{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:59:22Z","timestamp":1760151562762,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:00:00Z","timestamp":1648512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42071422"],"award-info":[{"award-number":["42071422"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0706004"],"award-info":[{"award-number":["2018YFC0706004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>NDVI is an important parameter for environmental assessment and precision agriculture that well-describes the status of vegetation. Nevertheless, the clouds in optical images often result in the absence of NDVI information at key growth stages. The integration of SAR and optical image features will likely address this issue. Although the mapping of different data sources is complex, the prosperity of deep learning technology provides an alternative approach. In this study, the double-attention RNN architecture based on the recurrent neural network (RNN) and attention mechanism is proposed to retrieve NDVI data of cloudy regions. Overall, the NDVI is retrieved by the proposed model from two aspects: the temporal domain and the pixel neighbor domain. The performance of the double-attention RNN is validated through different cloud coverage conditions, input ablation, and comparative experiments with various methods. The results conclude that a high retrieval accuracy is guaranteed by the proposed model, even under high cloud coverage conditions (R2 = 0.856, RMSE = 0.124). Using SAR images independently results in poor NDVI retrieval results (R2 = 0.728, RMSE = 0.141) with considerable artifacts, which need to be addressed with auxiliary data, such as IDM features. Temporal and pixel neighbor features play an important role in improving the accuracy of NDVI retrieval (R2 = 0.894, RMSE = 0.096). For the missing values of NDVI data caused by cloud coverage, the double-attention RNN proposed in this study provides a potential solution for information recovery.<\/jats:p>","DOI":"10.3390\/rs14071632","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T21:45:51Z","timestamp":1648590351000},"page":"1632","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An NDVI Retrieval Method Based on a Double-Attention Recurrent Neural Network for Cloudy Regions"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4423-4971","authenticated-orcid":false,"given":"Ran","family":"Jing","sequence":"first","affiliation":[{"name":"School of Geosciences, Yangtze University, Wuhan 430100, China"},{"name":"Engineering Research Center of Spatial Information Technology, MOE, Beijing 100048, China"}]},{"given":"Fuzhou","family":"Duan","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Spatial Information Technology, MOE, Beijing 100048, China"},{"name":"College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, China"}]},{"given":"Fengxian","family":"Lu","sequence":"additional","affiliation":[{"name":"Henan Engineering Research Center of Environmental Laser Remote Sensing Technology and Application, Nanyang 473061, China"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Henan Engineering Research Center of Environmental Laser Remote Sensing Technology and Application, Nanyang 473061, China"}]},{"given":"Wenji","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Alencar, A., Z Shimbo, J., Lenti, F., Balzani Marques, C., Zimbres, B., Rosa, M., Arruda, V., Castro, I., Fernandes M\u00e1rcico Ribeiro, J.P., and Varela, V. (2020). Mapping three decades of changes in the brazilian savanna native vegetation using landsat data processed in the google earth engine platform. Remote Sens., 12.","DOI":"10.3390\/rs12060924"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ye, C., Sun, J., Liu, M., Xiong, J., Zong, N., Hu, J., Huang, Y., Duan, X., and Tsunekawa, A. (2020). Concurrent and lagged effects of extreme drought induce net reduction in vegetation carbon uptake on Tibetan Plateau. Remote Sens., 12.","DOI":"10.3390\/rs12152347"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Qiu, L., Wu, Y., Shi, Z., Chen, Y., and Zhao, F. (2021). Quantifying the responses of evapotranspiration and its components to vegetation restoration and climate change on the Loess plateau of China. Remote Sens., 13.","DOI":"10.3390\/rs13122358"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1080\/01431161.2019.1657603","article-title":"Spatial\u2013temporal changes in vegetation coverage in the global coastal zone based on GIMMS NDVI3g data","volume":"41","author":"Hou","year":"2020","journal-title":"Int. J. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.gloplacha.2019.03.010","article-title":"NDVI indicated inter-seasonal non-uniform time-lag responses of terrestrial vegetation growth to daily maximum and minimum temperature","volume":"177","author":"Wen","year":"2019","journal-title":"Glob. Planet. Change"},{"key":"ref_6","first-page":"774","article-title":"A review on fractional vegetation cover estimation using remote sensing","volume":"28","author":"Jia","year":"2013","journal-title":"Adv. Earth Sci."},{"key":"ref_7","first-page":"27","article-title":"Influence of parameter determination methods of the pixel dichotomy model on the estimation accuracy of fractional vegetation cover by GF-1 PMS data","volume":"35","author":"Pang","year":"2019","journal-title":"Geogr. Geo-Inf. Sci."},{"key":"ref_8","first-page":"102453","article-title":"Mapping the vegetation distribution and dynamics of a wetland using adaptive-stacking and Google Earth Engine based on multi-source remote sensing data","volume":"102","author":"Long","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Houborg, R., and McCabe, M.F. (2018). Daily Retrieval of NDVI and LAI at 3 m Resolution via the Fusion of CubeSat, Landsat, and MODIS Data. Remote Sens., 10.","DOI":"10.3390\/rs10060890"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1109\/TGRS.2017.2785240","article-title":"Predicting missing values in spatio-temporal remote sensing data","volume":"56","author":"Gerber","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"111901","DOI":"10.1016\/j.rse.2020.111901","article-title":"Multispectral high resolution sensor fusion for smoothing and gap-filling in the cloud","volume":"247","author":"Maneta","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"111685","DOI":"10.1016\/j.rse.2020.111685","article-title":"Continental-scale land surface phenology from harmonized Landsat 8 and Sentinel-2 imagery","volume":"240","author":"Bolton","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4055","DOI":"10.5194\/bg-10-4055-2013","article-title":"A comparison of methods for smoothing and gap filling time series of remote sensing observations\u2013application to MODIS LAI products","volume":"10","author":"Kandasamy","year":"2013","journal-title":"Biogeosciences"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.rse.2012.04.001","article-title":"Inter-comparison of four models for smoothing satellite sensor time-series data to estimate vegetation phenology","volume":"123","author":"Atkinson","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.1109\/TGRS.2002.802519","article-title":"Seasonality extraction by function fitting to time-series of satellite sensor data","volume":"40","author":"Jonsson","year":"2002","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.rse.2005.10.021","article-title":"Improved monitoring of vegetation dynamics at very high latitudes: A new method using MODIS NDVI","volume":"100","author":"Beck","year":"2006","journal-title":"Remote Sens. Environ."},{"key":"ref_17","first-page":"93","article-title":"Optimizing and comparing gap-filling techniques using simulated NDVI time series from remotely sensed global data","volume":"76","author":"Julien","year":"2019","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_18","first-page":"2150","article-title":"A method for the analysis of small crop fields in sentinel-2 dense time series","volume":"58","author":"Bovolo","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","first-page":"62","article-title":"Review of forest above ground biomass inversion methods based on remote sensing technology","volume":"19","author":"Liu","year":"2015","journal-title":"J. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"111452","DOI":"10.1016\/j.rse.2019.111452","article-title":"Fusing optical and SAR time series for LAI gap filling with multioutput Gaussian processes","volume":"235","author":"Pipia","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.5194\/isprs-archives-XLIII-B3-2020-1379-2020","article-title":"Investigating the Performance of Random Forest and Support Vector Regression for Estimation of Cloud-Free Ndvi Using SENTINEL-1 SAR Data","volume":"43","author":"Mohite","year":"2020","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/LGRS.2017.2681128","article-title":"Deep learning classification of land cover and crop types using remote sensing data","volume":"14","author":"Kussul","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isprsjprs.2019.09.016","article-title":"Combining Sentinel-1 and Sentinel-2 Satellite Image Time Series for land cover mapping via a multi-source deep learning architecture","volume":"158","author":"Ienco","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5048","DOI":"10.1109\/JSTARS.2020.3019046","article-title":"Multilevel deep learning network for county-level corn yield estimation in the us corn belt","volume":"13","author":"Sun","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, W., and Yokoya, N. (2018). Multi-temporal sentinel-1 and-2 data fusion for optical image simulation. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7100389"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cresson, R., Ienco, D., Gaetano, R., Ose, K., and Minh, D.H.T. (August, January 28). Optical image gap filling using deep convolutional autoencoder from optical and radar images. Proceedings of the IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8900353"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Scarpa, G., Gargiulo, M., Mazza, A., and Gaetano, R. (2018). A CNN-based fusion method for feature extraction from sentinel data. Remote Sens., 10.","DOI":"10.3390\/rs10020236"},{"key":"ref_28","first-page":"1","article-title":"Spatial\u2013Temporal Prediction of Vegetation Index With Deep Recurrent Neural Networks","volume":"19","author":"Yu","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"111952","DOI":"10.1016\/j.rse.2020.111952","article-title":"Deeply synergistic optical and SAR time series for crop dynamic monitoring","volume":"247","author":"Zhao","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"120758","DOI":"10.1016\/j.jclepro.2020.120758","article-title":"Sustainable development and environmental restoration in Lake Erhai, China","volume":"258","author":"Lin","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.rse.2011.05.028","article-title":"GMES Sentinel-1 mission","volume":"120","author":"Torres","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.rse.2011.11.026","article-title":"Sentinel-2: ESA\u2019s optical high-resolution mission for GMES operational services","volume":"120","author":"Drusch","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.rse.2017.06.031","article-title":"Google Earth Engine: Planetary-scale geospatial analysis for everyone","volume":"202","author":"Gorelick","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_34","unstructured":"Moorthy, I., Sturn, T., Batic, M., See, L., Mil\u010dinski, G., and Fritz, S. (2019, January 1\u20134). Improving Cloud Detection in Satellite Imagery using a Citizen Science Approach. Proceedings of the Digital Earth Observation, Salzburg, Austria."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Banerjee, S., Sinha Chaudhuri, S., Mehra, R., and Misra, A. (2021). A Survey on Lee Filter and Its Improved Variants, Springer.","DOI":"10.1007\/978-981-15-9433-5_36"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B.v., G\u00fcl\u00e7ehre, \u00c7., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25\u201329). Learning Phrase Representations using RNN Encoder Decoder for Statistical Machine Translation. Proceedings of the EMNLP, Doha, Qatar.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1037\/a0019471","article-title":"A dual-stage two-phase model of selective attention","volume":"117","author":"Steinhauser","year":"2010","journal-title":"Psychol. Rev."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"112419","DOI":"10.1016\/j.rse.2021.112419","article-title":"Recurrent-based regression of Sentinel time series for continuous vegetation monitoring","volume":"263","author":"Garioud","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_40","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst., 32."},{"key":"ref_41","unstructured":"Kingma, D.P., and Ba, J. (2015). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_42","first-page":"202","article-title":"Smoothing and gap-filling of high resolution multi-spectral time series: Example of Landsat data","volume":"57","author":"Vuolo","year":"2017","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"104666","DOI":"10.1016\/j.envsoft.2020.104666","article-title":"DATimeS: A machine learning time series GUI toolbox for gap-filling and vegetation phenology trends detection","volume":"127","author":"Belda","year":"2020","journal-title":"Environ. Model. Softw."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"111954","DOI":"10.1016\/j.rse.2020.111954","article-title":"Dual polarimetric radar vegetation index for crop growth monitoring using sentinel-1 SAR data","volume":"247","author":"Mandal","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"John, E., Bunting, P., Hardy, A., Silayo, D.S., and Masunga, E. (2021). A Forest Monitoring System for Tanzania. Remote Sens., 13.","DOI":"10.3390\/rs13163081"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Dumitru, C.O., Schwarz, G., Pulak-Siwiec, A., Kulawik, B., Lorenzo, J., and Datcu, M. (August, January 28). Earth Observation Data Mining: A Use Case for Forest Monitoring. Proceedings of the IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8899135"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5322","DOI":"10.1109\/JSTARS.2017.2746185","article-title":"Development of an adaptive approach for precision agriculture monitoring with drone and satellite data","volume":"10","author":"Murugan","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.eswa.2018.07.019","article-title":"ModAugNet: A new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module","volume":"113","author":"Baek","year":"2018","journal-title":"Expert Syst. Appl."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/7\/1632\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:45:33Z","timestamp":1760136333000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/7\/1632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,29]]},"references-count":48,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["rs14071632"],"URL":"https:\/\/doi.org\/10.3390\/rs14071632","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2022,3,29]]}}}