A modified flexible spatiotemporal data fusion model

doi:10.1007/s11707-019-0800-x

Front. Earth Sci.

2020, Vol. 14

Issue (3) : 601-614 https://doi.org/10.1007/s11707-019-0800-x

RESEARCH ARTICLE

A modified flexible spatiotemporal data fusion model

Jia TANG¹, Jingyu ZENG¹, Li ZHANG², Rongrong ZHANG¹, Jinghan LI³, Xingrong LI⁴, Jie ZOU⁵, Yue Zeng¹, Zhanghua Xu¹, Qianfeng WANG^1,⁶(

), Qing ZHANG²(

)

¹. Fujian Provincial Key Laboratory of Remote Sensing of Soil Erosion and Disaster Protection, College of Environment and Resources, Fuzhou University, Fuzhou 350116, China
². Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
³. College of Geography and Tourism, Anhui Normal University, Wuhu 241000, China
⁴. College of Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
⁵. Spatial Information Research Center of Fujian Province, Fuzhou University, Fuzhou 350116, China
⁶. Joint Global Change Research Institute, Pacific Northwest National Laboratory and University of Maryland, College Park, MD 20740, USA

Download: PDF(4831 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Remote sensing spatiotemporal fusion models blend multi-source images of different spatial resolutions to create synthetic images with high resolution and frequency, contributing to time series research where high quality observations are not available with sufficient frequency. However, existing models are vulnerable to spatial heterogeneity and land cover changes, which are frequent in human-dominated regions. To obtain quality time series of satellite images in a human-dominated region, this study developed the Modified Flexible Spatial-temporal Data Fusion (MFSDAF) approach based on the Flexible Spatial-temporal Data Fusion (FSDAF) model by using the enhanced linear regression (ELR). Multiple experiments of various land cover change scenarios were conducted based on both actual and simulated satellite images, respectively. The proposed MFSDAF model was validated by using the correlation coefficient (r), relative root mean square error (RRMSE), and structural similarity (SSIM), and was then compared with the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) and FSDAF models. Results show that in the presence of significant land cover change, MFSDAF showed a maximum increase in r, RRMSE, and SSIM of 0.0313, 0.0109 and 0.049, respectively, compared to FSDAF, while ESTARFM performed best with less temporal difference of in the input images. In conditions of stable landscape changes, the three performance statistics indicated a small advantage of MFSDAF over FSDAF, but were 0.0286, 0.0102, 0.0317 higher than for ESTARFM, respectively. MFSDAF showed greater accuracy of capturing subtle changes and created high-precision images from both actual and simulated satellite images.

Keywords MFSDAF enhanced linear regression land cover change heterogeneous time-series

Corresponding Author(s): Qianfeng WANG,Qing ZHANG

Online First Date: 13 January 2020 Issue Date: 04 December 2020

Cite this article:

Jia TANG,Jingyu ZENG,Li ZHANG, et al. A modified flexible spatiotemporal data fusion model[J]. Front. Earth Sci., 2020, 14(3): 601-614.

URL:

https://academic.hep.com.cn/fesci/EN/10.1007/s11707-019-0800-x
https://academic.hep.com.cn/fesci/EN/Y2020/V14/I3/601

Fig.1 Location of the study area and the 30 m land cover map provided by Tsinghua University (Available at Tsinghua University website).

Fig.2 Acquisition dates of OLI and MOD09A1 images available in 2016 for this study.

Fig.3 Phenological curves extracted by actual MOD09A1 NDVI images from 2016 by using a logistic model. (a) First increasing greenness phase; and (b) second decreasing greenness phase; the inset images are the actual OLI images.

Fig.4 Flowchart of the MFSDAF algorithm.

Tab.1 Design details of the experiments for FSDAF and MFSDAF testing

Fig.5 Images used for four experiments. The first, second, and third rows represent Landsat, actual MOD09A1 and simulated MOD09A1 images, respectively.

Tab.2 Accuracy assessment of the three models applied to different growing phases

Tab.3 Spectral properties of the OLI and MOD09A1 images

Fig.6 Scatter plots of the actual and predicted values of the three bands for experiment 1.

Tab.4 Accuracy assessment of the three models applied to the same growing phases

Fig.7 Scatter plots of the actual and predicted values of the three bands for experiment 3.

Fig.8 Comparison of predicted images on May 4, 2016 based on three models

Fig.9 Zoomed in images of the areas marked by rectangles in Fig. 8

Fig.10 Landsat image of May 04, 2016. (a) Actual image; (b) predicted image by MFSDAF in experiment 4 (c) predicted image by MFSDAF in experiment 3.

Fig.11 Scatter plots of the actual and predicted values based on MFSDAF on May 04, 2016. (a)–(c) based on actual MOD09A1 images; (d)–(f) based on simulated MOD09A1 images.

Fig.12 Zoomed in images of the areas marked by rectangles in Fig. 10. (a) Actual image; (b) predicted image by MFSDAF in experiment 4 (c) predicted image by MFSDAF in experiment 3.

Tab.5 Accuracy assessment of ESTARFM based on different images combinations as input

1	B Chen, B Huang, B Xu (2017). A hierarchical spatiotemporal adaptive fusion model using one image pair. Int J Digit Earth, 10(6): 639–655 https://doi.org/10.1080/17538947.2016.1235621
2	Q Cheng, H Q Liu, H F Shen, P H Wu, L P Zhang (2017). A spatial and temporal nonlocal filter-based data fusion method. IEEE Trans Geosci Remote Sens, 55(8): 4476–4488 https://doi.org/10.1109/TGRS.2017.2692802
3	J T Cui, X Zhang, M Y Luo (2018). Combining linear pixel unmixing and STARFM for spatiotemporal fusion of Gaofen-1 wide field of view imagery and MODIS imagery. Remote Sens, 10(7): 1047 https://doi.org/10.3390/rs10071047
4	M Das, S K Ghosh (2016). Deep-STEP: a deep learning approach for spatiotemporal prediction of remote sensing data. IEEE Geosci Remote S, 13(12): 1984–1988 https://doi.org/10.1109/LGRS.2016.2619984
5	I V Emelyanova, T R McVicar, T G Van Niel, L T Li, A I J M van Dijk (2013). Assessing the accuracy of blending Landsat-MODIS surface reflectances in two landscapes with contrasting spatial and temporal dynamics: a framework for algorithm selection. Remote Sens Environ, 133(12): 193–209 https://doi.org/10.1016/j.rse.2013.02.007
6	F Gao, J Masek, M Schwaller, F Hall(2006). On the blending of the Landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance. IEEE T Geosci Remote, 44(8): 2207–2218 https://doi.org/10.1109/TGRS.2006.872081
7	C He, Z Zhang, D Xiong, J Du, M Liao (2017). Spatio-temporal series remote sensing image prediction based on multi-dictionary Bayesian Fusion. ISPRS Int J Geoinf, 6(11): 374 https://doi.org/10.3390/ijgi6110374
8	B Huang, H Zhang (2014). Spatio-temporal reflectance fusion via unmixing: accounting for both phenological and land-cover changes. Int J Remote Sens, 35(16): 6213–6233 https://doi.org/10.1080/01431161.2014.951097
9	K Knauer, U Gessner, R Fensholt, C Kuenzer (2016). An ESTARFM fusion framework for the generation of large-scale time series in cloud-prone and heterogeneous landscapes. Remote Sens, 8(5): 425 https://doi.org/10.3390/rs8050425
10	B Ping, Y S Meng, F Z Su (2018). An enhanced linear spatio-temporal fusion method for blending landsat and MODIS data to synthesize landsat-like imagery. Remote Sens, 10(6): 881 https://doi.org/10.3390/rs10060881
11	J Quan, W Zhan, T Ma, Y Du, Z Guo, B Qin (2018). An integrated model for generating hourly Landsat-like land surface temperatures over heterogeneous landscapes. Remote Sens Environ, 206: 403–423 https://doi.org/10.1016/j.rse.2017.12.003
12	D P Roy, M A Wulder, T R Loveland, W C E, R G Allen, M C Anderson, D Helder, J R Irons, D M Johnson, R Kennedy, T A Scambos, C B Schaaf, J R Schott, Y Sheng, E F Vermote, A S Belward, R Bindschadler, W B Cohen, F Gao, J D Hipple, P Hostert, J Huntington, C O Justice, A Kilic, V Kovalskyy, Z P Lee, L Lymburner, J G Masek, J McCorkel, Y Shuai, R Trezza, J Vogelmann, R H Wynne, Z Zhu (2014). Landsat-8: science and product vision for terrestrial global change research. Remote Sens Environ, 145: 154–172 https://doi.org/10.1016/j.rse.2014.02.001
13	H Song, B Huang (2013). Spatiotemporal satellite image fusion through one-pair image learning. IEEE Trans Geosci Remote Sens, 51(4): 1883–1896 https://doi.org/10.1109/TGRS.2012.2213095
14	J R Townshend, J G Masek, C Huang, E F Vermote, F Gao, S Channan, J O Sexton, M Feng, R Narasimhan, D Kim, K Song, D Song, X P Song, P Noojipady, B Tan, M C Hansen, M Li, R E Wolfe (2012). Global characterization and monitoring of forest cover using Landsat data: opportunities and challenges. Int J Digit Earth, 5(5): 373–397 https://doi.org/10.1080/17538947.2012.713190
15	J J Walker, K M de Beurs, R H Wynne, F Gao (2012). Evaluation of landsat and MODIS data fusion products for analysis of dryland forest phenology. Remote Sens Environ, 117: 381–393 https://doi.org/10.1016/j.rse.2011.10.014
16	H Wang, X Pan, J Luo, Z Luo, C Chang, Y Shen (2015b). Using remote sensing to analyze spatiotemporal variations in crop planting in the North China Plain. Chin J Eco Agric, 23(9): 1199–1209
17	J Wang, B Huang (2018). A spatiotemporal satellite image fusion model with autoregressive error correction (AREC). Int J Remote Sens, 39(20): 1–26 https://doi.org/10.1080/01431161.2018.1466073
18	J Wang, B Huang (2017). A rigorously-weighted spatiotemporal Fusion model with uncertainty analysis. Remote Sens, 9(10): 990 https://doi.org/10.3390/rs9100990
19	P Wang, F Gao, J G Masek (2014a). Operational data fusion framework for building frequent landsat-like imagery. IEEE Trans Geosci Remote Sens, 52(11): 7353–7365 https://doi.org/10.1109/TGRS.2014.2311445
20	Q Wang, P M Atkinson (2018). Spatio-temporal fusion for daily Sentinel-2 images. Remote Sens Environ, 204: 31–42 https://doi.org/10.1016/j.rse.2017.10.046
21	Q M Wang, G A Blackburn, A O Onojeghuo, J Dash, L Zhou, Y Zhang, P M Atkinson (2017a). Fusion of Landsat 8 OLI and Sentinel-2 MSI data. IEEE Trans Geosci Remote Sens, 55(7): 3885–3899 https://doi.org/10.1109/TGRS.2017.2683444
22	Q F Wang, P Shi, T Lei, G Geng, J Liu, X Mo, X Li, H Zhou, J Wu (2015a). The alleviating trend of drought in the Huang-Huai-Hai Plain of China based on the daily SPEI. Int J Biometeorol, 35(13): 3760–3769
23	Q F Wang, J Tang, J Y Zeng, Y P Qu, Q Zhang, W Shui, W L Wang, L Yi, S Leng (2018a). Spatial-temporal evolution of vegetation evapotranspiration in Hebei Province, China. J Integr Agric, 17(9): 2107–2117 https://doi.org/10.1016/S2095-3119(17)61900-2
24	Q F Wang, J Tang, J Y Zeng, S Leng, W Shui (2019). Regional detecting of multiple change points and workable application for precipitation by maximum likelihood approach. Arab J Geosci, 12(23): 745 https://doi.org/?10.1007/s12517-?019–4790–5
25	Q F Wang, J Wu, T Lei, B He, Z Wu, M Liu, X Mo, G Geng, X Li, H Zhou, D Liu (2014b). Temporal-spatial characteristics of severe drought events and their impact on agriculture on a global scale. Quatern int, 349: 10–21 https://doi.org/10.1016/j.quaint.2014.06.021
26	Q F Wang, J Wu, X Li, H Zhou, J Yang, G Geng, X An, L Liu, Z Tang (2017c). A comprehensively quantitative method of evaluating the impact of drought on crop yield using daily multi-scale SPEI and crop growth process model. Int J Biometeorol, 61(4): 685–699 https://doi.org/10.1007/s00484-016-1246-4 pmid: 27888338
27	Q F Wang, J Y Zeng, S Leng, B X Fan, J Tang, C Jiang, Y Huang, Q Zhang, Y P Qu, W L Wang, W Shui (2018b). The effects of air temperature and precipitation on the net primary productivity in China during the early 21st century. Front Earth Sci, 12(4): 818–833 https://doi.org/10.1007/s11707-018-0697-9
28	Q M Wang, Y Zhang, A O Onojeghuo, X Zhu, P M Atkinson (2017b). Enhancing spatio-temporal fusion of MODIS and landsat data by incorporating 250 m MODIS data. IEEE J Stars, 10(9): 1–8 https://doi.org/10.1109/JSTARS.2017.2701643
29	Z Wang, A C Bovik, H R Sheikh, E P Simoncelli (2004). Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 13(4): 600–612 https://doi.org/10.1109/TIP.2003.819861 pmid: 15376593
30	J D Watts, S L Powell, R L Lawrence, T Hilker (2011). Improved classification of conservation tillage adoption using high temporal and synthetic satellite imagery. Remote Sens Environ, 115(1): 66–75 https://doi.org/10.1016/j.rse.2010.08.005
31	Q Weng, P Fu, F Gao (2014). Generating daily land surface temperature at landsat resolution by fusing landsat and MODIS data. Remote Sens Environ, 145(8): 55–67 https://doi.org/10.1016/j.rse.2014.02.003
32	M Q Wu, C Y Wu, W J Huang, Z Niu, C Y Wang, W Li, P Y Hao (2016). An improved high spatial and temporal data fusion approach for combining landsat and MODIS data to generate daily synthetic Landsat imagery. Inf Fusion, 31: 14–25 https://doi.org/10.1016/j.inffus.2015.12.005
33	M Wu, C Yang, X Song, W C Hoffmann, W Huang, Z Niu, C Wang, W Li, B Yu (2018). Monitoring cotton root rot by synthetic Sentinel-2 NDVI time series using improved spatial and temporal data fusion. Sci Rep, 8(1): 2016 https://doi.org/10.1038/s41598-018-20156-z pmid: 29386526
34	P Wu, H Shen, L Zhang, F M Göttsche (2015). 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, 156: 169–181 https://doi.org/10.1016/j.rse.2014.09.013
35	D Xie, J Zhang, X Zhu, Y Pan, H Liu, Z Yuan, Y Yun (2016). 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 (Basel), 16(2): 207 https://doi.org/10.3390/s16020207 pmid: 26861334
36	H Xu, T Shi, M Wang, Z Lin (2017). Land cover changes in the Xiong’ an New Area and a prediction of ecological response to forthcoming regional planning. Acta Ecol Sin, 37(19): 6289–6301
37	J Xue, Y Leung, T Fung (2017). A bayesian data fusion approach to spatio-temporal fusion of remotely sensed images. Remote Sens, 9(12): 1310 https://doi.org/10.3390/rs9121310
38	L Xun, C Deng, S Wang, G B Huang, B Zhao, P Lauren (2017). Fast and accurate spatiotemporal fusion based upon extreme learning machine. IEEE Geosci Remote S, 13(12): 2039–2043
39	H Zhang, J M Chen, B Huang, H Song, Y Li (2014). Reconstructing seasonal variation of landsat vegetation index related to leaf area index by fusing with MODIS data. IEEE J Stars, 7(3): 950–960 https://doi.org/10.1109/JSTARS.2013.2284528
40	W Zhang, A Li, H Jin, J Bian, Z Zhang, G Lei, Z Qin, C Huang (2013). An enhanced spatial and temporal data fusion model for fusing landsat and MODIS surface reflectance to generate high temporal landsat-like data. Remote Sens, 5(10): 5346–5368 https://doi.org/10.3390/rs5105346
41	X Y Zhang (2015). Reconstruction of a complete global time series of daily vegetation index trajectory from long-term AVHRR data. Remote Sens Environ, 156: 457–472 https://doi.org/10.1016/j.rse.2014.10.012
42	X Y Zhang, M A Friedl, C B Schaaf, A H Strahler, J C F Hodges, F Gao, B C Reed, A Huete (2003). Monitoring vegetation phenology using MODIS. Remote Sens Environ, 84(3): 471–475 https://doi.org/10.1016/S0034-4257(02)00135-9
43	Y Zhao, B Huang, H Song (2018). A robust adaptive spatial and temporal image fusion model for complex land surface changes. Remote Sens Environ, 208: 42–62 https://doi.org/10.1016/j.rse.2018.02.009
44	X Zhu, J Chen, F Gao, X Chen, J G Masek (2010). An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions. Remote Sens Environ, 114(11): 2610–2623 https://doi.org/10.1016/j.rse.2010.05.032
45	X Zhu, E H Helmer, F Gao, D Liu, J Chen, M A Lefsky (2016). A flexible spatiotemporal method for fusing satellite images with different resolutions. Remote Sens Environ, 172: 165–177 https://doi.org/10.1016/j.rse.2015.11.016

[1]	Shiyong YAN, Ke SHI, Yi LI, Jinglong LIU, Hongfeng ZHAO. Integration of satellite remote sensing data in underground coal fire detection: A case study of the Fukang region, Xinjiang, China[J]. Front. Earth Sci., 2020, 14(1): 1-12.
[2]	Shou MA,Jianchun GUO,Lianchong LI,Leslie George THAM,Yingjie XIA,Chun’an TANG. Influence of pore pressure on tensile fracture growth in rocks: a new explanation based on numerical testing[J]. Front. Earth Sci., 2015, 9(3): 412-426.
[3]	Christopher K. WRIGHT, Kirsten M. de BEURS, Geoffrey M. HENEBRY. Combined analysis of land cover change and NDVI trends in the Northern Eurasian grain belt[J]. Front Earth Sci, 2012, 6(2): 177-187.
[4]	Jiaguo QI, Temirbek S. BOBUSHEV, Rashid KULMATOV, Pavel GROISMAN, Garik GUTMAN. Addressing global change challenges for Central Asian socio-ecosystems[J]. Front Earth Sci, 2012, 6(2): 115-121.
[5]	Lev SPIVAK, Irina VITKOVSKAYA, Madina BATYRBAYEVA, Alexey TEREKHOV. The experience of land cover change detection by satellite data[J]. Front Earth Sci, 2012, 6(2): 140-146.
[6]	Yun JIANG, Jie LIU, Qing CUI, Xianghua AN, Chunxu WU. Land use/land cover change and driving force analysis in Xishuangbanna Region in 1986---2008[J]. Front Earth Sci, 2011, 5(3): 288-293.
[7]	HLAING Kay Thwe, HARUYAMA Shigeko, AYE Maung Maung. Using GIS-based distributed soil loss modeling and morphometric analysis to prioritize watershed for soil conservation in Bago river basin of Lower Myanmar[J]. Front. Earth Sci., 2008, 2(4): 465-478.

Viewed

Full text

Abstract

Cited

Shared

Discussed