Método de identificación de cultivos mediante el análisis masivo multitemporal de imágenes multiespectrales de satélite

Resumen

-Motivación- La detección de cultivos mediante imágenes de satélite ha experimentado un gran auge en los últimos años, debido principalmente a dos factores: por un lado, las nuevas misiones satelitales; y, por otro lado, la popularización de sistemas de aprendizaje máquina aplicados a la monitorización de cultivos. En trabajos relacionados se pueden apreciar propuestas referidas a la detección de cultivos, pero que se centran en cultivos, regiones o técnicas concretas. La literatura carece de una metodología completa que permita implementar un sistema de identificación de cultivos desde cero, y que pueda adaptarse de manera concreta a las necesidades de cada proyecto. -Propuesta- Esta tesis doctoral propone un método completo de identificación de cultivos, haciendo uso de imágenes de satélite multiespectrales, y realizando el análisis de las imágenes a lo largo del tiempo. El método comprende una serie de fases y recomendaciones. El método propone cómo seleccionar y estandarizar la información de los recintos agrícolas que se desea analizar. Posteriormente, tiene lugar la descarga de imágenes, y el etiquetado, selección y filtrado de datos. Desde estos datos, el método propone la generación de imágenes sintéticas multitemporales y multiespectrales para el aprendizaje, y todas las cuestiones relacionadas con el diseño del sistema. Finalmente, la propuesta incluye un método específico para determinar el periodo de detección adecuado de los cultivos. El resultado de aplicar el método consiste en un sistema software completo para la identificación de cultivos. Este trabajo incluye también un caso de uso para probar su aplicabilidad a un proyecto real. -Conclusiones- La principal contribución de este trabajo es un método que describe los procedimientos y técnicas para desarrollar un sistema de análisis de cultivos usando imágenes satelitales. El ámbito de aplicación es óptimo para grandes extensiones de terreno, y con un número elevado de recintos, por lo que se denomina de tratamiento masivo. Además, se basa en el análisis múltiple de imágenes de cada recinto para considerar su evolución en el tiempo, por lo que también se le denomina multitemporal. -Bibliografía- [1] IGN, Teledetección. https://www.ign.es/web/resources/docs/IGNCnig/OBSTeledeteccion.pdf. [2] ESA, ¿qué es la teledetección?. https://www.esa.int/SPECIALS/Eduspace_ES/SEMO1U3FEXF_0.html. [3] NASA History Division, Sputnik and the dawn of the space age. https://history.nasa.gov/sputnik.html. [4] E. D. A. Inc., Teledetección satelital: Tipos, usos y aplicaciones. https://eos.com/es/blog/teledeteccion/, 2021. [5] IGN, Plan nacional de teledetección. aplicaciones. https://pnt.ign.es/aplicaciones. [6] IGN, Plan nacional de teledetección. https://pnt.ign.es. [7] NASA, Landsat 1. https://landsat.gsfc.nasa.gov/satellites/landsat-1/. [8] J. L. Engvall, J. D. Tubbs, and Q. A. Holmes, Pattern recognition of landsat data based upon temporal trend analysis, Remote Sensing of Environment, vol. 6, no. 4, pp. 303-314, 1977. [9] D. Alonso, 50 aplicaciones de la teledetección. https://mappinggis.com/2018/10/50-aplicaciones-de-lateledeteccion/. [10] Instituto Andaluz de Investigación y Formación agraria, pesquera, alimentaria y de la producción ecológica, Teledetección para la agricultura. https://www.juntadeandalucia.es/agriculturaypesca/ifapa/servifapa/registroservifapa/bdac6055-21a9-4dd7-8cba-06a3e9d67873/download. [11] Copernicus, Sentinel-2. https://sentinels.copernicus.eu/web/sentinel/missions/sentinel2. [12] Copernicus, Copernicus web page. https://www.copernicus.eu/es. [13] M. Racic, K. Ostir, D. Peressutti, A. Zupanc, and L. C. Zajc, Application of temporal convolutional neural network for the classification of crops on sentinel-2 time series, vol. 43, pp. 1337-1342, International Society for Photogrammetry and Remote Sensing, 2020. [14] Y. Zhai, N. Wang, L. Zhang, L. Hao, and C. Hao, Automatic crop classification in northeastern china by improved nonlinear dimensionality reduction for satellite image time series, Remote Sensing, vol. 12, no. 17, p. 2726, 2020. [15] S. Siachalou, G. Mallinis, and M. Tsakiri-Strati, A hidden markov models approach for crop classification: Linking crop phenology to time series of multi-sensor remote sensing data, Remote Sensing, vol. 7, no. 4, pp. 3633-3650, 2015. [16] L. García-Torres, J. J. Caballero-Novella, D. Gómez-Candón, and J. M. Peña, Census parcels cropping system classification from multitemporal remote imagery: A proposed universal methodology, PLoS ONE, vol. 10, no. 2, 2015. [17] Q. Hu, D. Sulla-Menashe, B. Xu, H. Yin, H. Tang, P. Yang, and W. Wu, A phenology-based spectral and temporal feature selection method for crop mapping from satellite time series, International Journal of Applied Earth Observation and Geoinformation, vol. 80, pp. 218-229, 2019. [18] K. Jia, B. Wu, and Q. Li, Crop classification using hj satellite multispectral data in the north china plain, Journal of Applied Remote Sensing, vol. 7, no. 1, 2013. [19] X. Zhang, M. Zhang, Y. Zheng, and B. Wu, Crop mapping using proba-v time series data at the yucheng and hongxing farm in china, Remote Sensing, vol. 8, no. 11, p. 915, 2016. [20] S. Siachalou, G. Mallinis, and M. Tsakiri-Strati, Analysis of timeseries spectral index data to enhance crop identification over a mediterranean rural landscape, IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 9, pp. 1508-1512, 2017. [21] Z. Li, G. Chen, and T. Zhang, Temporal attention networks for multitemporal multisensor crop classification, IEEE Access, vol. 7, pp. 134677-134690, 2019. [22] G. Ghazaryan, O. Dubovyk, F. Löw, M. Lavreniuk, A. Kolotii, J. Schellberg, and N. Kussul, A rule-based approach for crop identification using multi-temporal and multi-sensor phenological metrics, European Journal of Remote Sensing, vol. 51, no. 1, pp. 511-524, 2018. [23] H. Snevajs, K. Charvat, V. Onckelet, J. Kvapil, F. Zadrazil, H. Kubickova, J. Seidlova, and I. Bartlova, Crop detection using time series of sentinel-2 and sentinel-1 and existing land parcel information systems, Remote Sensing, vol. 14, no. 5, p. 1095, 2022. [24] N. Addimando, M. Engel, F. Schwarz, and M. Batic, A deep learning approach for crop type mapping based on combined time series of satellite and weather data, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 43, no. B3, pp. 1301-1308, 2022. [25] D. J. Lary, A. H. Alavi, A. H. Gandomi, and A. L. Walker, Machine learning in geosciences and remote sensing, Geoscience Frontiers, vol. 7, no. 1, p. 3-10, 2016. [26] K. Schulz, R. Hänsch, and U. Sörgel, Machine learning methods for remote sensing applications: an overview, Earth Resources and Environmental Remote Sensing / GIS Applications IX, 10 2018. [27] A. Sharma, A. Jain, P. Gupta, and V. Chowdary, Machine learning applications for precision agriculture: A comprehensive review, IEEE Access, vol. 9, pp. 4843-4873, 2021. [28] W. Devos, G. Lemoine, P. Milenov, D. Fasbender, P. Loudjani, C. Wirnhardt, A. Sima, and P. Griffiths, Second discussion document on the introduction of monitoring to substitute otsc: rules for processing application in 2018-2019, Publications Office of the European Union, Luxembourg, 2018. [29] F. Nègre, La financiación de la pac. https://www.europarl.europa.eu/factsheets/es/sheet/106/lafinanciacion-de-la-pac, 2022. [30] European Comission, The common agricultural policy at a glance. https://agriculture.ec.europa.eu/commonagricultural-policy/cap-overview/cap-glance_en. [31] Q. Zheng, W. Huang, X. Cui, Y. Shi, and L. Liu, New spectral index for detecting wheat yellow rust using sentinel-2 multispectral imagery, Sensors, vol. 18, no. 3, p. 868, 2018. [32] H. Zhang, J. Kang, X. Xu, and L. Zhang, 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, vol. 176, p. 105618, 2020. [33] F. Pucha, Lista de índices espectrales en sentinel 2 y landsat. https://acolita.com/lista-de-indices-espectralesen-sentinel-2-y-landsat/, 2019. [34] J. Xue and B. Su, Significant remote sensing vegetation indices: A review of developments and applications, Journal of Sensors, vol. 2017, pp. 1-17, 2017. [35] ESA, Snap. https://earth.esa.int/eogateway/tools/snap. [36] P. Hao, L. Wang, Y. Zhan, C. Wang, Z. Niu, and M. Wu, Crop classification using crop knowledge of the previous-year: Case study in southwest kansas, usa, European Journal of Remote Sensing, vol. 49, pp. 1061-1077, 2016. [37] A. Htitiou, A. Boudhar, Y. Lebrini, R. Hadria, H. Lionboui, and T. Benabdelouahab, A comparative analysis of different phenological information retrieved from sentinel-2 time series images to improve crop classification: a machine learning approach, Geocarto International, vol. 37, no. 5, pp. 1426-1449, 2020. [38] Z. Li, G. Chen, and T. Zhang, A cnn-transformer hybrid approach for crop classification using multitemporal multisensor images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 847-858, 2020. [39] U. Rauf, W. S. Qureshi, H. Jabbar, A. Zeb, A. Mirza, E. Alanazi, U. S. Khan, and N. Rashid, A new method for pixel classification for rice variety identification using spectral and time series data from sentinel-2 satellite imagery, Computers and Electronics in Agriculture, vol. 193, p. 106731, 2022. [40] L. Yin, N. You, G. Zhang, J. Huang, and J. Dong, Optimizing feature selection of individual crop types for improved crop mapping, Remote Sensing, vol. 12, no. 1, p. 162, 2020. [41] L. Viskovic, I. N. Kosovic, and T. Mastelic, Crop classification using multi-spectral and multitemporal satellite imagery with machine learning, Institute of Electrical and Electronics Engineers Inc., 2019. [42] J. Yao, J. Wu, C. Xiao, Z. Zhang, and J. Li, The classification method study of crops remote sensing with deep learning, machine learning, and google earth engine, Remote Sensing, vol. 14, no. 12, p. 2758, 2022. [43] Y. Li, Q. Shi, L. He, R. Cai, L. Meng, J. Li, and A. Plaza, Fusing sentinel-2 and landsat-8 surface reflectance data via pixel-wise local normalization, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 7359-7374, 2022. [44] J. Fan, X. Zhang, C. Zhao, Z. Qin, M. D. Vroey, and P. Defourny, Evaluation of crop type classification with different high resolution satellite data sources, Remote Sensing, vol. 13, no. 5, pp. 1-17, 2021. [45] Copernicus, Level-2a algorithm overview. https://sentinels.copernicus.eu/web/sentinel/technical-guides/sentinel-2-msi/level-2a/algorithm. [46] EO Research, Cloud masks at your service. https://medium.com/sentinel-hub/cloud-masks-at-yourservice-6e5b2cb2ce8a, 2020. [47] N. You and J. Dong, Examining earliest identifiable timing of crops using all available sentinel 1/2 imagery and google earth engine, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 161, pp. 109-123, 2020. [48] S.-H. Kim and J. Eun, Development of cloud and shadow detection algorithm for periodic composite of sentinel-2a/b satellite images, Korean Journal of Remote Sensing, vol. 37, no. 5, pp. 989-998, 2021. [49] J. D. Braaten, W. B. Cohen, and Z. Yang, Automated cloud and cloud shadow identification in landsat mss imagery for temperate ecosystems, Remote Sensing of Environment, vol. 169, pp. 128-138, 2015. [50] M. Czerkawski, P. Upadhyay, C. Davison, A. Werkmeister, J. Cardona, R. Atkinson, C. Michie, I. Andonovic, M. Macdonald, and C. Tachtatzis, Deep internal learning for inpainting of cloud-affected regions in satellite imagery, Remote Sensing, vol. 14, no. 6, p. 1342, 2022. [51] A. Hollstein, K. Segl, L. Guanter, M. Brell, and M. Enesco, Ready-to-use methods for the detection of clouds, cirrus, snow, shadow, water and clear sky pixels in sentinel-2 msi images, Remote Sensing, vol. 8, no. 8, p. 666, 2016. [52] R. K. Pearson, Y. Neuvo, J. Astola, and M. Gabbouj, Generalized hampel filters, EURASIP Journal on Advances in Signal Processing, vol. 2016, no. 1, p. 87, 2016. [53] I. Arslan, M. Topakci, and N. Demir, Monitoring maize growth and calculating plant heights with synthetic aperture radar (sar) and optical satellite images, Agriculture, vol. 12, no. 6, p. 800, 2022. [54] B. Tuvdendorj, H. Zeng, B. Wu, A. Elnashar, M. Zhang, F. Tian, M. Nabil, L. Nanzad, A. Bulkhbai, and N. Natsagdorj, Performance and the optimal integration of sentinel-1/2 time-series features for crop classification in northern mongolia, Remote Sensing, vol. 14, no. 8, p. 1830, 2022. [55] F. Kordi and H. Yousefi, Crop classification based on phenology information by using time series of optical and synthetic-aperture radar images, Remote Sensing Applications: Society and Environment, vol. 27, p. 100812, 2022. [56] S. Valero, C. Pelletier, and M. Bertolino, Patch-based reconstruction of high resolution satellite image time series with missing values using spatial, spectral and temporal similarities, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016. [57] F. Mouret, M. Albughdadi, S. Duthoit, D. Kouamé, G. Rieu, and J. Y. Tourneret, Reconstruction of sentinel-2 derived time series using robust gaussian mixture models ¿ application to the detection of anomalous crop development, Computers and Electronics in Agriculture, vol. 198, p. 106983, 7 2022. [58] L. E. Christovam, M. H. Shimabukuro, M. De, L. B. T. Galo, and E. Honkavaara, Pix2pix conditional generative adversarial network with mlp loss function for cloud removal in a cropland time series, Remote Sensing, vol. 14, no. 1, p. 144, 2021. [59] K. K. Gadiraju, B. Ramachandra, Z. Chen, R. R. Vatsavai, and A. C. M. S. A. C. M. SIGMOD, Multimodal deep learning based crop classification using multispectral and multitemporal satellite imagery, pp. 3234-3242, Association for Computing Machinery, 2020. [60] Z. Li, G. Zhou, and T. Zhang, Interleaved group convolutions for multitemporal multisensor crop classification, Infrared Physics and Technology, vol. 102, 2019. [61] Y. Wang, Z. Zhang, L. Feng, Y. Ma, and Q. Du, A new attentionbased cnn approach for crop mapping using time series sentinel-2 images, Computers and Electronics in Agriculture, vol. 184, p. 106090, 2021. [62] C. Boryan, Z. Yang, R. Mueller, and M. Craig, Monitoring us agriculture: the us department of agriculture, national agricultural statistics service, cropland data layer program, Geocarto International, vol. 26, pp. 341-358, 8 2011. [63] M. O. Turkoglu, S. D¿Aronco, G. Perich, F. Liebisch, C. Streit, K. Schindler, and J. D. Wegner, Crop mapping from image time series: Deep learning with multi-scale label hierarchies, Remote Sensing of Environment, vol. 264, 2021. [64] A. Moumni, B. Sebbar, V. Simonneaux, J. Ezzahar, A. Lahrouni, and T. S. of Photo-Optical Instrumentation Engineers (SPIE), Sample period dependent classification approach for the cartography of crops in the haouz plain, morocco, vol. 11149, SPIE, 2019. [65] A. Masse, D. Ducrot, and P. Marthon, Tools for multitemporal analysis and classification of multisource satellite imagery, 2011 6th International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, pp. 209-212, 2011. [66] T. G. V. Niel and T. R. McVicar, Determining temporal Windows for crop discrimination with remote sensing: A case study in southeastern australia, Computers and Electronics in Agriculture, vol. 45, no. 1-3, pp. 91-108, 2004. [67] H. Carrao, P. Gonçalves, and M. Caetano, Contribution of multispectral and multitemporal information from modis images to land cover classification, Remote Sensing of Environment, vol. 112, no. 3, pp. 986-997, 2007. [68] D. Zhang, S. Fang, B. She, H. Zhang, N. Jin, H. Xia, Y. Yang, and Y. Ding, Winter wheat mapping based on sentinel-2 data in heterogeneous planting conditions, Remote Sensing, vol. 11, no. 22, p. 2647, 2019. [69] P. Fang, X. Zhang, P. Wei, Y. Wang, H. Zhang, F. Liu, and J. Zhao, The classification performance and mechanism of machine learning algorithms in winter wheat mapping using sentinel-2 10 m resolution imagery, Applied Sciences, vol. 10, no. 15, p. 5075, 2020. [70] C. Sun, Y. Bian, T. Zhou, and J. Pan, Using of multi-source and multi-temporal remote sensing data improves crop-type mapping in the subtropical agriculture region, Sensors, vol. 19, no. 10, p. 2401, 2019. [71] B. Chen, H. Zheng, L. Wang, O. Hellwich, C. Chen, L. Yang, T. Liu, G. Luo, A. Bao, and X. Chen, A joint learning im-bilstm model for incomplete time-series sentinel-2a data imputation and crop classification, International Journal of Applied Earth Observation and Geoinformation, vol. 108, 4 2022. [72] Z. Ma, Z. Liu, Y. Zhao, L. Zhang, D. Liu, T. Ren, X. Zhang, and S. Li, An unsupervised crop classification method based on principal components isometric binning, ISPRS International Journal of Geo- Information, vol. 9, no. 11, p. 648, 2020. [73] M. A. Peña, R. Liao, and A. Brenning, Using spectrotemporal índices to improve the fruit-tree crop classification accuracy, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 128, pp. 158-169, 2017. [74] S. Mangiarotti, A. K. Sharma, S. Corgne, L. Hubert-Moy, L. Ruiz, M. Sekhar, and Y. Kerr, Can the global modeling technique be used for crop classification?, Chaos, Solitons and Fractals, vol. 106, pp. 363-378, 2018. [75] L. A. Ruiz, J. Almonacid-Caballer, P. Crespo-Peremarch, J. A. Recio, J. E. Pardo-Pascual, and E. Sánchez-García, Automated classification of crop types and condition in a mediterranean area using a fine-tuned convolutional neural network, vol. 43, pp. 1061-1068, International Society for Photogrammetry and Remote Sensing, 2020. [76] A. Moumni, M. Oujaoura, J. Ezzahar, and A. Lahrouni, A new synergistic approach for crop discrimination in a semi-arid región using sentinel-2 time series and the multiple combination of machine learning classifiers, vol. 1743, p. 012026, IOP Publishing Ltd, 2021. [77] U. Kanjir, N. Duric, and T. Veljanovski, Sentinel-2 based temporal detection of agricultural land use anomalies in support of common agricultural policy monitoring, ISPRS International Journal of Geo-Information, vol. 7, no. 10, p. 405, 2018. [78] M. A. Peña and A. Brenning, Assessing fruit-tree crop classification from landsat-8 time series for the maipo valley, chile, Remote Sensing of Environment, vol. 171, pp. 234-244, 2015. [79] P. Benevides, H. Costa, F. D. Moreira, D. Moraes, M. Caetano, T. I. of Electrical, E. E. Geoscience, and R. S. S. (GRSS), Annual crop classification experiments in portugal using sentinel-2, pp. 5838- 5841, Institute of Electrical and Electronics Engineers Inc., 2021. [80] V. Saxena, R. K. Dwivedi, A. Kumar, and iNurture Education Solutions Private Limited; Teerthanker Mahaveer University, Analysis of machine learning algorithms for crop mapping on satellite image data, pp. 23-28, Institute of Electrical and Electronics Engineers Inc., 2021. [81] S. Jing and T. Chao, Time series land cover classification based on semi-supervised convolutional long short-term memory neural networks, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciencese, vol. 43, no. B2, pp. 1521- 1528, 2020. [82] M. K. Dhodhi, J. A. Saghri, I. Ahmad, and R. Ul-Mustafa, Disodata: A distributed algorithm for unsupervised classification of remotely sensed data on network of workstations, Journal of Parallel and Distributed Computing, vol. 59, pp. 280-301, 11 1999. [83] A. J. Rivera, M. D. Pérez-Godoy, D. Elizondo, L. Deka, and M. J. del Jesus, A preliminary study on crop classification with unsupervised algorithms for time series on images with olive trees and cereal crops, Advances in Intelligent Systems and Computing, vol. 1268, pp. 276-285, 2021. [84] X. Wang, J. Zhang, L. Xun, J. Wang, Z. Wu, M. Henchiri, S. Zhang, S. Zhang, Y. Bai, S. Yang, S. Li, and X. Yu, Evaluating the effectiveness of machine learning and deep learning models combined time-series satellite data for multiple crop types classification over a large-scale region, Remote Sensing, vol. 14, no. 10, p. 2341, 2022. [85] K. Tatsumi, Y. Yamashiki, M. A. C. Torres, and C. L. R. Taipe, Crop classification of upland fields using random forest of time-series landsat 7 etm+ data, Computers and Electronics in Agriculture, vol. 115, pp. 171-179, 2015. [86] A. Khobragade, P. Athawale, and M. Raguwanshi, Optimization of statistical learning algorithm for crop discrimination using remote sensing data. 2015. [87] L. Yang, L. R. Mansaray, J. Huang, and L. Wang, Optimal segmentation scale parameter, feature subset and classification algorithm for geographic object-based crop recognition using multisource satellite imagery, Remote Sensing, vol. 11, no. 5, p. 514, 2019. [88] J. Pluto-Kossakowska, Review on multitemporal classification methods of satellite images for crop and arable land recognition, Agriculture, vol. 11, no. 10, 2021. [89] A. Li, S. Liang, A. Wang, and J. Qin, Estimating crop yield from multi-temporal satellite data using multivariate regression and neural network techniques, Photogrammetric Engineering and Remote Sensing, vol. 73, no. 10, pp. 1149-1157, 2007. [90] D. Wang, W. Cao, F. Zhang, Z. Li, S. Xu, and X. Wu, A review of deep learning in multiscale agricultural sensing, Remote Sensing, vol. 60, pp. 1-16, 2022. [91] S. Yang, L. Gu, X. Li, F. Gao, and T. Jiang, Fully automated classification method for crops based on spatiotemporal deep-learning fusion technology, IEEE Transactions On Geoscience And Remote Sensing, vol. 60, pp. 1-16, 2022. [92] M. Y. Moreno-Revelo, L. Guachi-Guachi, J. B. Gómez-Mendoza, J. Revelo-Fuelagán, and D. H. Peluffo-Ordóñez, Enhanced convolutional-neural-network architecture for crop classification, Applied Sciences, vol. 11, no. 9, p. 4192, 2021. [93] J. M. Haut, A. Alcolea, M. E. Paoletti, J. Plaza, J. Resano, and A. Plaza, Gpu-friendly neural networks for remote sensing scene classification, IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022. [94] X. X. Zhu, D. Tuia, L. Mou, G.-S. Xia, L. Zhang, F. Xu, and F. Fraundorfer, Deep learning in remote sensing: A comprehensive review and list of resources, IEEE Geoscience and Remote Sensing Magazine, vol. 5, no. 4, pp. 8-36, 2017. [95] X. Jia, A. Khandelwal, D. J. Mulla, P. G. Pardey, and V. Kumar, Bringing automated, remote-sensed, machine learning methods to monitoring crop landscapes at scale, Agricultural Economics, vol. 50, no. S1, pp. 41-50, 2019. [96] B. She, Y. Yang, Z. Zhao, L. Huang, D. Liang, and D. Zhang, Identification and mapping of soybean and maize crops based on sentinel-2 data, International Journal of Agricultural and Biological Engineering, vol. 13, no. 6, pp. 171-182, 2020. [97] J. B. Castro, R. Q. Feitosa, L. C. L. Rosa, P. A. Diaz, and I. Sanches, A comparative analysis of deep learning techniques for subtropical crop types recognition from multitemporal optical/sar image sequences; a comparative analysis of deep learning techniques for sub-tropical crop types recognition from multitemporal optical/sar image sequences, 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2017. [98] S. Yang, L. Gu, X. Li, T. Jiang, and R. Ren, Crop classification method based on optimal feature selection and hybrid cnn-rf networks for multi-temporal remote sensing imagery, Remote Sensing, vol. 12, no. 19, p. 3119, 2020. [99] V. Mazzia, A. Khaliq, and M. Chiaberge, Improvement in land cover and crop classification based on temporal features learning from sentinel-2 data using recurrent-convolutional neural network (rcnn), Applied Sciences, vol. 10, no. 1, p. 238, 2020. [100] G. S. Phartiyal and D. Singh, Comparative study on deep neural network models for crop classification using time series polsar and optical data, vol. 42, pp. 675-681, International Society for Photogrammetry and Remote Sensing, 2018. [101] A. Morales, Los 10 formatos gis vectoriales más populares. https://mappinggis.com/2013/11/los-formatosgis-vectoriales-mas-populares. [102] A. Lozano-Tello, M. Fernández-Sellers, E. Quirós, L. Fragoso-Campón, A. García-Martín, J. A. G. Gallego, C. Mateos, R. Trenado, and P. Muñoz, Crop identification by massive processing of multiannual satellite imagery for eu common agriculture policy subsidy control, European Journal of Remote Sensing, vol. 54, no. 1, pp. 1-12, 2021. [103] G. Siesto, M. Fernández-Sellers, A. Lozano-Tello, Crop classification of satellite imagery using synthetic multitemporal and multispectral images in convolutional neural networks, Remote Sensing, vol. 13, p. 3378, 8 2021. [104] M. Claesen and B. D. Moor, Hyperparameter search in machine learning. https://arxiv.org/pdf/1502.02127.pdf, 2015. [105] J. T. Tsai, J. H. Chou, and T. K. Liu, Tuning the structure and parameters of a neural network by using hybrid taguchi-genetic algo-rithm, IEEE Transactions on Neural Networks, vol. 17, pp. 69-80, 1 2006. [106] J. Bergstra and Y. Bengio, Random search for hyper-parameter optimization yoshua bengio, Journal of Machine Learning Research, vol. 13, pp. 281-305, 2012. [107] D. R. Jones, M. Schonlau, and W. J. Welch, Efficient global optimization of expensive black-box functions, Journal of Global Optimization, vol. 13, no. 4, pp. 455-492, 1998. [108] M. Aach, R. Sedona, A. Lintermann, G. Cavallaro, H. Neukirchen, and M. Riedel, Accelerating hyperparameter tuning of a deep learning model for remote sensing image classification, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2022, pp. 263-266, 2022. [109] G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: with Applications in R. New York: Springer, 2013. [110] M. Fernández-Sellers, G. Siesto, A. Lozano-Tello, and P. J. Clemente, Finding a suitable sensing time period for crop identification using heuristic techniques with multi-temporal satellite images, International Journal of Remote Sensing, vol. 43, no. 15-16, pp. 6038-6055, 2021. [111] S. Russell and P. Norving, Artificial Intelligence: A Modern Approach. Harlow: Pearson, 2022. [112] Y. Sasaki, The truth of the f-measure. https://www.cs.odu.edu/¿mukka/cs795sum09dm/Lecturenotes/Day3/Fmeasure-YS-26Oct07.pdf, 2007. [113] GeoJSON, Geojson web page. https://geojson.org. [114] S. Gillies, M. Russell, C. Farwell, and B. Grotewold, Python-geojson library. https://python-geojson.readthedocs.io. [115] S. Gillies, Shapely library. https://shapely.readthedocs.io. [116] Y. Matsubara, Pymysql. https://pymysql.readthedocs.io. [117] ESA, Copernicus open access hub. https://scihub.copernicus.eu. [118] M. Wille and K. Clauss, Sentinelsat. https://sentinelsat.readthedocs.io. [119] ESA, Sen2cor. https://step.esa.int/main/snapsupported-plugins/sen2cor. [120] A. Schwankner, Esa snap with python. https://github.com/schwankner/esa-snap-with-python. [121] C. R. Harris, K. J. Millman, S. J. van der Walt, R. Gommers, P. Virtanen, D. Cournapeau, E. Wieser, J. Taylor, S. Berg, N. J. Smith, R. Kern, M. Picus, S. Hoyer, M. H. van Kerkwijk, M. Brett, A. Haldane, J. F. del Río, M. Wiebe, P. Peterson, P. Gérard-Marchant, K. Sheppard, T. Reddy, W. Weckesser, H. Abbasi, C. Gohlke, and T. E. Oliphant, Array programming with NumPy, Nature, vol. 585, no. 7825, pp. 357-362, 2020. [122] Wes McKinney, Data Structures for Statistical Computing in Python, in Proceedings of the 9th Python in Science Conference (Stéfan van der Walt and Jarrod Millman, eds.), pp. 56-61, 2010. [123] S. Ioffe and C. Szegedy, Batch normalization: Accelerating Deep network training by reducing internal covariate shift. https://arxiv.org/pdf/1502.03167.pdf, 2015.