Feature-level fusion of Sentinel-1 SAR and Sentinel-2 optical imagery for crop-type mapping in humid tropical mountainous terrain
Article Sidebar
Main Article Content
Abstract
Accurate crop-type mapping in humid tropical mountains is challenged by persistent cloud cover, rugged topography, and fragmented smallholder parcels. This study evaluates a feature-level fusion workflow that integrates Sentinel-2 optical indices and Sentinel-1 SAR backscatter for crop-type mapping in Candipuro District, Lumajang, East Java, Indonesia. Sentinel-2 surface reflectance and Sentinel-1 IW data acquired in June–July 2023 were harmonised in Google Earth Engine to a common 10 m pixel grid, so that all comparison maps were evaluated on the same spatial support. The optical component comprised NDVI, NDBI, and NDWI, whereas the radar component used the VH/VV polarisation ratio. A DEM was used only to characterise the mountainous setting and to assist terrain interpretation, and was not included as a predictor in the classifier. The stacked feature image was classified using a Random Forest model trained with 101 field-survey ground control points representing eight land-cover/crop-related classes. Accuracy was assessed using 393 stratified random validation points. The fused-image classification achieved an overall accuracy of 93% and a kappa coefficient of 0.90. The fusion workflow yielded richer thematic differentiation than the optical-only comparison scenarios, particularly for water bodies, sugarcane, and shrubland. However, class-level results reveal substantial uncertainty for corn fields and moderate confusion in built-up and water classes. Therefore, the present workflow should be interpreted as a site-specific, single-date proof of concept rather than a fully transferable operational solution. The results indicate that Sentinel-1/Sentinel-2 feature fusion is promising for crop-type mapping in cloud-prone mountainous landscapes, while future work should incorporate multi-temporal phenology, richer vegetation indices, SAR texture features, uncertainty mapping, and broader field sampling.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Ofori-Ampofo S, Pelletier C, Lang S. Crop type mapping from optical and radar time series using attention-based deep learning. Remote Sens. 2021;13(22):4668. DOI: https://doi.org/10.3390/rs13224668
Xu Z, Zhou Y, Wang S, Wang L, Li F, Wang S, et al. A novel intelligent classification method for urban green space based on high-resolution remote sensing images. Remote Sens. 2020;12(22):3845. DOI: https://doi.org/10.3390/rs12223845
Kaplan G, Avdan U. Sentinel-1 and Sentinel-2 Data Fusion for Mapping and Monitoring Wetlands [Internet]. Preprints.org [Preprint]. 2018 [cited 2026 May 3]. Available from: https://www.preprints.org/manuscript/201807.0244. DOI: https://doi.org/10.20944/preprints201807.0244.v1
Kaplan G, Avdan U. Object-based water body extraction model using Sentinel-2 satellite imagery. Eur J Remote Sens. 2017;50(1):137-43. DOI: https://doi.org/10.1080/22797254.2017.1297540
Phiri D, Simwanda M, Salekin S, Nyirenda VR, Murayama Y, Ranagalage M. Sentinel-2 data for land cover/use mapping: a review. Remote Sens. 2020;12(14):2291. DOI: https://doi.org/10.3390/rs12142291
Bhumiphan N, Nontapon J, Kaewplang S, Srihanu N, Koedsin W, Huete A. Estimation of rubber yield using Sentinel-2 satellite data. Sustainability. 2023;15(9):7223. DOI: https://doi.org/10.3390/su15097223
Schubert A, Miranda N, Geudtner D, Small D. Sentinel-1A/B combined product geolocation accuracy. Remote Sens. 2017;9(6):607. DOI: https://doi.org/10.3390/rs9060607
Bauer-Marschallinger B, Cao S, Navacchi C, Freeman V, Reuß F, Geudtner D, et al. The normalised Sentinel-1 Global Backscatter Model, mapping Earth’s land surface with C-band microwaves. Sci Data. 2021;8(1):277. DOI: https://doi.org/10.1038/s41597-021-01059-7
Dubrovin K, Stepanov A, Verkhoturov A. Cropland mapping using Sentinel-1 data in the southern part of the Russian Far East. Sensors. 2023;23(18):7902. DOI: https://doi.org/10.3390/s23187902
Qi L, Wang M, Hu C, Holt B. On the capacity of Sentinel-1 synthetic aperture radar in detecting floating macroalgae and other floating matters. Remote Sens Environ. 2022;280:113188. DOI: https://doi.org/10.1016/j.rse.2022.113188
Zhang J. Multi-source remote sensing data fusion: status and trends. Int J Image Data Fusion. 2010;1(1):5-24. DOI: https://doi.org/10.1080/19479830903561035
Zhang J. High-performance data processing for image and data fusion. Int J Image Data Fusion. 2016;7(1):1-2. DOI: https://doi.org/10.1080/19479832.2016.1122697
Kaur H, Koundal D, Kadyan V. Image fusion techniques: a survey. Arch Computat Methods Eng. 2021;28(7):4425-47. DOI: https://doi.org/10.1007/s11831-021-09540-7
Madaan S, Kaur S. A machine learning and deep learning approach for accurate crop-type mapping using Sentinel-1 satellite data. In: Ranganathan G, Papakostas GA, Rocha Á, editors. Inventive Communication and Computational Technologies 2023. Lecture Notes in Networks and Systems, vol 757. Singapore: Springer; 2023. p. 599-611. DOI: https://doi.org/10.1007/978-981-99-5166-6_41
Kaur J, Shekhar C. Multimodal medical image fusion using deep learning. In: Koundal D, Gupta S, editors. Advances in Computational Techniques for Biomedical Image Analysis. London: Academic Press; 2020. p. 35-56. DOI: https://doi.org/10.1016/B978-0-12-820024-7.00002-5
Ma C, Johansen K, McCabe MF. Monitoring irrigation events and crop dynamics using Sentinel-1 and Sentinel-2 time series. Remote Sens. 2022;14(5):1205. DOI: https://doi.org/10.3390/rs14051205
Guo J, Luan Y, Li Z, Liu X, Li C, Chang X. Mozambique flood (2019) caused by tropical cyclone idai monitored from sentinel-1 and sentinel-2 images. IEEE J Sel Top Appl Earth Obs Remote Sens. 2019;14:8761-72. DOI: https://doi.org/10.1109/JSTARS.2021.3107279
Habibie MI, Dayuf Yusuf M, Setyaningrum N, Pianto TA, Nurdiansyah N, Aziz ML. Mapping and monitoring urban areas using Sentinel 1 and Sentinel 2. 2021 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS); 2021 Sep 29-30; Jakarta Pusat, Indonesia. USA: IEEE; 2021. p. 125-9. DOI: https://doi.org/10.1109/AGERS53903.2021.9617263
Wang X, Zhang Y, Zhang K. Automatic 10 m forest cover mapping in 2020 at China’s Han River Basin by fusing ESA Sentinel-1/Sentinel-2 land cover and Sentinel-2 near real-time forest cover possibility. Forests. 2023;14(6):1133. DOI: https://doi.org/10.3390/f14061133
Nguyen TTH, Chau TNQ, Pham TA, Tran TXP, Phan TH, Pham TMT. Mapping Land use/land cover using a combination of Radar Sentinel-1A and Sentinel-2A optical images. IOP Conf Ser: Earth Environ Sci. 2021;652:012021. DOI: https://doi.org/10.1088/1755-1315/652/1/012021
Guisao-Betancur A, Gómez Déniz L, Marulanda-Tobón A. Forest/Nonforest segmentation using Sentinel-1 and -2 data fusion in the Bajo Cauca Subregion in Colombia. Remote Sens. 2024;16(1):5. DOI: https://doi.org/10.3390/rs16010005
Xie G, Niculescu S. Mapping crop types using Sentinel-2 data machine learning and monitoring crop phenology with Sentinel-1 backscatter time series in pays de Brest, Brittany, France. Remote Sens. 2022;14(18):4437. DOI: https://doi.org/10.3390/rs14184437
Sun L, Chen J, Guo S, Deng X, Han Y. Integration of time series sentinel-1 and sentinel-2 imagery for crop type mapping over oasis agricultural areas. Remote Sens. 2020;12(1):158. DOI: https://doi.org/10.3390/rs12010158
Borges J, Higginbottom TP, Symeonakis E, Jones M. Sentinel-1 and Sentinel-2 data for savannah land cover mapping: optimising the combination of sensors and seasons. Remote Sens. 2020;12(23):3862. DOI: https://doi.org/10.3390/rs12233862
Asam S, Gessner U, Almengor González R, Wenzl M, Kriese J, Kuenzer C. Mapping crop types of Germany by combining temporal statistical metrics of Sentinel-1 and Sentinel-2 time series with LPIS data. Remote Sens. 2022;14(13):2981. DOI: https://doi.org/10.3390/rs14132981
Veci L, March I. Sentinel-1 toolbox SAR basics tutorial. Paris: Esa; 2015.
Mandal D, Vaka DS, Bhogapurapu NR, Vanama VSK, Kumar V, Rao YS, et al. Sentinel-1 SLC preprocessing workflow for polarimetric applications: a generic practice for generating dual-pol covariance matrix elements in SNAP S-1 toolbox [Internet]. Preprints.org [Preprint]. 2019 [cited 2025 Jun 13]. Available from: https://www.preprints.org/manuscript/201911.0393. DOI: https://doi.org/10.20944/preprints201911.0393.v1
Braun A, Veci L. Sentinel-1 toolbox SAR basics tutorial. Paris: Esa; 2021.
Ghorbanian A, Zaghian S, Asiyabi RM, Amani M, Mohammadzadeh A, Jamali S. Mangrove ecosystem mapping using sentinel-1 and sentinel-2 satellite images and random forest algorithm in google earth engine. Remote Sens. 2021;13(13):2565. DOI: https://doi.org/10.3390/rs13132565
Wang L, Wang J, Qin F. Feature fusion approach for temporal land use mapping in complex agricultural areas. Remote Sens. 2021;13(13):2517. DOI: https://doi.org/10.3390/rs13132517
Xulu S, Mbatha N, Peerbhay K, Gebreslasie M. Gebreslasie. Detecting harvest events in plantation forest using Sentinel-1 and -2 data via google earth engine. Forests. 2020;11(12):1283. DOI: https://doi.org/10.3390/f11121283
Huang C, Zhang C, He Y, Liu Q, Li H, Su F, et al. Land cover mapping in cloud-prone tropical areas using Sentinel-2 data: integrating spectral features with Ndvi temporal dynamics. Remote Sens. 2020;12(7):1163. DOI: https://doi.org/10.3390/rs12071163
Alademomi AS, Okolie CJ, Daramola OE, Akinnusi SA, Adediran E, Olanrewaju HO, et al. The interrelationship between LST, NDVI, NDBI, and land cover change in a section of Lagos metropolis, Nigeria. Appl Geomat. 2022;14(2):299-314. DOI: https://doi.org/10.1007/s12518-022-00434-2
Keerthi Naidu BN, Chundeli FA. Assessing LULC changes and LST through NDVI and NDBI spatial indicators: a case of Bengaluru, India. GeoJournal. 2023;88(4):4335-50. DOI: https://doi.org/10.1007/s10708-023-10862-1
McFeeters SK. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int J Remote Sens. 1996;17(7):1425-32. DOI: https://doi.org/10.1080/01431169608948714
Jackson TJ, Chen D, Cosh M, Li F, Anderson M, Walthall C, et al. Vegetation water content mapping using Landsat data derived normalized difference water index for corn and soybeans. Remote Sens Environ. 2004;92(4):475-82. DOI: https://doi.org/10.1016/j.rse.2003.10.021
Zhang HK, Roy DP, Yan L, Li Z, Huang H, Vermote E, et al. Characterization of Sentinel-2A and Landsat-8 top of atmosphere, surface, and nadir BRDF adjusted reflectance and NDVI differences. Remote Sens Environ. 2018;215:482-94. DOI: https://doi.org/10.1016/j.rse.2018.04.031
Wu M, Yang C, Song X, Hoffmann WC, Huang W, Niu Z, et al. Monitoring cotton root rot by synthetic Sentinel-2 NDVI time series using improved spatial and temporal data fusion. Sci Rep. 2018;8(1):2016. DOI: https://doi.org/10.1038/s41598-018-20156-z
Manakos I, Kordelas GA, Marini K. Fusion of Sentinel-1 data with Sentinel-2 products to overcome non-favourable atmospheric conditions for the delineation of inundation maps. Eur J Remote Sens. 2020;53(sup2):53-66. DOI: https://doi.org/10.1080/22797254.2019.1596757
Schubert A, Small D, Miranda N, Geudtner D, Meier E. Sentinel-1A product geolocation accuracy: commissioning phase results. Remote Sens. 2015;7(7):9431-49. DOI: https://doi.org/10.3390/rs70709431
Singh S, Kansal ML. Chamoli flash-flood mapping and evaluation with a supervised classifier and NDWI thresholding using Sentinel-2 optical data in google earth engine. Earth Sci Inform. 2022;15(2):1073-86. DOI: https://doi.org/10.1007/s12145-022-00786-8
Sonobe R, Yamaya Y, Tani H, Wang X, Kobayashi N, Mochizuki K. Crop classification from Sentinel-2-derived vegetation indices using ensemble learning. J Appl Remote Sens. 2018;12(2):026019. DOI: https://doi.org/10.1117/1.JRS.12.026019
Dibs H, Hasab HA, Jaber HS, Al-Ansari N. Automatic feature extraction and matching modelling for highly noise near-equatorial satellite images. Innov Infrastruct Solut. 2022;7(1):2. DOI: https://doi.org/10.1007/s41062-021-00598-7
Imani M, Ghassemian H. Feature extraction using weighted training samples. IEEE Geosci Remote Sens Lett. 2015;12(7):1387-91. DOI: https://doi.org/10.1109/LGRS.2015.2402167
Imani M, Ghassemian H. An overview on spectral and spatial information fusion for hyperspectral image classification: current trends and challenges. Inf Fusion. 2020;59:59-83. DOI: https://doi.org/10.1016/j.inffus.2020.01.007
Mahrus I, Indarto I, Wheny K, Fahmi K. Crop type mapping using mavhine learning-based approach and Sentinel-2: study in Lumajang, East Java, Indonesia. INMATEH - Agric Eng. 2024;72(1):129-37. DOI: https://doi.org/10.35633/inmateh-72-12
Forestier G, Inglada J, Wemmert C, Gançarski P. Comparison of optical sensors discrimination ability using spectral libraries. Int J Remote Sens. 2013;34(7):2327-49. DOI: https://doi.org/10.1080/01431161.2012.744488
Li Y, Fang H. Real-time software for the efficient generation of the clumping index and its application based on the google earth engine. Remote Sens. 2022;14(15):3837. DOI: https://doi.org/10.3390/rs14153837
