Detailed Mapping of Irrigated Rice Fields Using Remote Sensing data and Segmentation Techniques: A case of study in Turvo, Santa Catarina, Brazil
DOI:
https://doi.org/10.5753/jidm.2025.4181Keywords:
CBERS-4A/WPM, Sentinel-2, Time Series, Agriculture, Segment Anything ModelAbstract
In this study, we evaluated multiple methods and data sources for mapping irrigated rice fields in Turvo, Santa Catarina, using a detailed reference map that includes irrigation channels, roads, and boundaries within and between rice fields. We tested different approaches using a per-pixel and segmentation approaches. In the per-pixel classifications scenarios we used a a Random Forest (RF) applied to the China-Brazil Earth-Resources Satellite Multispectral and Panchromatic Wide-Scan Camera (CBERS-4A/WPM) data, and to Sentinel-2 (S2) imagery. For the segmentation approach we used a combination of S2 imagery with a Segment Anything Model geospatial (Samgeo) mask applied to high-resolution CBERS-4A/WPM data (S2+WPM/Samgeo). We qualitatively and quantitatively compared maps derived from a existing source (MapBiomas) with our scenarios. MapBiomas and per-pixel S2 classification provided adequate general plot boundary identification, however, lacked finer details. CBERS-4A/WPM data captured some of these details, although they showed a high rate of false positives due to confusion with other vegetation types. We also examined how detailed rice field mapping affected time-series analysis. Our findings indicate that the S2+WPM/Samgeo approach most closely matched the reference map time-series and offered superior detail, better distinguishing field heterogeneities. This method could support more detailed and accurate monitoring of rice fields. Overall, S2+WPM/Samgeo delivered the most precise and detailed mapping of irrigated rice in the region.
Downloads
References
Amani, M., Kakooei, M., Moghimi, A., Ghorbanian, A., Ranjgar, B., Mahdavi, S., Davidson, A., Fisette, T., Rollin, P., Brisco, B., and Mohammadzadeh, A. (2020). Application of Google Earth Engine Cloud Computing Platform, Sentinel Imagery, and Neural Networks for Crop Mapping in Canada. Remote Sensing, 12(21):2072–4292. DOI: https://doi.org/10.3390/rs122135611.
ANA (2020). Mapeamento do arroz irrigado no Brasil. Technical report, Agência Nacional de Águas e Saneamento - ANA.
Badda, H., Cherif, E. K., Boulaassal, H., Wahbi, M., Alaoui, O. Y., Maatouk, M., Bernardino, A., Coren, F., and El Kharki, O. (2023). Improving the Accuracy of Random Forest Classifier for Identifying Burned Areas in the Tangier-Tetouan-Al Hoceima Region Using Google Earth Engine. Remote Sensing, 15(17):4226. DOI: https://doi.org/10.3390/rs15174226.
Bazzan, T., Rennó, C, D., Lima, D. L. C., and Reckziegel, E. W. (2022). Integração da incerteza na amostragem e classificação Random Forest utilizando bandas e índices espectrais para o mapeamento de inundação. Geociências, 41(4):905–925. DOI: https://doi.org/10.5016/geociencias.v41i04.16802.
Bellón, B., Bégué, A., Lo Seen, D., De Almeida, C. A., and Simões, M. (2017). A remote sensing approach for regional-scale mapping of agricultural land-use systems based on ndvi time series. Remote Sensing, 9(6):600. DOI: https://doi.org/10.3390/rs9060600.
Beriaux, E., Jago, A., Lucau-Danila, C., Planchon, V., and Defourny, P. (2021). Sentinel-1 time series for crop identification in the framework of the future cap monitoring. Remote Sensing, 13(14):2785. DOI: https://doi.org/10.3390/rs13142785.
Boschetti, M., Busetto, L., Manfron, G., Laborte, A., Asilo, S., Pazhanivelan, S., and Nelson, A. (2017). PhenoRice: A method for automatic extraction of spatio-temporal information on rice crops using satellite data time series. Remote sensing of environment, 194:347–365. DOI: https://doi.org/10.1016/j.rse.2017.03.029.
Brinkhoff, J., Hornbuckle, J., and Barton, J. L. (2018). Assessment of aquatic weed in irrigation channels using uav and satellite imagery. Water, 10(11):1497. DOI: https://doi.org/10.3390/w10111497.
Castro Álvarez, R., Morejón Rivera, R., Díaz Solís, S. H., and Álvarez, G. E. (2013). Efecto de borde y la validez de los muestreos en el cultivo del arroz. Cultivos Tropicales, 34(2):70–75. DOI: https://tinyurl.com/3yzdz6az.
Clauss, K., Ottinger, M., and Künzer, C. (2018). Mapping rice areas with sentinel-1 time series and superpixel segmentation. International journal of remote sensing, 39(5):1399–1420. DOI: https://doi.org/10.1080/01431161.2017.1404162.
CONAB (2023). Acompanhamento da safra brasileira de grãos - Safra 2022/23. Technical Report 9, Companhia Nacional de Abastecimento.
Crisóstomo de Castro Filho, H., Abílio de Carvalho Júnior, O., Ferreira de Carvalho, O. L., Pozzobon de Bem, P., dos Santos de Moura, R., Olino de Albuquerque, A., Rosa Silva, C., Guimaraes Ferreira, P. H., Fontes Guimarães, R., and Trancoso Gomes, R. A. (2020). Rice crop detection using lstm, bi-lstm, and machine learning models from sentinel-1 time series. Remote Sensing, 12(16):2655. DOI: https://doi.org/10.3390/rs12162655.
Csillik, O., Belgiu, M., Asner, G. P., and Kelly, M. (2019). Object-based time-constrained dynamic time warping classification of crops using sentinel-2. Remote sensing, 11(10):1257. DOI: https://doi.org/10.3390/rs11101257.
Cucho-Padin, G., Loayza, H., Palacios, S., Balcazar, M., Carbajal, M., and Quiroz, R. (2020). Development of low-cost remote sensing tools and methods for supporting small-holder agriculture. Applied Geomatics, 12:247–263. DOI: https://doi.org/10.1007/s12518-019-00292-5.
de Bem, P. P., de Carvalho Júnior, O. A., de Carvalho, O. L. F., Gomes, R. A. T., Guimarães, R. F., and Pimentel, C. M. M. (2021). Irrigated rice crop identification in southern brazil using convolutional neural networks and sentinel-1 time series. Remote Sensing Applications: Society and Environment, 24:100627. DOI: https://doi.org/10.1016/j.rsase.2021.100627.
FAO (2022). FAOSTAT: FAO Statistical Databases. Available: [link]. Accessed on: 2022-06-19.
Garcia, A. D. B., Chaves, M. E. D., Prudente, V. H. R., and Sanches, I. D. (2023). Assessing The Influence Of Borders And Roads On The Segmentation Of Rice Fields: A Case Study. In XXIV Brazilian Symposium on Geoinformatics - GEOINFO 2023, São José dos Campos, SP, Brazil, December 4-6, 2023, pages 1–12. MCTI/INPE. DOI: https://dblp.org/db/conf/geoinfo/geoinfo2023.html.
Garcia-Pedrero, A., Lillo-Saavedra, M., Rodriguez-Esparragon, D., and Gonzalo-Martin, C. (2019). Deep learning for automatic outlining agricultural parcels: Exploiting the land parcel identification system. IEEE access, 7:158223–158236. DOI: https://doi.org/10.1109/ACCESS.2019.2950371.
GDAL and OGR (2024). GDAL/OGR: Geospatial Data Abstraction software Library. Available: [link]. Access: 01 may 2024.
Gomez, K. A. and De Datta, S. K. (1971). Border effects in rice experimental plots I. unplanted borders. Experimental Agriculture, 7(1):87–92. DOI: https://doi.org/10.1017/S0014479700004816.
Google (2024). Google earth engine developers: Resampling and reducing resolution. Website. Available: [link]. Access: 01 may 2024.
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. DOI: https://doi.org/10.1016/j.rse.2017.06.031.
Guan, X., Huang, C., Liu, G., Meng, X., and Liu, Q. (2016). Mapping rice cropping systems in vietnam using an ndvi-based time-series similarity measurement based on dtw distance. Remote Sensing, 8(1):19. DOI: https://doi.org/10.3390/rs8010019.
Harsh, S., Singh, D., and Pathak, S. (2021). Efficient and cost-effective drone–ndvi system for precision farming. International Journal of New Practices in Management and Engineering, 10(04):14–19. DOI: https://doi.org/10.17762/ijnpme.v10i04.126.
Holzman, M. E., Rivas, R. E., and Bayala, M. I. (2021). Relationship between tir and nir-swir as indicator of vegetation water availability. Remote Sensing, 13(17):3371. DOI: https://doi.org/10.3390/rs13173371.
Jiang, L., Zhang, B., Ni, Q., Sun, X., and Dong, P. (2019). Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method. Access, 7:12647–12657. DOI: https://doi.org/10.1109/ACCESS.2019.2893269.
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023). Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4015–4026. DOI: https://arxiv.org/abs/2304.02643.
Laborte, A. G., Gutierrez, M. A., Balanza, J. G., Saito, K., Zwart, S. J., Boschetti, M., Murty, M., Villano, L., Aunario, J. K., Reinke, R., et al. (2017). Riceatlas, a spatial database of global rice calendars and production. Scientific data, 4(1):1–10. DOI: https://doi.org/10.1038/sdata.2017.74.
Li, Q., Wang, C., Zhang, B., and Lu, L. (2015). Object-based crop classification with landsat-modis enhanced time-series data. Remote Sensing, 7(12):16091–16107. DOI: https://doi.org/10.3390/rs71215820.
Li, Z., Zhang, H. K., Roy, D. P., Yan, L., Huang, H., and Li, J. (2017). Landsat 15-m panchromatic-assisted downscaling (lpad) of the 30-m reflective wavelength bands to sentinel-2 20-m resolution. Remote Sensing, 9(7):755. DOI: https://doi.org/10.3390/rs9070755.
Lobell, D. B., Burke, M. B., Tebaldi, C., Mastrandrea, M. D., Falcon, W. P., and Naylor, R. L. (2008). Prioritizing climate change adaptation needs for food security in 2030. Science, 319(5863):607–610. DOI: https://doi.org/10.1126/science.1152339.
Luo, Z., Yang, W., Yuan, Y., Gou, R., and Li, X. (2023). Semantic segmentation of agricultural images: A survey. Information Processing in Agriculture. DOI: https://doi.org/10.1016/j.inpa.2023.02.001.
Macarini, D. S., Vieira, A. C. P., Zilli, J. C., and Bruch, K. L. (2019). As cultivares plantadas por pequenos produtores: inovação na cadeia orizícola no sul de Santa Catarina. Revista de Propriedade Intelectual, Direito Contemporâneo e Constituição, 13(1):200–219. DOI: http://hdl.handle.net/10183/194759.
MapBiomas (2023). Mapbiomas general “handbook”: Algorithm theoretical basis document (atbd). Website. Available: [link]. Access: 03 may 2024.
Masoud, K. M., Persello, C., and Tolpekin, V. A. (2019). Delineation of agricultural field boundaries from sentinel-2 images using a novel super-resolution contour detector based on fully convolutional networks. Remote sensing, 12(1):59. DOI: https://doi.org/10.3390/rs12010059.
Meng, S., Wang, X., Hu, X., Luo, C., and Zhong, Y. (2021). Deep learning-based crop mapping in the cloudy season using one-shot hyperspectral satellite imagery. Computers and Electronics in Agriculture, 186:106188. DOI: https://doi.org/10.1016/j.compag.2021.106188.
Orynbaikyzy, A., Gessner, U., and Conrad, C. (2022). Spatial transferability of random forest models for crop type classification using sentinel-1 and sentinel-2. Remote Sensing, 14(6):1493. DOI: https://doi.org/10.3390/rs14061493.
Osco, L. P., Wu, Q., Lemos, E. L., Gonçalves, W. N., Ramos, A. P. M., Li, J., and Marcato Junior, J.
(2023). The segment anything model (sam) for remote sensing applications: From zero to one shot. International Journal of Applied Earth Observation and Geoinformation, 124(1):103540. DOI: https://doi.org/10.1016/j.jag.2023.103540.
Oshiro, T. M., Perez, P. S., and Baranauskas, J. A. (2012). How many trees in a random forest? In Machine Learning and Data Mining in Pattern Recognition: 8th International Conference, MLDM 2012, Berlin, Germany, July 13-20, 2012. Proceedings 8, pages 154–168. Springer. DOI: https://doi.org/10.1007/978-3-642-31537-4_13.
Padua, L., Marques, P., Dinis, L.-T., Moutinho-Pereira, J., Sousa, J. J., Morais, R., and Peres, E. (2024). Detection of leak areas in vineyard irrigation systems using uav-based data. Drones, 8(5):187. DOI: https://doi.org/10.3390/drones8050187.
Prudente, V. H. R., Martins, V. S., Vieira, D. C., e Silva, N. R. d. F., Adami, M., and Sanches, I. D. (2020). Limitations of cloud cover for optical remote sensing of agricultural areas across South America. Remote Sensing Applications: Society and Environment, 20:100414. DOI: https://doi.org/10.1016/j.rsase.2020.100414.
Reyes, F., Casa, R., Tolomio, M., Dalponte, M., and Mzid, N. (2023). Soil properties zoning of agricultural fields based on a climate-driven spatial clustering of remote sensing time series data. European Journal of Agronomy, 150:126930. DOI: https://doi.org/10.1016/j.eja.2023.126930.
Segarra, J., Buchaillot, M. L., Araus, J. L., and Kefauver, S. C. (2020). Remote sensing for precision agriculture: Sentinel-2 improved features and applications. Agronomy, 10(5):641. DOI: https://doi.org/10.3390/agronomy10050641.
Shimabukuro, Y. E., Arai, E., da Silva, G. M., Hoffmann, T. B., Duarte, V., Martini, P. R., Dutra, A. C., Mataveli, G., Cassol, H. L., and Adami, M. (2023). Mapping land use and land cover classes in são paulo state, southeast of brazil, using landsat-8 oli multispectral data and the derived spectral indices and fraction images. Forests, 14(8):1669. DOI: https://doi.org/10.3390/f14081669.
Stoy, P. C., Khan, A. M., Wipf, A., Silverman, N., and Powell, S. L. (2022). The spatial variability of ndvi within a wheat field: Information content and implications for yield and grain protein monitoring. PloS one, 17(3):e0265243. DOI: https://doi.org/10.1371/journal.pone.0265243.
Tang, Z., Wang, H., Li, X., Li, X., Cai, W., and Han, C. (2020). An object-based approach for mapping crop coverage using multiscale weighted and machine learning methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13:1700–1713. DOI: https://doi.org/10.1109/JSTARS.2020.2983439.
Traore, S., Fipps, G., Swanson, C., Dufek, J., and Robin, M. (2022). Unmanned aerial vehicle system integrating high-resolution sensors for detecting leaks in irrigation canals—proof of concept. Irrigation and Drainage, 71(1):206–217. DOI: https://doi.org/10.1002/ird.2641.
Vernertti, V. P., Vernetti, F. d. J., and Silveira Junior, P. (1982). Efeito de bordadura lateral e de extremidades de fileiras, sob dois níveis de nitrogênio, em quatro cultivares de arroz na região sudeste do Rio Grande do Sul, Brasil. Pesquisa Agropecuária Brasileira, 17(2):185–194. DOI: https://seer.sct.embrapa.br/index.php/pab/article/view/15588.
Waldner, F. and Diakogiannis, F. I. (2020). Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote sensing of environment, 245:111741. DOI: https://doi.org/10.1016/j.rse.2020.111741.
Wang, K., Zhou, H., Wang, B., Jian, Z., Wang, F., Huang, J., Nie, L., Cui, K., and Peng, S. (2013). Quantification of border effect on grain yield measurement of hybrid rice. Field Crops Research, 141:47–54. DOI: https://doi.org/10.1016/j.fcr.2012.11.012.
Watkins, B. and Van Niekerk, A. (2019). A comparison of object-based image analysis approaches for field boundary delineation using multi-temporal sentinel-2 imagery. Computers and Electronics in Agriculture, 158:294–302. DOI: https://doi.org/10.1016/j.compag.2019.02.009.
Wen, C., Lu, M., Bi, Y., Zhang, S., Xue, B., Zhang, M., Zhou, Q., and Wu, W. (2022). An object-based genetic programming approach for cropland field extraction. Remote Sensing, 14(5):1275. DOI: https://doi.org/10.3390/rs14051275.
Wrege, M, S., Steinmetz, S., Reisser Junior, C., Rodrigues de Almeida, I., Garrastazu, M. C., Herter, F. G., Caramori, P. H., Matzenauer, R., Radin, B., Braga, H. J., Pandolfo, C., Prestes, S. D., Rocca da Cunha, G., and Maluf, J. R. T. (2012). Atlas climático da região sul do Brasil: estados do Paraná, Santa Catarina e Rio Grande do Sul, institution = Empresa Brasileira de Pesquisa Agropecuária - Embrapa. Technical report, EMBRAPA.
Wu, Q. and Osco, L. (2023a). Segment-geospatial: samgeo module. Available: [link]. Access: 01 may 2024.
Wu, Q. and Osco, L. P. (2023b). samgeo: A python package for segmenting geospatial data with the segment any-thing model (sam). Journal of Open Source Software, 8(89):5663. DOI: https://doi.org/10.21105/joss.05663.
Xiao, W., Xu, S., and He, T. (2021). Mapping paddy rice with sentinel-1/2 and phenology-, object-based algorithm—a implementation in hangjiahu plain in china using gee platform. Remote Sensing, 13(5):990. DOI: https://doi.org/10.3390/rs13050990.
Xue, Y., Zhao, J., and Zhang, M. (2021). A watershed-segmentation-based improved algorithm for extracting cultivated land boundaries. Remote Sensing, 13(5):939. DOI: https://doi.org/10.3390/rs13050939.
Zhang, M., Lin, H., Wang, G., Sun, H., and Fu, J. (2018a). Mapping Paddy Rice Using a Convolutional Neural Network (CNN) with Landsat 8 Datasets in the Dongting Lake Area, China. Remote Sensing, 10(11):2072–4292. DOI: https://doi.org/10.3390/rs10111840.
Zhang, X., Wang, Y., Zhang, N., Xu, D., and Chen, B. (2019). Research on scene classification method of high-resolution remote sensing images based on rfpnet. Applied Sciences, 9(10):2028. DOI: https://doi.org/10.3390/app9102028.
Zhang, X., Wu, B., Ponce-Campos, G. E., Zhang, M., Chang, S., and Tian, F. (2018b). Mapping up-to-date paddy rice extent at 10 m resolution in china through the integration of optical and synthetic aperture radar images. Remote Sensing, 10(8):1200. DOI: https://doi.org/10.3390/rs10081200.
Zheng, C., Wang, Y.-c., Xu, W.-b., Yang, D.-s., Yang, G.-d., Yang, C., Huang, J.-l., and Peng, S.-b. (2023). Border effects of the main and ratoon crops in the rice ratooning system. Journal of Integrative Agriculture, 22(1):80–91. DOI: https://doi.org/10.1016/j.jia.2022.08.048.
