{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:13:32Z","timestamp":1760228012077,"version":"build-2065373602"},"reference-count":55,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["41801347","2016YFA0600103"],"award-info":[{"award-number":["41801347","2016YFA0600103"]}]},{"name":"National Key Research and Development Program of China","award":["41801347","2016YFA0600103"],"award-info":[{"award-number":["41801347","2016YFA0600103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Landsat has provided the longest fine resolution data archive of Earth\u2019s environment since 1972; however, one of the challenges in using Landsat data for various applications is its frequent large data gaps and heavy cloud contaminations. One pressing research topic is to generate the regular time series by integrating coarse-resolution satellite data through data fusion techniques. This study presents a novel spatiotemporal fusion (STF) method based on a depthwise separable convolutional neural network (DSC), namely, STFDSC, to generate Landsat-surface reflectance time series at 8-day intervals by fusing Landsat 30 m with high-quality Moderate Resolution Imaging Spectroradiometer (MODIS) 500 m surface reflectance data. The STFDSC method consists of three main stages: feature extraction, feature fusion and prediction. Features were first extracted from Landsat and MODIS surface reflectance changes, and the extracted multilevel features were then stacked and fused. Both low-level and middle-level features that were generally ignored in convolutional neural network (CNN)-based fusion models were included in STFDSC to avoid key information loss and thus ensure high prediction accuracy. The prediction stage generated a Landsat residual image and is combined with original Landsat data to obtain predictions of Landsat imagery at the target date. The performance of STFDSC was evaluated in the Greater Khingan Mountains (GKM) in Northeast China and the Ziwuling (ZWL) forest region in Northwest China. A comparison of STFDSC with four published fusion methods, including two classic fusion methods (FSDAF, ESTARFM) and two machine learning methods (EDCSTFN and STFNET), was also carried out. The results showed that STFDSC made stable and more accurate predictions of Landsat surface reflectance than other methods in both the GKM and ZWL regions. The root-mean-square-errors (RMSEs) of TM bands 2, 3, 4, and 7 were 0.0046, 0.0038, 0.0143, and 0.0055 in GKM, respectively, and 0.0246, 0.0176, 0.0280, and 0.0141 in ZWL, respectively; it can be potentially used for generating the global surface reflectance and other high-level land products.<\/jats:p>","DOI":"10.3390\/rs14092199","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T02:19:48Z","timestamp":1651717188000},"page":"2199","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A New Spatial\u2013Temporal Depthwise Separable Convolutional Fusion Network for Generating Landsat 8-Day Surface Reflectance Time Series over Forest Regions"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1613-5770","authenticated-orcid":false,"given":"Yuzhen","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4187-1289","authenticated-orcid":false,"given":"Jindong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2708-9183","authenticated-orcid":false,"given":"Shunlin","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Geographical Sciences, University of Maryland, College Park, MD 20742, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manyao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11011","DOI":"10.1126\/science.320.5879.1011a","article-title":"Free Access to Landsat Imagery","volume":"320","author":"Woodcock","year":"2008","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.rse.2019.02.015","article-title":"Current status of Landsat program, science, and applications","volume":"225","author":"Wulder","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Nguyen, T.H., Jones, S., Soto-Berelov, M., Haywood, A., and Hislop, S. (2020). Landsat Time-Series for Estimating Forest Aboveground Biomass and Its Dynamics across Space and Time: A Review. Remote Sens., 12.","DOI":"10.3390\/rs12010098"},{"key":"ref_4","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_5","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.rse.2017.02.021","article-title":"Mapping major land cover dynamics in Beijing using all Landsat images in Google Earth Engine","volume":"202","author":"Huang","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.rse.2014.01.011","article-title":"Continuous change detection and classification of land cover using all available Landsat data","volume":"144","author":"Zhu","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.isprsjprs.2017.07.011","article-title":"A mangrove forest map of China in 2015: Analysis of time series Landsat 7\/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform","volume":"131","author":"Chen","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1016\/j.rse.2009.12.018","article-title":"Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: A comparison of empirical modeling approaches","volume":"114","author":"Powell","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.rse.2017.03.035","article-title":"A nationwide annual characterization of 25 years of forest disturbance and recovery for Canada using Landsat time series","volume":"194","author":"White","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.rse.2013.04.022","article-title":"Forest disturbances, forest recovery, and changes in forest types across the Carpathian ecoregion from 1985 to 2010 based on Landsat image composites","volume":"151","author":"Griffiths","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yan, L., and Roy, D.P. (2018). Large-Area Gap Filling of Landsat Reflectance Time Series by Spectral-Angle-Mapper Based Spatio-Temporal Similarity (SAMSTS). Remote Sens., 10.","DOI":"10.3390\/rs10040609"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1080\/15481603.2013.823733","article-title":"Derivation of 16-day time-series NDVI data for environmental studies using a data assimilation approach","volume":"50","author":"Meng","year":"2013","journal-title":"GIScience Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1109\/TGRS.2006.872081","article-title":"On the blending of the Landsat and MODIS surface reflectance: Predicting daily Landsat surface reflectance","volume":"44","author":"Gao","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112130","DOI":"10.1016\/j.rse.2020.112130","article-title":"Sensitivity of six typical spatiotemporal fusion methods to different influential factors: A comparative study for a normalized difference vegetation index time series reconstruction","volume":"252","author":"Zhou","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.rse.2014.02.003","article-title":"Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data","volume":"145","author":"Weng","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.agrformet.2013.11.001","article-title":"Mapping daily evapotranspiration at field scales over rainfed and irrigated agricultural areas using remote sensing data fusion","volume":"186","author":"Cammalleri","year":"2014","journal-title":"Agric. For. Meteorol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1016\/j.rse.2009.05.011","article-title":"Generation of dense time series synthetic Landsat data through data blending with MODIS using a spatial and temporal adaptive reflectance fusion model","volume":"113","author":"Hilker","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2610","DOI":"10.1016\/j.rse.2010.05.032","article-title":"An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions","volume":"114","author":"Zhu","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1080\/15481603.2019.1627062","article-title":"Landsat-MODIS image fusion and object-based image analysis for observing flood inundation in a heterogeneous vegetated scene","volume":"56","author":"Dao","year":"2019","journal-title":"GISci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"063507","DOI":"10.1117\/1.JRS.6.063507","article-title":"Use of MODIS and Landsat time series data to generate high-resolution temporal synthetic Landsat data using a spatial and temporal reflectance fusion model","volume":"6","author":"Wu","year":"2012","journal-title":"J. Appl. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6213","DOI":"10.1080\/01431161.2014.951097","article-title":"Spatio-temporal reflectance fusion via unmixing: Accounting for both phenological and land-cover changes","volume":"35","author":"Huang","year":"2014","journal-title":"Int. J. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.rse.2014.09.012","article-title":"A comparison of STARFM and an unmixing-based algorithm for Landsat and MODIS data fusion","volume":"156","author":"Gevaert","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.rse.2015.11.016","article-title":"A flexible spatiotemporal method for fusing satellite images with different resolutions","volume":"172","author":"Zhu","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1109\/TIP.2018.2878958","article-title":"An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing","volume":"28","author":"Hong","year":"2019","journal-title":"IEEE Trans. Image Processing"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tan, Z., Di, L., Zhang, M., Guo, L., and Gao, M. (2019). An Enhanced Deep Convolutional Model for Spatiotemporal Image Fusion. Remote Sens., 11.","DOI":"10.3390\/rs11242898"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.1109\/TGRS.2012.2186638","article-title":"Spatiotemporal Reflectance Fusion via Sparse Representation","volume":"50","author":"Huang","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.1109\/TGRS.2012.2213095","article-title":"Spatiotemporal Satellite Image Fusion Through One-Pair Image Learning","volume":"51","author":"Song","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1109\/JSTARS.2018.2797894","article-title":"Spatiotemporal Satellite Image Fusion Using Deep Convolutional Neural Networks","volume":"11","author":"Song","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6552","DOI":"10.1109\/TGRS.2019.2907310","article-title":"StfNet: A Two-Stream Convolutional Neural Network for Spatiotemporal Image Fusion","volume":"57","author":"Liu","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1973","DOI":"10.1080\/01431161.2020.1809742","article-title":"Spatiotemporal Fusion of Remote Sensing Images using a Convolutional Neural Network with Attention and Multiscale Mechanisms","volume":"42","author":"Li","year":"2021","journal-title":"Int. J. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, B., Li, J., and Jin, Y.F. (2021). Deep Learning for Feature-Level Data Fusion: Higher Resolution Reconstruction of Historical Landsat Archive. Remote Sens., 13.","DOI":"10.3390\/rs13020167"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gao, J., Yuan, Q., Li, J., Zhang, H., and Su, X. (2020). Cloud Removal with Fusion of High Resolution Optical and SAR Images Using Generative Adversarial Networks. Remote Sens., 12.","DOI":"10.3390\/rs12010191"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature Pyramid Networks for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_35","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France."},{"key":"ref_36","unstructured":"Xu, B., Wang, N., Chen, T., and Li, M. (2015). Empirical Evaluation of Rectified Activations in Convolutional Network. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Fu, Y., He, H.S., Zhao, J., Larsen, D.R., Zhang, H., Sunde, M.G., and Duan, S. (2018). Climate and Spring Phenology Effects on Autumn Phenology in the Greater Khingan Mountains, Northeastern China. Remote Sens., 10.","DOI":"10.3390\/rs10030449"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2674","DOI":"10.1007\/s11629-020-6036-0","article-title":"The driving factors and their interactions of fire occurrence in Greater Khingan Mountains, China","volume":"17","author":"Guo","year":"2020","journal-title":"J. Mt. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6873","DOI":"10.1038\/srep06873","article-title":"Population Structure and Spatial Pattern of Main Tree Species in Secondary Betula platyphylla Forest in Ziwuling Mountains, China","volume":"4","author":"Kang","year":"2014","journal-title":"Sci. Rep."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.agee.2004.12.009","article-title":"Effects of erosion patterns on nutrient loss following deforestation on the Loess Plateau of China","volume":"108","author":"Zheng","year":"2005","journal-title":"Agric. Ecosyst. Environ."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5325","DOI":"10.3390\/rs6065325","article-title":"A Circa 2010 Thirty Meter Resolution Forest Map for China","volume":"6","author":"Li","year":"2014","journal-title":"Remote Sens."},{"key":"ref_42","unstructured":"USGS (2019). Landsat Collection 1 Level 1 Product Definition."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Hislop, S., Jones, S., Soto-Berelov, M., Skidmore, A., Haywood, A., and Nguyen, T.H. (2018). Using Landsat Spectral Indices in Time-Series to Assess Wildfire Disturbance and Recovery. Remote Sens., 10.","DOI":"10.3390\/rs10030460"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.rse.2011.10.014","article-title":"Evaluation of Landsat and MODIS data fusion products for analysis of dryland forest phenology","volume":"117","author":"Walker","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.rse.2014.01.007","article-title":"Dryland vegetation phenology across an elevation gradient in Arizona, USA, investigated with fused MODIS and Landsat data","volume":"144","author":"Walker","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1109\/TGRS.2020.2999943","article-title":"Spatiotemporal Fusion of Land Surface Temperature Based on a Convolutional Neural Network","volume":"59","author":"Yin","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.rse.2009.05.022","article-title":"Development of an approach for generation of temporally complete daily nadir MODIS reflectance time series","volume":"114","author":"Ju","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"140302","DOI":"10.1007\/s11432-019-2805-y","article-title":"A new sensor bias-driven spatio-temporal fusion model based on convolutional neural networks","volume":"63","author":"Li","year":"2020","journal-title":"Sci. China Inf. Sci."},{"key":"ref_50","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Hirschmugl, M., Deutscher, J., Sobe, C., Bouvet, A., Mermoz, S., and Schardt, M. (2020). Use of SAR and Optical Time Series for Tropical Forest Disturbance Mapping. Remote Sens., 12.","DOI":"10.3390\/rs12040727"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"141","DOI":"10.5721\/EuJRS20154809","article-title":"Quality assessment of ten fusion techniques applied on Worldview-2","volume":"48","author":"Nikolakopoulos","year":"2015","journal-title":"Eur. J. Remote Sens."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1109\/LGRS.2020.3003322","article-title":"Constructing 10-m NDVI Time Series From Landsat 8 and Sentinel 2 Images Using Convolutional Neural Networks","volume":"18","author":"Ao","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_54","first-page":"102260","article-title":"Fusion of Sentinel-2 and PlanetScope time-series data into daily 3 m surface reflectance and wheat LAI monitoring","volume":"96","author":"Sadeh","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.inffus.2012.04.001","article-title":"Data fusion for high spatial resolution LAI estimation","volume":"16","author":"Nunes","year":"2014","journal-title":"Inf. Fusion"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/9\/2199\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:06:08Z","timestamp":1760137568000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/9\/2199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,4]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["rs14092199"],"URL":"https:\/\/doi.org\/10.3390\/rs14092199","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2022,5,4]]}}}