FSDAF 2.0: Improving the performance of retrieving land cover changes and preserving spatial details

Guo, Dizhou; Shi, Wenzhong; Hao, Ming; Zhu, Xiaolin

doi:10.1016/j.rse.2020.111973

Cited by 67 publications

(22 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hybrid STF methods focus on improving generalization through combinations of multiple methods to deal with different cases of land surface temporal change [36]. The flexible spatiotemporal data fusion (FSDAF) method [12] and the subsequently proposed revisions of FSDAF, which include the improved FSDAF (IFSDAF) [44], enhanced FSDAF (SFSDAF) [45], and FSDAF 2.0 [46], are representative of this type. Through the combination of spectral mixing analysis and a residual distribution strategy, these methods are able to address PC and LC prediction simultaneously, while their input requirement of one fine-coarse image pair further increases their practicality in areas with severe cloud contamination.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Deep Learning-Based Spatiotemporal Fusion Method for Combining Satellite Images with Different Resolutions

et al. 2021

View full text Add to dashboard Cite

Spatiotemporal fusion (STF) is considered a feasible and cost-effective way to deal with the trade-off between the spatial and temporal resolution of satellite sensors, and to generate satellite images with high spatial and high temporal resolutions. This is achieved by fusing two types of satellite images, i.e., images with fine temporal but rough spatial resolution, and images with fine spatial but rough temporal resolution. Numerous STF methods have been proposed, however, it is still a challenge to predict both abrupt landcover change, and phenological change, accurately. Meanwhile, robustness to radiation differences between multi-source satellite images is crucial for the effective application of STF methods. Aiming to solve the abovementioned problems, in this paper we propose a hybrid deep learning-based STF method (HDLSFM). The method formulates a hybrid framework for robust fusion with phenological and landcover change information with minimal input requirements, and in which a nonlinear deep learning-based relative radiometric normalization, a deep learning-based superresolution, and a linear-based fusion are combined to address radiation differences between different types of satellite images, landcover, and phenological change prediction. Four comparative experiments using three popular STF methods, i.e., spatial and temporal adaptive reflectance fusion model (STARFM), flexible spatiotemporal data fusion (FSDAF), and Fit-FC, as benchmarks demonstrated the effectiveness of the HDLSFM in predicting phenological and landcover change. Meanwhile, HDLSFM is robust for radiation differences between different types of satellite images and the time interval between the prediction and base dates, which ensures its effectiveness in the generation of fused time-series data.

show abstract

Section: Introductionmentioning

confidence: 99%

A Hybrid Deep Learning-Based Spatiotemporal Fusion Method for Combining Satellite Images with Different Resolutions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Moreover, FSDAF has the ability to predict both gradual change and land cover type change (Zhu et al, 2016;Liu et al, 2019b). Following FSDAF, the enhanced FSDAF (EFSDAF), an improved FSDAF (IFSDAF), an enhanced FSDAF that incorporates subpixel class fraction change information (SFSDAF), and FSDAF 2.0 were later developed to overcome the limitations of FSDAF and improve the prediction accuracy (Liu et al, 2019b;Guo et al, 2020;X. Li et al, 2020;Shi et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…While above spatiotemporal fusion algorithms have ability to produce effective fusion result to a certain extent, they still face some challenges in practice. First, many existing spatiotemporal fusion methods, like ESTARFM, STAARCH and Bayesianbased methods need more than one low-and highresolution image pair as input data, which greatly limits the application scenarios of spatiotemporal fusion technology (Guo et al, 2020). Specifically, methods like ESTARFM cannot be used to do realtime processing due to it needs the data after the prediction phase.…”

Section: Introductionmentioning

confidence: 99%

An object-based spatiotemporal fusion model for remote sensing images

Hua

Sun

Shi

et al. 2021

European Journal of Remote Sensing

Self Cite

View full text Add to dashboard Cite

Spatiotemporal fusion technique can combine the advantages of temporal resolution and spatial resolution of different images to achieve continuous monitoring for the Earth's surface, which is a feasible solution to resolve the trade-off between the temporal and spatial resolutions of remote sensing images. In this paper, an object-based spatiotemporal fusion model (OBSTFM) is proposed to produce spatiotemporally consistent data, especially in areas experiencing non-shape changes (including phenology changes and land cover changes without shape changes). Considering different changes that might occur in different regions, multiresolution segmentation is first employed to produce segmented objects, and then a linear injection model is introduced to produce preliminary prediction. In addition, a new optimized strategy to select similar pixels is developed to obtain a more accurate prediction. The performance of proposed OBSTFM is validated using two remotely sensed dataset experiencing phenology changes in the heterogeneous area and land cover type changes, experimental results show that the proposed method is advantageous in such areas with non-shape changes, and has satisfactory robustness and reliability in blending large-scale abrupt land cover changes. Consequently, OBSTFM has great potential for monitoring highly dynamic landscapes.

show abstract

“…The recent rapid development of remote-sensing technology has played an increasingly important role in environmental-ecological studies concerning dynamic ecosystem changes [23,24]. Due to the limitations of the technology, most sensors of orbit satellites often cannot acquire a sufficient number of high spatiotemporal resolution images in a given period [25].…”

Section: Introductionmentioning

confidence: 99%

“…Based on the principles of data fusion, Guo et al [24] divided the spatiotemporal fusion models into five categories: learning-based, weight-function-based, Bayesian-based, hybrid, and unmixing-based methods. Their working principles can be found in the literature [33].…”

Section: Introductionmentioning

confidence: 99%

Feasibility of the Spatiotemporal Fusion Model in Monitoring Ebinur Lake’s Suspended Particulate Matter under the Missing-Data Scenario

et al. 2021

View full text Add to dashboard Cite

High-frequency monitoring of suspended particulate matter (SPM) concentration can improve water resource management. Missing high-resolution satellite images could hamper remote-sensing SPM monitoring. This study resolved the problem by applying spatiotemporal fusion technology to obtain high spatial resolution and dense time-series data to fill image-data gaps. Three data sources (MODIS, Landsat 8, and Sentinel 2) and two spatiotemporal fusion methods (the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) and the flexible spatiotemporal data fusion (FSDAF)) were used to reconstruct missing satellite images. We compared their fusion accuracy and verified the consistency of fusion images between data sources. For the fusion images, we used random forest (RF) and XGBoost as inversion methods and set “fusion first” and “inversion first” strategies to test the method’s feasibility in Ebinur Lake, Xinjiang, arid northwestern China. Our results showed that (1) the blue, green, red, and NIR bands of ESTARFM fusion image were better than FSDAF, with a good consistency (R2 ≥ 0.54) between the fused Landsat 8, Sentinel 2 images, and their original images; (2) the original image and fusion image offered RF inversion effect better than XGBoost. The inversion accuracy based on Landsat 8 and Sentinel 2 were R2 0.67 and 0.73, respectively. The correlation of SPM distribution maps of the two data sources attained a good consistency of R2 0.51; (3) in retrieving SPM from fused images, the “fusion first” strategy had better accuracy. The optimal combination was ESTARFM (Landsat 8)_RF and ESTARFM (Sentinel 2)_RF, consistent with original SPM maps (R2 = 0.38, 0.41, respectively). Overall, the spatiotemporal fusion model provided effective SPM monitoring under the image-absence scenario, with good consistency in the inversion of SPM. The findings provided the research basis for long-term and high-frequency remote-sensing SPM monitoring and high-precision smart water resource management.

show abstract

FSDAF 2.0: Improving the performance of retrieving land cover changes and preserving spatial details

Cited by 67 publications

References 33 publications

A Hybrid Deep Learning-Based Spatiotemporal Fusion Method for Combining Satellite Images with Different Resolutions

A Hybrid Deep Learning-Based Spatiotemporal Fusion Method for Combining Satellite Images with Different Resolutions

An object-based spatiotemporal fusion model for remote sensing images

Feasibility of the Spatiotemporal Fusion Model in Monitoring Ebinur Lake’s Suspended Particulate Matter under the Missing-Data Scenario

Contact Info

Product

Resources

About