logo

SCIENCE CHINA Information Sciences, Volume 63, Issue 4: 140301(2020) https://doi.org/10.1007/s11432-019-2785-y

Spatio-temporal fusion for remote sensing data: an overview and new benchmark

More info
  • ReceivedDec 3, 2019
  • AcceptedFeb 10, 2020
  • PublishedMar 9, 2020

Abstract

Spatio-temporal fusion (STF) aims at fusing (temporally dense) coarse resolution images and (temporally sparse) fine resolution images to generate image series with adequate temporal and spatial resolution. In the last decade, STF has drawn a lot of attention and many STF methods have been developed. However, to datethe STF domain still lacks benchmark datasets, which is a pressing issue that needs to be addressed in order to foster the development of this field. In this review, we provide (for the first time in the literature) a robust benchmark STF dataset that includes three important characteristics: (1) diversity of regions, (2) long timespan, and (3) challenging scenarios. We also provide a survey of highly representative STF techniques, along with a detailed quantitative and qualitative comparison of their performance with our newly presented benchmark dataset. The proposed dataset is public and available online.


Acknowledgment

This work was supported in part by National Natural Science Foundation of China (Grant Nos. 61771496, 61571195), National Key Research and Development Program of China (Grant No. 2017YFB0502900), and Guangdong Provincial Natural Science Foundation (Grant No. 2017A030313382). The authors would like to thank the developers of STARFM, ESTARFM, FSDAF and STFDCNN algorithms for sharing their codes.


References

[1] Shen M, Tang Y, Chen J. Influences of temperature and precipitation before the growing season on spring phenology in grasslands of the central and eastern Qinghai-Tibetan Plateau. Agric For Meteor, 2011, 151: 1711-1722 CrossRef Google Scholar

[2] Amorós-López J, Gómez-Chova L, Alonso L. Multitemporal fusion of Landsat/TM and ENVISAT/MERIS for crop monitoring. Int J Appl Earth Observation GeoInf, 2013, 23: 132-141 CrossRef Google Scholar

[3] Johnson M D, Hsieh W W, Cannon A J. Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods. Agric For Meteor, 2016, 218-219: 74-84 CrossRef Google Scholar

[4] Liao C, Wang J, Dong T. Using spatio-temporal fusion of Landsat-8 and MODIS data to derive phenology, biomass and yield estimates for corn and soybean.. Sci Total Environ, 2019, 650: 1707-1721 CrossRef PubMed Google Scholar

[5] Nduati E, Sofue Y, Matniyaz A. Cropland Mapping Using Fusion of Multi-Sensor Data in a Complex Urban/Peri-Urban Area. Remote Sens, 2019, 11: 207 CrossRef Google Scholar

[6] Zhang M, Lin H, Sun H. Estimation of Vegetation Productivity Using a Landsat 8 Time Series in a Heavily Urbanized Area, Central China. Remote Sens, 2019, 11: 133 CrossRef Google Scholar

[7] Hwang T, Song C, Bolstad P V. Downscaling real-time vegetation dynamics by fusing multi-temporal MODIS and Landsat NDVI in topographically complex terrain. Remote Sens Environ, 2011, 115: 2499-2512 CrossRef ADS Google Scholar

[8] Knipper K R, Kustas W P, Anderson M C. Evapotranspiration estimates derived using thermal-based satellite remote sensing and data fusion for irrigation management in California vineyards. Irrig Sci, 2019, 37: 431-449 CrossRef Google Scholar

[9] Pan Y, Shen F, Wei X. Fusion of Landsat-8/OLI and GOCI Data for Hourly Mapping of Suspended Particulate Matter at High Spatial Resolution: A Case Study in the Yangtze (Changjiang) Estuary. Remote Sens, 2018, 10: 158 CrossRef Google Scholar

[10] Yang X, Lo C P. Using a time series of satellite imagery to detect land use and land cover changes in the Atlanta, Georgia metropolitan area. Int J Remote Sens, 2002, 23: 1775-1798 CrossRef Google Scholar

[11] Heimhuber V, Tulbure M G, Broich M. Addressing spatio-temporal resolution constraints in Landsat and MODIS-based mapping of large-scale floodplain inundation dynamics. Remote Sens Environ, 2018, 211: 307-320 CrossRef Google Scholar

[12] Pastick N, Wylie B, Wu Z. Spatiotemporal Analysis of Landsat-8 and Sentinel-2 Data to Support Monitoring of Dryland Ecosystems. Remote Sens, 2018, 10: 791-806 CrossRef Google Scholar

[13] Chiesi M, Battista P, Fibbi L. Spatio-temporal fusion of NDVI data for simulating soil water content in heterogeneous Mediterranean areas. Eur J Remote Sens, 2019, 52: 88-95 CrossRef Google Scholar

[14] Li X, Zhou Y, Asrar G R. Response of vegetation phenology to urbanization in the conterminous United States. Glob Change Biol, 2017, 23: 2818-2830 CrossRef PubMed ADS Google Scholar

[15] Spatiotemporal Fusion of Multisource Remote Sensing Data: Literature Survey, Taxonomy, Principles, Applications, and Future Directions. Remote Sens, 2018, 10: 527 CrossRef Google Scholar

[16] Feng Gao , Masek J, Schwaller M. On the blending of the Landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance. IEEE Trans Geosci Remote Sens, 2006, 44: 2207-2218 CrossRef Google Scholar

[17] Hilker T, Wulder M A, Coops N C. A new data fusion model for high spatial- and temporal-resolution mapping of forest disturbance based on Landsat and MODIS. Remote Sens Environ, 2009, 113: 1613-1627 CrossRef Google Scholar

[18] Zhu X, Chen J, Gao F. An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions. Remote Sens Environ, 2010, 114: 2610-2623 CrossRef ADS Google Scholar

[19] Shen H, Wu P, Liu Y. A spatial and temporal reflectance fusion model considering sensor observation differences. Int J Remote Sens, 2013, 34: 4367-4383 CrossRef ADS Google Scholar

[20] Peijuan Wang , Feng Gao , Masek J G. Operational Data Fusion Framework for Building Frequent Landsat-Like Imagery. IEEE Trans Geosci Remote Sens, 2014, 52: 7353-7365 CrossRef Google Scholar

[21] Wang Q, Zhang Y, Onojeghuo A O. Enhancing Spatio-Temporal Fusion of MODIS and Landsat Data by Incorporating 250 m MODIS Data. IEEE J Sel Top Appl Earth Observations Remote Sens, 2017, 10: 4116-4123 CrossRef Google Scholar

[22] Zhao Y, Huang B, Song H. A robust adaptive spatial and temporal image fusion model for complex land surface changes. Remote Sens Environ, 2018, 208: 42-62 CrossRef ADS Google Scholar

[23] Bo Huang , Juan Wang , Huihui Song . Generating High Spatiotemporal Resolution Land Surface Temperature for Urban Heat Island Monitoring. IEEE Geosci Remote Sens Lett, 2013, 10: 1011-1015 CrossRef Google Scholar

[24] Xia H, Chen Y, Li Y. Combining kernel-driven and fusion-based methods to generate daily high-spatial-resolution land surface temperatures. Remote Sens Environ, 2019, 224: 259-274 CrossRef Google Scholar

[25] Weng Q, Fu P, Gao F. Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data. Remote Sens Environ, 2014, 145: 55-67 CrossRef Google Scholar

[26] Xu C, Qu J, Hao X. Downscaling of Surface Soil Moisture Retrieval by Combining MODIS/Landsat and In Situ Measurements. Remote Sens, 2018, 10: 210 CrossRef Google Scholar

[27] Houborg R, McCabe M F, Gao F. A Spatio-Temporal Enhancement Method for medium resolution LAI (STEM-LAI). Int J Appl Earth Observation GeoInf, 2016, 47: 15-29 CrossRef Google Scholar

[28] Wu P, Shen H, Zhang L. Integrated fusion of multi-scale polar-orbiting and geostationary satellite observations for the mapping of high spatial and temporal resolution land surface temperature. Remote Sens Environ, 2015, 156: 169-181 CrossRef Google Scholar

[29] Fu D, Chen B, Wang J. An Improved Image Fusion Approach Based on Enhanced Spatial and Temporal the Adaptive Reflectance Fusion Model. Remote Sens, 2013, 5: 6346-6360 CrossRef Google Scholar

[30] Liu M, Liu X, Wu L. A Modified Spatiotemporal Fusion Algorithm Using Phenological Information for Predicting Reflectance of Paddy Rice in Southern China. Remote Sens, 2018, 10: 772 CrossRef Google Scholar

[31] Cheng Q, Liu H, Shen H. A Spatial and Temporal Nonlocal Filter-Based Data Fusion Method. IEEE Trans Geosci Remote Sens, 2017, 55: 4476-4488 CrossRef Google Scholar

[32] Hazaymeh K, Hassan Q K. Spatiotemporal image-fusion model for enhancing the temporal resolution of Landsat-8 surface reflectance images using MODIS images. J Appl Remote Sens, 2015, 9: 096095 CrossRef ADS Google Scholar

[33] A Rigorously-Weighted Spatiotemporal Fusion Model with Uncertainty Analysis. Remote Sens, 2017, 9: 990 CrossRef Google Scholar

[34] Roy D P, Ju J, Lewis P. Multi-temporal MODIS-Landsat data fusion for relative radiometric normalization, gap filling, and prediction of Landsat data. Remote Sens Environ, 2008, 112: 3112-3130 CrossRef ADS Google Scholar

[35] Wu B, Huang B, Cao K. Improving spatiotemporal reflectance fusion using image inpainting and steering kernel regression techniques. Int J Remote Sens, 2017, 38: 706-727 CrossRef Google Scholar

[36] Wang J, Huang B. A spatiotemporal satellite image fusion model with autoregressive error correction (AREC). International Journal of Remote Sensing, 2018, 39: 1--26. Google Scholar

[37] Wang Q, Blackburn G A, Onojeghuo A O. Fusion of Landsat 8 OLI and Sentinel-2 MSI Data. IEEE Trans Geosci Remote Sens, 2017, 55: 3885-3899 CrossRef ADS Google Scholar

[38] Malleswara Rao J, Rao C V, Senthil Kumar A. Spatiotemporal Data Fusion Using Temporal High-Pass Modulation and Edge Primitives. IEEE Trans Geosci Remote Sens, 2015, 53: 5853-5860 CrossRef Google Scholar

[39] Sun Y, Zhang H, Shi W. A spatio-temporal fusion method for remote sensing data Using a linear injection model and local neighbourhood information. Int J Remote Sens, 2019, 40: 2965-2985 CrossRef ADS Google Scholar

[40] Yin G, Li A, Jin H. Spatiotemporal fusion through the best linear unbiased estimator to generate fine spatial resolution NDVI time series. Int J Remote Sens, 2018, 39: 3287-3305 CrossRef Google Scholar

[41] Liao C, Wang J, Pritchard I. A Spatio-Temporal Data Fusion Model for Generating NDVI Time Series in Heterogeneous Regions. Remote Sens, 2017, 9: 1125 CrossRef Google Scholar

[42] Bhattarai N, Quackenbush L J, Dougherty M. A simple Landsat-MODIS fusion approach for monitoring seasonal evapotranspiration at 30 m spatial resolution. Int J Remote Sens, 2015, 36: 115-143 CrossRef Google Scholar

[43] Kwan C, Budavari B, Gao F. A Hybrid Color Mapping Approach to Fusing MODIS and Landsat Images for Forward Prediction. Remote Sens, 2018, 10: 520 CrossRef Google Scholar

[44] Zhang Y, Foody G M, Ling F. Spatial-temporal fraction map fusion with multi-scale remotely sensed images. Remote Sens Environ, 2018, 213: 162-181 CrossRef Google Scholar

[45] Wang Q, Atkinson P M. Spatio-temporal fusion for daily Sentinel-2 images. Remote Sens Environment, 2017, 204: S0034425717305096. Google Scholar

[46] Zhukov B, Oertel D, Lanzl F. Unmixing-based multisensor multiresolution image fusion. IEEE Trans Geosci Remote Sens, 1999, 37: 1212-1226 CrossRef Google Scholar

[47] Zurita-Milla R, Clevers J, Schaepman M E. Unmixing-Based Landsat TM and MERIS FR Data Fusion. IEEE Geosci Remote Sens Lett, 2008, 5: 453-457 CrossRef Google Scholar

[48] Maselli F, Rembold F. Integration of LAC and GAC NDVI data to improve vegetation monitoring in semi-arid environments. Int J Remote Sens, 2002, 23: 2475-2488 CrossRef Google Scholar

[49] Niu Z. Use of MODIS and Landsat time series data to generate high-resolution temporal synthetic Landsat data using a spatial and temporal reflectance fusion model. J Appl Remote Sens, 2012, 6: 063507 CrossRef Google Scholar

[50] Wu M, Huang W, Niu Z. Generating Daily Synthetic Landsat Imagery by Combining Landsat and MODIS Data.. Sensors, 2015, 15: 24002-24025 CrossRef PubMed Google Scholar

[51] Zhang W, Li A, Jin H. An Enhanced Spatial and Temporal Data Fusion Model for Fusing Landsat and MODIS Surface Reflectance to Generate High Temporal Landsat-Like Data. Remote Sens, 2013, 5: 5346-5368 CrossRef Google Scholar

[52] Huang B, Zhang H. Spatio-temporal reflectance fusion via unmixing: accounting for both phenological and land-cover changes. Int J Remote Sens, 2014, 35: 6213-6233 CrossRef Google Scholar

[53] Yong Xu , Bo Huang , Yuyue Xu . Spatial and Temporal Image Fusion via Regularized Spatial Unmixing. IEEE Geosci Remote Sens Lett, 2015, 12: 1362-1366 CrossRef Google Scholar

[54] Mizuochi H, Hiyama T, Ohta T. Development and evaluation of a lookup-table-based approach to data fusion for seasonal wetlands monitoring: An integrated use of AMSR series, MODIS, and Landsat. Remote Sens Environ, 2017, 199: 370-388 CrossRef Google Scholar

[55] Lu M, Chen J, Tang H. Land cover change detection by integrating object-based data blending model of Landsat and MODIS. Remote Sens Environ, 2016, 184: 374-386 CrossRef Google Scholar

[56] Rao Y, Zhu X, Chen J. An Improved Method for Producing High Spatial-Resolution NDVI Time Series Datasets with Multi-Temporal MODIS NDVI Data and Landsat TM/ETM+ Images. Remote Sens, 2015, 7: 7865-7891 CrossRef Google Scholar

[57] Huang B, Song H. Spatiotemporal Reflectance Fusion via Sparse Representation. IEEE Trans Geosci Remote Sens, 2012, 50: 3707-3716 CrossRef Google Scholar

[58] Song H, Huang B. Spatiotemporal Satellite Image Fusion Through One-Pair Image Learning. IEEE Trans Geosci Remote Sens, 2013, 51: 1883-1896 CrossRef Google Scholar

[59] Li D, Li Y, Yang W. An Enhanced Single-Pair Learning-Based Reflectance Fusion Algorithm with Spatiotemporally Extended Training Samples. Remote Sens, 2018, 10: 1207 CrossRef Google Scholar

[60] Zhao C, Gao X, Emery W J. An Integrated Spatio-Spectral-Temporal Sparse Representation Method for Fusing Remote-Sensing Images With Different Resolutions. IEEE Trans Geosci Remote Sens, 2018, 56: 3358-3370 CrossRef Google Scholar

[61] Wu B, Huang B, Zhang L. An Error-Bound-Regularized Sparse Coding for Spatiotemporal Reflectance Fusion. IEEE Trans Geosci Remote Sens, 2015, 53: 6791-6803 CrossRef ADS Google Scholar

[62] Wei J, Wang L, Liu P. Spatiotemporal Fusion of Remote Sensing Images with Structural Sparsity and Semi-Coupled Dictionary Learning. Remote Sens, 2017, 9: 21 CrossRef Google Scholar

[63] Wei J, Wang L, Liu P. Spatiotemporal Fusion of MODIS and Landsat-7 Reflectance Images via Compressed Sensing. IEEE Trans Geosci Remote Sens, 2017, 55: 7126-7139 CrossRef Google Scholar

[64] Liu X, Deng C, Wang S. Fast and Accurate Spatiotemporal Fusion Based Upon Extreme Learning Machine. IEEE Geosci Remote Sens Lett, 2016, 13: 2039-2043 CrossRef ADS Google Scholar

[65] Song H, Liu Q, Wang G. Spatiotemporal Satellite Image Fusion Using Deep Convolutional Neural Networks. IEEE J Sel Top Appl Earth Observations Remote Sens, 2018, 11: 821-829 CrossRef ADS Google Scholar

[66] Liu X, Deng C, Chanussot J. IEEE Trans Geosci Remote Sens, 2019, 57: 6552-6564 CrossRef Google Scholar

[67] Tan Z, Yue P, Di L. Deriving High Spatiotemporal Remote Sensing Images Using Deep Convolutional Network. Remote Sens, 2018, 10: 1066 CrossRef Google Scholar

[68] Tao X, Liang S, Wang D. Improving Satellite Estimates of the Fraction of Absorbed Photosynthetically Active Radiation Through Data Integration: Methodology and Validation. IEEE Trans Geosci Remote Sens, 2018, 56: 2107-2118 CrossRef ADS Google Scholar

[69] Ke Y, Im J, Park S. Downscaling of MODIS One Kilometer Evapotranspiration Using Landsat-8 Data and Machine Learning Approaches. Remote Sens, 2016, 8: 215 CrossRef Google Scholar

[70] Boyte S P, Wylie B K, Rigge M B. Fusing MODIS with Landsat 8 data to downscale weekly normalized difference vegetation index estimates for central Great Basin rangelands, USA. GISci Remote Sens, 2018, 55: 376-399 CrossRef Google Scholar

[71] Moosavi V, Talebi A, Mokhtari M H. A wavelet-artificial intelligence fusion approach (WAIFA) for blending Landsat and MODIS surface temperature. Remote Sens Environ, 2015, 169: 243-254 CrossRef Google Scholar

[72] Li Y F, Li J, He L, et al. A sensor-bias driven spatio-temporal fusion model based on convolutional neural networks. Sci China Inf Sci, for review. Google Scholar

[73] Xue J, Leung Y, Fung T. A Bayesian Data Fusion Approach to Spatio-Temporal Fusion of Remotely Sensed Images. Remote Sens, 2017, 9: 1310 CrossRef Google Scholar

[74] Li A, Bo Y, Zhu Y. Blending multi-resolution satellite sea surface temperature (SST) products using Bayesian maximum entropy method. Remote Sens Environ, 2013, 135: 52-63 CrossRef Google Scholar

[75] Huang B, Zhang H, Song H. Unified fusion of remote-sensing imagery: generating simultaneously high-resolution synthetic spatial-temporal-spectral earth observations. Remote Sens Lett, 2013, 4: 561-569 CrossRef Google Scholar

[76] Shen H, Meng X, Zhang L. An Integrated Framework for the Spatio-Temporal-Spectral Fusion of Remote Sensing Images. IEEE Trans Geosci Remote Sens, 2016, 54: 7135-7148 CrossRef ADS Google Scholar

[77] Gevaert C M, García-Haro F J. A comparison of STARFM and an unmixing-based algorithm for Landsat and MODIS data fusion. Remote Sens Environ, 2015, 156: 34-44 CrossRef Google Scholar

[78] Ma J, Zhang W, Marinoni A. An Improved Spatial and Temporal Reflectance Unmixing Model to Synthesize Time Series of Landsat-Like Images. Remote Sens, 2018, 10: 1388 CrossRef Google Scholar

[79] Xie D, Zhang J, Zhu X. An Improved STARFM with Help of an Unmixing-Based Method to Generate High Spatial and Temporal Resolution Remote Sensing Data in Complex Heterogeneous Regions.. Sensors, 2016, 16: 207 CrossRef PubMed Google Scholar

[80] Zhu X, Helmer E H, Gao F. A flexible spatiotemporal method for fusing satellite images with different resolutions. Remote Sens Environ, 2016, 172: 165-177 CrossRef Google Scholar

[81] Liu M, Yang W, Zhu X. An Improved Flexible Spatiotemporal DAta Fusion (IFSDAF) method for producing high spatiotemporal resolution normalized difference vegetation index time series. Remote Sens Environ, 2019, 227: 74-89 CrossRef Google Scholar

[82] Cui J, Zhang X, Luo M. Combining Linear Pixel Unmixing and STARFM for Spatiotemporal Fusion of Gaofen-1 Wide Field of View Imagery and MODIS Imagery. Remote Sens, 2018, 10: 1047 CrossRef Google Scholar

[83] Li X, Ling F, Foody G M. Generating a series of fine spatial and temporal resolution land cover maps by fusing coarse spatial resolution remotely sensed images and fine spatial resolution land cover maps. Remote Sens Environ, 2017, 196: 293-311 CrossRef Google Scholar

[84] Ping B, Meng Y, Su F. An Enhanced Linear Spatio-Temporal Fusion Method for Blending Landsat and MODIS Data to Synthesize Landsat-Like Imagery. Remote Sens, 2018, 10: 881 CrossRef Google Scholar

[85] Quan J, Zhan W, Ma T. An integrated model for generating hourly Landsat-like land surface temperatures over heterogeneous landscapes. Remote Sens Environ, 2018, 206: 403-423 CrossRef Google Scholar

[86] Liu W, Zeng Y, Li S. An Improved Spatiotemporal Fusion Approach Based on Multiple Endmember Spectral Mixture Analysis.. Sensors, 2019, 19: 2443 CrossRef PubMed Google Scholar

[87] Liao L, Song J, Wang J. Bayesian Method for Building Frequent Landsat-Like NDVI Datasets by Integrating MODIS and Landsat NDVI. Remote Sens, 2016, 8: 452 CrossRef Google Scholar

[88] Xue J, Leung Y, Fung T. An Unmixing-Based Bayesian Model for Spatio-Temporal Satellite Image Fusion in Heterogeneous Landscapes. Remote Sens, 2019, 11: 324 CrossRef Google Scholar

[89] Wang Z, Bovik A C, Sheikh H R. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Trans Image Process, 2004, 13: 600-612 CrossRef PubMed ADS Google Scholar

[90] Renza D, Martinez E, Arquero A. A New Approach to Change Detection in Multispectral Images by Means of ERGAS Index. IEEE Geosci Remote Sens Lett, 2013, 10: 76-80 CrossRef Google Scholar

  • Figure 1

    (Color online) Example pairs from the AHB dataset.

  • Figure 2

    (Color online) Example pairs from the Tianjin dataset.

  • Figure 3

    (Color online) Example pairs from the Daxing dataset.

  • Figure 4

    (Color online) Test data from the AHB dataset, where the 1st row displays the MODIS images and the 2nd row displays the Landsat images.

  • Figure 5

    (Color online) Test data from Tianjin dataset.

  • Figure 6

    (Color online) Test data from Daxing dataset.

  • Figure 7

    (Color online) Ground truth image and obtained predictions for the AHB dataset.

  • Figure 9

    (Color online) Ground truth image and obtained predictions for the Daxing dataset.

  • Table 1   Summary of the three considered datasets
    Dataset Image size Pairs Timespan Main change
    AHB 2480$\times$2800$\times$6 27 2013/05/30 – 2018/12/06 Phenological changes in rural areas
    Tianjin 2100$\times$1970$\times$6 27 2013/09/01 – 2019/09/18 Phenological changes in urban areas
    Daxing 1640$\times$1640$\times$6 29 2013/09/01 – 2019/11/05 Land-cover changes
  • Table 2   Quantitative assessment of experimental results on the AHB dataset
    Band STARFM ESTARFM FSDAF STFDCNN BiaSTF
    RMSE Band 1 0.0286 0.0159 0.0300 0.0171 0.0136
    Band 2 0.0355 0.0222 0.0366 0.0244 0.0248
    Band 3 0.0552 0.0405 0.0563 0.0419 0.0426
    Band 4 0.0666 0.0680 0.0675 0.0675 0.0660
    CC Band 1 0.6781 0.5188 0.7006 0.5684 0.7200
    Band 2 0.7033 0.7207 0.7296 0.6382 0.7496
    Band 3 0.7120 0.7376 0.7371 0.6835 0.7634
    Band 4 0.6972 0.7260 0.7232 0.6416 0.7313
    SSIM Band 1 0.7922 0.8432 0.7828 0.8441 0.9026
    Band 2 0.7795 0.8442 0.7818 0.8065 0.8499
    Band 3 0.7263 0.7765 0.7331 0.7489 0.7942
    Band 4 0.7411 0.7574 0.7572 0.7017 0.7649
    ERGAS 2.007 1.3899 2.0730 1.849 1.3963
    SAM 0.110 0.0800 0.1159 0.0941 0.0720
  • Table 3   Quantitative assessment of experimental results on the Tianjin dataset
    Band STARFM ESTARFM FSDAF STFDCNN BiaSTF
    RMSE Band 1 0.0241 0.0212 0.0226 0.0274 0.0234
    Band 2 0.0312 0.0240 0.0297 0.0389 0.0242
    Band 3 0.0375 0.0342 0.0347 0.0452 0.0310
    Band 4 0.0896 0.1425 0.0872 0.0602 0.0853
    CC Band 1 0.8385 0.8612 0.8462 0.7693 0.8193
    Band 2 0.7740 0.8367 0.7812 0.5980 0.8301
    Band 3 0.6863 0.7957 0.7147 0.6191 0.7985
    Band 4 0.6883 0.3121 0.7155 0.8179 0.7264
    SSIM Band 1 0.8722 0.8886 0.8813 0.8220 0.8582
    Band 2 0.8158 0.8640 0.8222 0.6821 0.8579
    Band 3 0.7430 0.8127 0.7651 0.6752 0.8220
    Band 4 0.6874 0.3258 0.7000 0.8117 0.7204
    ERGAS 1.6180 1.7313 1.5304 1.9832 1.4292
    SAM 0.1965 0.1656 0.1766 0.1574 0.1443
  • Table 4   Quantitative assessment of experimental results on the Daxing dataset
    Band STARFM ESTARFM FSDAF STFDCNN BiaSTF
    RMSE Band 1 0.0124 0.0152 0.0127 0.0177 0.0121
    Band 2 0.0161 0.0160 0.0159 0.0187 0.0153
    Band 3 0.0221 0.0219 0.0213 0.0251 0.0209
    Band 4 0.0429 0.0509 0.0419 0.0519 0.0456
    CC Band 1 0.9397 0.9338 0.9406 0.9038 0.9478
    Band 2 0.9239 0.9307 0.9284 0.9120 0.9324
    Band 3 0.8962 0.8985 0.9025 0.8768 0.9062
    Band 4 0.7775 0.7079 0.7885 0.7020 0.7486
    SSIM Band 1 0.9556 0.9434 0.9543 0.9226 0.9594
    Band 2 0.9398 0.9429 0.9410 0.9277 0.9452
    Band 3 0.9140 0.9155 0.9176 0.8962 0.9218
    Band 4 0.8011 0.7371 0.8109 0.7320 0.7753
    ERGAS 0.9642 1.0436 0.9524 1.3085 0.9328
    SAM 0.0673 0.0706 0.0660 0.0794 0.0658
  • Table 5   Quantitative assessment of the obtained results in the three considered benchmark datasets
    AHB datasetTianjin datasetDaxing dataset
    Pair STFDCNN BiaSTF Pair STFDCNN BiaSTF Pair STFDCNN BiaSTF
    18th 0.0270 0.0180 18th 0.0413 0.050920th 0.0379 0.0379
    19th 0.0316 0.0304 19th 0.0417 0.051521st 0.0386 0.0355
    20th 0.0325 0.0247 20th 0.0633 0.084622nd 0.0425 0.0456
    21st 0.0477 0.0394 21st 0.0463 0.045923rd 0.0333 0.0394
    RMSE22nd 0.0265 0.0237 22nd 0.0471 0.039924th 0.0410 0.0394
    23rd 0.0222 0.1910 23rd 0.0429 0.040925th 0.0258 0.0231
    24th 0.0377 0.0367 24th 0.0549 0.091026th 0.0283 0.0234
    25th 0.0295 0.0436 25th 0.0502 0.049727th 0.0315 0.0292
    26th 0.0277 0.0296 26th 0.0321 0.026428th 0.0289 0.0295
    27th 0.0308 0.0397 27th 0.0333 0.035529th 0.0463 0.0309
    18th 0.7455 0.8898 18th 0.7479 0.819820th 0.8117 0.8471
    19th 0.6883 0.8204 19th 0.6501 0.819821st 0.7583 0.8095
    20th 0.6489 0.8011 20th 0.4795 0.604922nd 0.7100 0.7285
    21st 0.5427 0.7877 21st 0.6683 0.757323rd 0.8179 0.8837
    CC22nd 0.7183 0.8159 22nd 0.7558 0.784224th 0.7329 0.8834
    23rd 0.6382 0.6593 23rd 0.7010 0.793525th 0.8456 0.8869
    24th 0.6329 0.7411 24th 0.6797 0.761626th 0.8486 0.8837
    25th 0.6136 0.7698 25th 0.7282 0.788927th 0.8406 0.8686
    26th 0.6216 0.7030 26th 0.8648 0.909628th 0.8653 0.8705
    27th 0.4892 0.6218 27th 0.8809 0.855229th 0.7276 0.8050
    18th 0.8222 0.9243 18th 0.7874 0.810620th 0.8433 0.8607
    19th 0.7740 0.8552 19th 0.7320 0.654521st 0.7868 0.8405
    20th 0.7301 0.8495 20th 0.5516 0.637322nd 0.7509 0.7231
    21st 0.6268 0.7552 21st 0.7126 0.773023rd0.8278 0.8581
    SSIM 22rd 0.8016 0.8637 22rd 0.7585 0.808624th 0.7603 0.8599
    23nd 0.8148 0.8372 23nd 0.7477 0.814625th 0.8719 0.9040
    24th 0.7753 0.8279 24th 0.7196 0.756026th 0.8696 0.9004
    25th 0.7584 0.7043 25th 0.7556 0.796427th 0.8565 0.8783
    26th 0.7781 0.7911 26th 0.8766 0.920228th 0.8845 0.8843
    27th 0.6853 0.6996 27th 0.8868 0.867729th 0.7184 0.8352
    18th 0.8165 0.5345 18th 2.1370 2.441620th 1.3017 1.3017
    19th 1.1292 1.2540 19th 1.7090 1.996021st 1.4559 1.1097
    20th 1.2808 0.7552 20th 2.5530 1.997022nd 1.9421 1.8862
    21st 2.7802 2.5355 21st 2.3168 2.286823rd 1.5581 1.4893
    ERGAS22rd 3.9073 3.7836 22rd 2.0626 1.775724th 1.5646 1.9691
    23nd 1.1872 1.3057 23nd 1.9832 1.595425th 1.1212 0.9930
    24th 1.8490 1.3963 24th 1.8920 1.786426th 1.3085 0.9328
    25th 1.9249 7.5260 25th 2.4567 2.175727th 1.8015 1.5930
    26th 1.8163 1.9451 26th 1.7705 1.481028th 1.5409 1.5033
    27th 2.7139 2.2231 27th 1.8223 1.677129th 2.3941 1.0790
    18th 0.0908 0.0394 18th 0.1393 0.134520th 0.0825 0.0663
    19th 0.1204 0.0790 19th 0.1200 0.121021st 0.1343 0.1052
    20th 0.1422 0.0809 20th 0.1429 0.164522nd 0.1640 0.2008
    21st 0.2570 0.2461 21st 0.1843 0.179123rd 0.1300 0.0919
    SAM 22nd 0.2756 0.2247 22nd 0.1925 0.142224th 0.1266 0.0896
    23rd 0.1299 0.1265 23rd 0.1574 0.144325th 0.0746 0.0689
    24th 0.0941 0.0720 24th 0.1699 0.146226th 0.0794 0.0658
    25th 0.1864 0.3368 25th 0.1567 0.157727th 0.0782 0.0706
    26th 0.2056 0.2623 26th 0.1050 0.083628th 0.0768 0.0729
    27th 0.3030 0.2663 27th 0.1007 0.086529th 0.1604 0.0935

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1