‌موج‌های لبه‌قرمز و شاخص‌های مشتق‌شده از آن باعث شد محصولاتی همچون جو، لوبیا، باقلا و کتان نسبت به سایر محصولات با صحت بالاتری تفکیک شود. بهترین نتیجه در میان ترکیبات مختلف ویژگی‌ها مربوط به تلفیق سری زمانی ویژگی‌های طیفی تصاویر سنتینل-2 با سری زمانی تصاویر سنتینل-1 بود. صحت کلی 67/84 درصد و ضریب کاپا 31/ 82 درصد به دست آمد. نتایج نشان داد باندهای لبه‌قرمز و شاخص‌های پوشش گیاهی مبتنی بر آن به‌تنهایی قابلیت جداسازی محصولات زراعی را از همدیگر دارند.
نتیجه‌گیری: پیشنهاد می‌شود برای دستیابی به صحت بالاتر در تفکیک محصولات زراعی انتخاب باندهای طیفی هدفمند مورد توجه قرار گیرد. ترکیبی از تصاویر راداری و اپتیک همیشه از روش طبقه‌بندی براساس تک‌سنجنده بهتر عمل می‌کند و به افزایش اطلاعات طبقه‌بندی منجر می‌شود.

کلیدواژه‌ها

عنوان مقاله [English]

Crop mapping using a combination of Sentinel-1 and 2 images in Ardabil province

نویسندگان [English]

  • Bahar Asadi 1
  • Ali shamsoddini 2
1 Msc, Department of Remote Sensing and GIS, Tarbiat Modares University, Tehran, Iran
2 Associate professor, Department of Remote Sensing and GIS, Tarbiat Modares University, Tehran, Iran
چکیده [English]

Introduction: Identifying and mapping crops provides important information to agricultural lands management and cultivation area estimation of crops. Optical and radar images are valuable resources for classifiying agricultural land. Features deriverd from optical images contain information about the reflectance signatures of various products, while radar images provides information about the structural characteristics and distribution mechanisms of products. The combination of these two sources can create a complementary dataset with a significant number of spectral, texture and polarized temporal features for the classification of agricultural land
Material and methods: This study aims to explore the significance of red edge bands for the segregation of crops such aswheat, barley, alfalfa, beans, broad beans, flax, corn, sugar beet and potatoes using the random forest method and support vector machine. To conduct the analysis, a time series of Sentinel-1 and 2 images 2019 in the northwest region of Ardabil was retrieved from the Google Earth Engine (GEE) platform. The study evaluates the effectiveness of spectral and temporal information, plant indices and backscatter information on the crop mapping by examining different combinations of bands. Through the random forest feature selection method, essential features are identified and utilized as inputs for both the random forest and support vector machine classifiers.
Results and discussion: The random forest provided the most favorable outcomes across all scenarios. The results revealed that incorporating red edge wavelengths and red edge-based vegetation indices proved more beneficial than other bands and vegetation indices for differentiating between barley, beans, broad beans, and flax. The most optimal outcome among various feature combinations was associated with the time series of spectral features from Sentinel-2 images combined with the time series of Sentinel-1 images, resulting in an overall accuracy of 84.67% and a kappa coefficient of 82.31%.  Furthermore, the results demonstrated that red edge bands and red edge-based vegetation indices effectively distinguish between different types of crops
Conclusion: It is recommended to carefully consider the selection of specific spectral bands to achieve higher accuracy in separation of crops. It is important to highlight that combining radar and optical images consistently yields superior results compared to classification methods based on a single sensor, leading to increased classification information.

کلیدواژه‌ها [English]

  • Optical and radar image fusion
  • Crop mapping
  • Red edge bands
  • Red edge-based vegetation indices
  • Machine learning

مراجع

Aduvukha, G. R., Abdel-Rahman, E. M., Sichangi, A. W., Makokha, G. O., Landmann, T., Mudereri, B. T., ... & Dubois, T. (2021). Cropping Pattern Mapping in an Agro-Natural Heterogeneous Landscape Using Sentinel-2 and Sentinel-1 Satellite D atasets. Agriculture, 11(6), 530. https://doi.org/10.3390/agriculture11060530
Ban, Y. (2003). Synergy of multitemporal ERS-1 SAR and Landsat TM data for classification of agricultural crops. Canadian Journal of Remote Sensing, 29(4), 518-526. https://doi.org/10.5589/m03-014
Blickensdörfer, L., Schwieder, M., Pflugmacher, D., Nendel, C., Erasmi, S., & Hostert, P. (2022). Mapping of crop types and crop sequences with combined time series of Sentinel-1, Sentinel-2 and Landsat 8 data for Germany. Remote sensing of environment, 269, 112831. https://doi.org/10.1016/j.rse.2021.112831
 
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Brisco,B.(1998).”Agricultural Application With Radar” Principles and Application of Imaging RADAR:381-406.
Bégué, A., Arvor, D., Bellón, B., Betbeder, J., Abelleyra, D. D., Ferraz, R. P. D., ... & Verón, S. R. Remote Sensing and Cropping Practices: A Review. Remote Sens, 2018, 10 (1), 99.
Bolton, D. K., & Friedl, M. A. (2013). Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agricultural and Forest Meteorology, 173, 74-84. https://doi.org/10.1016/j.agrformet.2013.01.007
Belgiu, M., & Csillik, O. (2018). Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote sensing of environment, 204, 509-523. https://doi.org/10.1016/j.rse.2017.10.005
Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote sensing of environment, 37(1), 35-46.
https://doi.org/10.1016/0034-4257(91)90048-B
Chong, L. U. O., LIU, H. J., LU, L. P., LIU, Z. R., KONG, F. C., & ZHANG, X. L. (2021). Monthly composites from Sentinel-1 and Sentinel-2 images for regional major crop mapping with Google Earth Engine. Journal of Integrative Agriculture, 20(7), 1944-1957. https://doi.org/10.1016/S2095-3119(20)63329-9
 
Conese, C., & Maselli, F. (1991). Use of multitemporal information to improve the classification performance of TM scenes in complex terrain. ISPRS Journal of Photogrammetry and Remote Sensing, 46(4), 187-197. https://doi.org/10.1016/0924-2716(91)90052-W
 
Clerici, N., Valbuena Calderón, C. A., & Posada, J. M. (2017). Fusion of Sentinel-1A and Sentinel-2A data for land cover mapping: a case study in the lower Magdalena region, Colombia. Journal of Maps, 13(2), 718-726. https://doi.org/10.1080/17445647.2017.1372316
 
Dash, J., & Curran, P. J. (2004). The MERIS terrestrial chlorophyll index.
Feng, S., Zhao, J., Liu, T., Zhang, H., Zhang, Z., & Guo, X. (2019). Crop type identification and mapping using machine learning algorithms and sentinel-2 time series data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(9), 3295-3306. https://doi.org/10.1109/JSTARS.2019.2922469
Filgueiras, R., Mantovani, E. C., Althoff, D., Fernandes Filho, E. I., & Cunha, F. F. D. (2019). Crop NDVI monitoring based on sentinel 1. Remote Sensing, 11(12), 1441. https://doi.org/10.3390/rs11121441
Gao, F., Anderson, M. C., Zhang, X., Yang, Z., Alfieri, J. G., Kustas, W. P., ... & Prueger, J. H. (2017). Toward mapping crop progress at field scales through fusion of Landsat and MODIS imagery. Remote Sensing of Environment, 188, 9-25. https://doi.org/10.1016/j.rse.2016.11.004
Gitelson, A. A., Kaufman, Y. J., & Merzlyak, M. N. (1996). Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote sensing of Environment, 58(3), 289-298. https://doi.org/10.1016/S0034-4257(96)00072-7
Haboudane, D., Miller, J. R., Pattey, E., Zarco-Tejada, P. J., & Strachan, I. B. (2004). Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote sensing of environment, 90(3), 337-352. https://doi.org/10.1016/S0034-4257(96)00072-7
Huang, Z., Chen, H., Hsu, C. J., Chen, W. H., & Wu, S. (2004). Credit rating analysis with support vector machines and neural networks: a market comparative study. Decision support systems, 37(4), 543-558. https://doi.org/10.1016/S0167-9236(03)00086-1
Immitzer, M., Vuolo, F., & Atzberger, C. (2016). First experience with Sentinel-2 data for crop and tree species classifications in central Europe. Remote sensing, 8(3), 166. https://doi.org/10.3390/rs8030166
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, p. 18). New York: Springer
Jia, K., Li, Q., Tian, Y., Wu, B., Zhang, F., & Meng, J. (2012). Crop classification using multi-configuration SAR data in the North China Plain. International Journal of Remote Sensing, 33(1), 170-183. https://doi.org/10.1080/01431161.2011.587844
Joelsson, S. R., Benediktsson, J. A., & Sveinsson, J. R. (2005, July). Random forest classifiers for hyperspectral data. In Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS'05. (Vol. 1, pp. 4-pp). IEEE. https://doi.org/10.1109/IGARSS.2005.1526129
 
Kang, Y., Meng, Q., Liu, M., Zou, Y., & Wang, X. (2021). Crop Classification Based on Red Edge Features Analysis of GF-6 WFV Data. Sensors, 21(13), 4328. https://doi.org/10.3390/s21134328
 
Kim, H. O., & Yeom, J. M. (2014). Effect of red-edge and texture features for object-based paddy rice crop classification using RapidEye multi-spectral satellite image data. International Journal of Remote Sensing, 35(19), 7046-7068. https://doi.org/10.1080/01431161.2014.965285
 
Kobayashi, N., Tani, H., Wang, X., & Sonobe, R. (2020). Crop classification using spectral indices derived from Sentinel-2A imagery. Journal of Information and Telecommunication, 4(1), 67-90. https://doi.org/10.1080/24751839.2019.1694765
 
 
Khosravi, I., & Alavipanah, S. K. (2019). A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. International Journal of Remote Sensing, 40(18), 7221-7251. https://doi.org/10.1080/01431161.2019.1601285
 
[26] Khosravi, I., Safari, A., & Homayouni, S. (2018). MSMD: maximum separability and minimum dependency feature selection for cropland classification from optical and radar data. International Journal of Remote Sensing, 39(8), 2159-2176. https://doi.org/10.1080/01431161.2018.1425564
 
Liu, C., Shang, J., Vachon, P. W., & McNairn, H. (2012). Multiyear crop monitoring using polarimetric RADARSAT-2 data. IEEE Transactions on Geoscience and Remote sensing, 51(4), 2227-2240. https://doi.org/10.1109/TGRS.2012.2208649
 
 
Liu, Y., Wang, X., & Qian, J. (2021). Crop distribution extraction based on Sentinel data. In E3S Web of Conferences (Vol. 252, p. 02081). EDP Sciences.
https://doi.org/10.1051/e3sconf/202125202081
 
 
Nitze, I., Barrett, B., & Cawkwell, F. (2015). Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series. International Journal of Applied Earth Observation and Geoinformation, 34, 136-146. https://doi.org/10.1016/j.jag.2014.08.001
 
Orynbaikyzy, A., Gessner, U., & Conrad, C. (2019). Crop type classification using a combination of optical and radar remote sensing data: a review. International journal of remote sensing, 40(17), 6553-6595. https://doi.org/10.1080/01431161.2019.1569791
 
Pal, M., & Mather, P. M. (2004). Assessment of the effectiveness of support vector machines for hyperspectral data. Future generation computer systems, 20(7), 1215-1225. https://doi.org/10.1016/j.future.2003.11.011
 
Qiong, H. U., WU, W. B., Qian, S. O. N. G., Miao, L. U., Di, C. H. E. N., YU, Q. Y., & TANG, H. J. (2017). How do temporal and spectral features matter in crop classification in Heilongjiang Province, China?. Journal of integrative agriculture, 16(2), 324-336. https://doi.org/10.1016/S2095-3119(15)61321-1
 
Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93-104. https://doi.org/10.1016/j.isprsjprs.2011.11.002
 
Shamsoddini, A., J. C. Trinder, and R. Turner. 2013. “Non-Linear Methods for Inferring Lidar Metrics Using SPOT-5 Textural Data.” ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences II-5/W2: 259–264. doi:10.5194/isprsannals-II-5-W2-259-2013. https://doi.org/10.5194/isprsannals-II-5-W2-259-2013, 2013.
 
 
Skriver, H., Mattia, F., Satalino, G., Balenzano, A., Pauwels, V. R., Verhoest, N. E., & Davidson, M. (2011). Crop classification using short-revisit multitemporal SAR data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 4(2), 423-431. https://doi.org/10.1109/JSTARS.2011.2106198
 
Sun, C., Bian, Y., Zhou, T., & Pan, J. (2019). Using of multi-source and multi-temporal remote sensing data improves crop-type mapping in the subtropical agriculture region. Sensors, 19(10), 2401. https://doi.org/10.3390/s19102401
 
Sun, L., Chen, J., Guo, S., Deng, X., & Han, Y. (2020). Integration of Time Series Sentinel-1 and Sentinel-2 Imagery for Crop Type Mapping over Oasis Agricultural Areas. Remote Sensing, 12(1), 158. https://doi.org/10.3390/rs12010158
 
Shamsoddini, A., & Raval, S. (2018). Mapping red edge-based vegetation health indicators using Landsat TM data for Australian native vegetation cover. Earth Science Informatics, 11(4), 545-552. https://doi.org/10.1080/01431160701281056
 
Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote sensing of Environment, 62(1), 77-89.
https://doi.org/10.1016/S0034-4257(97)00083-7
 
Stehman, S. V., & Foody, G. M. (2019). Key issues in rigorous accuracy assessment of land cover products. Remote Sensing of Environment, 231, 111199.
https://doi.org/10.1016/j.rse.2019.05.018
 
Sonobe, R., Yamaya, Y., Tani, H., Wang, X., Kobayashi, N., & Mochizuki, K. I. (2018). Crop classification from Sentinel-2-derived vegetation indices using ensemble learning. Journal of Applied Remote Sensing, 12(2), 026019. https://doi.org/10.1117/1.JRS.12.026019
 
 
Schuster, C., Förster, M., & Kleinschmit, B. (2012). Testing the red edge channel for improving land-use classifications based on high-resolution multi-spectral satellite data. International Journal of Remote Sensing, 33(17), 5583-5599. https://doi.org/10.1080/01431161.2012.666812
 
Tariq, A., Yan, J., Gagnon, A. S., Riaz Khan, M., & Mumtaz, F. (2022). Mapping of cropland, cropping patterns and crop types by combining optical remote sensing images with decision tree classifier and random forest. Geo-spatial Information Science, 1-19. https://doi.org/10.1080/10095020.2022.2100287
 
Tavakkoli, M. (2011). Multi-Temporal Classification of Crops Using ENVISAT ASAR Data (Doctoral dissertation, Ph. D. Dissertation, Leibniz University of Hannover). DOI:10.4236/ijg.2014.52021
 
 
Tscharntke, T., Clough, Y., Wanger, T. C., Jackson, L., Motzke, I., Perfecto, I., ... & Whitbread, A. (2012). Global food security, biodiversity conservation and the future of agricultural intensification. Biological Conservation, 151(1), 53-59. https://doi.org/10.1016/j.biocon.2012.01.068
 
Wilson, J. H., Zhang, C., & Kovacs, J. M. (2014). Separating crop species in northeastern Ontario using hyperspectral data. Remote Sensing, 6(2), 925-945. https://doi.org/10.3390/rs6020925
 
Veloso, A., Mermoz, S., Bouvet, A., Le Toan, T., Planells, M., Dejoux, J. F., & Ceschia, E. (2017). Understanding the temporal behaviour of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote sensing of environment, 199, 415-426. https://doi.org/10.1016/j.rse.2017.07.015
 
Yilmaz, M. T., Hunt Jr, E. R., & Jackson, T. J. (2008). Remote sensing of vegetation water content from equivalent water thickness using satellite imagery. Remote Sensing of Environment, 112(5), 2514-2522. https://doi.org/10.1016/j.rse.2007.11.014
 
Yi, Z., Jia, L., & Chen, Q. (2020). Crop classification using multi-temporal Sentinel-2 data in the Shiyang River Basin of China. Remote Sensing, 12(24), 4052. https://doi.org/10.3390/rs12244052
 
Zandsalimi, Z., Sima, S., & Mousivand, A. (2021). Evaluating the Performance of Global Land Cover Maps in Agricultural Land Delineation (Case Study: Lake Urmia Basin). Iranian Journal of Soil and Water Research, 52(3), 795-810. https://dx.doi.org/10.22059/ijswr.2021.315097.668828
 
Zhong, L., Gong, P., & Biging, G. S. (2014). Efficient corn and soybean mapping with temporal extendability: A multi-year experiment using Landsat imagery. Remote Sensing of Environment, 140, 1-13. https://doi.org/10.1016/j.rse.2013.08.023
 
Zhang, T., Su, J., Liu, C., Chen, W. H., Liu, H., & Liu, G. (2017, September). Band selection in Sentinel-2 satellite for agriculture applications. In 2017 23rd International Conference on Automation and Computing (ICAC) (pp. 1-6). IEEE. https://doi.org/10.23919/IConAC.2017.8081990
 
Zhang, H., Kang, J., Xu, X., & Zhang, L. (2020). Accessing the temporal and spectral features in crop type mapping using multi-temporal Sentinel-2 imagery: A case study of Yi’an County, Heilongjiang province, China. Computers and Electronics in Agriculture, 176, 105618. https://doi.org/10.1016/j.compag.2020.105618
 
Zhang, L., Gong, Z. N., Wang, Q. W., Jin, D. D., & Wang, X. (2019). Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images. J. Remote Sens, 23, 313-326. https://doi.org/10.1016/j.scitotenv.2021.147061
 
Zhang, H., Wang, Y., Shang, J., Liu, M., & Li, Q. (2021). Investigating the impact of classification features and classifiers on crop mapping performance in heterogeneous agricultural landscapes. International Journal of Applied Earth Observation and Geoinformation, 102, 102388. https://doi.org/10.1016/j.jag.2021.102388

فایل ها

هم رسانی

ارجاع به این مقاله

آمار