A robust adaptive spatial and temporal image fusion model for complex land surface changes

A key challenge in developing models for the fusion of surface reflectance data across multiple satellite sensors is ensuring that they apply to both gradual vegetation phenological dynamics and abrupt land surface changes. To better model land cover spatial and temporal changes, we proposed previously a Prediction Smooth Reflectance Fusion Model (PSRFM) that combines a dynamic prediction model based on the linear spectral mixing model with a smoothing filter corresponding to the weighted average of forward and backward temporal predictions. One of the significant advantages of PSRFM is that PSRFM can model abrupt land surface changes either through optimized clusters or the residuals of the predicted gradual changes. In this paper, we expanded our approach and developed more efficient methods for clustering. We applied the new methods for dramatic land surface changes caused by a flood and a forest fire. Comparison of the model outputs showed that the new methods can capture the land surface changes more effectively. We also compared the improved PSRFM to two most popular reflectance fusion algorithms: Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) and Enhanced version of STARFM (ESTARFM). The results showed that the improved PSRFM is more effective and outperforms STARFM and ESTARFM both visually and quantitatively.

Download Full-text

Scaling Effect of Fused ASTER-MODIS Land Surface Temperature in an Urban Environment

Sensors ◽

10.3390/s18114058 ◽

2018 ◽

Vol 18 (11) ◽

pp. 4058 ◽

Cited By ~ 5

Author(s):

Hua Liu ◽

Qihao Weng

Keyword(s):

Los Angeles ◽

Image Fusion ◽

Land Surface ◽

Nearest Neighbor ◽

Thermal Emission ◽

Thermal Studies ◽

Urban Heat Islands ◽

Bilinear Interpolation ◽

Fusion Model ◽

Resampling Methods

There is limited research in land surface temperatures (LST) simulation using image fusion techniques, especially studies addressing the downscaling effect of LST image fusion. LST simulation and associated downscaling effect can potentially benefit the thermal studies requiring both high spatial and temporal resolutions. This study simulated LSTs based on observed Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Terra Moderate Resolution Imaging Spectroradiometer (MODIS) LST imagery with Spatial and Temporal Adaptive Reflectance Fusion Model, and investigated the downscaling effect of LST image fusion at 15, 30, 60, 90, 120, 250, 500, and 1000 m spatial resolutions. The study area partially covered the City of Los Angeles, California, USA, and surrounding areas. The reference images (observed ASTER and MODIS LST imagery) were acquired on 04/03/2007 and 07/01/2007, with simulated LSTs produced for 4/28/2007. Three image resampling methods (Cubic Convolution, Bilinear Interpolation, and Nearest Neighbor) were used during the downscaling and upscaling processes, and the resulting LST simulations were compared. Results indicated that the observed ASTER LST and simulated ASTER LST images (date 04/28/2007, spatial resolution 90 m) had high agreement in terms of spatial variations and basic statistics based on a comparison between the observed and simulated ASTER LST maps. Urban developed lands possessed higher LSTs with lighter tones and mountainous areas showed dark tones with lower LSTs. The Cubic Convolution and Bilinear Interpolation resampling methods yielded better results over Nearest Neighbor resampling method across the scales from 15 to 1000 m. The simulated LSTs with image fusion can be used as valuable inputs in heat related studies that require frequent LST measurements with fine spatial resolutions, e.g., seasonal movements of urban heat islands, monthly energy budget assessment, and temperature-driven epidemiology. The observation of scale-independency of the proposed image fusion method can facilitate with image selections of LST studies at various locations.

Download Full-text

Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients

npj Precision Oncology ◽

10.1038/s41698-021-00205-z ◽

2021 ◽

Vol 5 (1) ◽

Author(s):

Jing Yan ◽

Bin Zhang ◽

Shuaitong Zhang ◽

Jingliang Cheng ◽

Xianzhi Liu ◽

...

Keyword(s):

Image Fusion ◽

Molecular Subtypes ◽

Progression Free Survival ◽

Quantitative Mri ◽

Promoter Mutation ◽

Fusion Model ◽

Free Survival ◽

Contrast Enhanced ◽

Apparent Diffusion ◽

The Status

AbstractGliomas can be classified into five molecular groups based on the status of IDH mutation, 1p/19q codeletion, and TERT promoter mutation, whereas they need to be obtained by biopsy or surgery. Thus, we aimed to use MRI-based radiomics to noninvasively predict the molecular groups and assess their prognostic value. We retrospectively identified 357 patients with gliomas and extracted radiomic features from their preoperative MRI images. Single-layered radiomic signatures were generated using a single MR sequence using Bayesian-regularization neural networks. Image fusion models were built by combing the significant radiomic signatures. By separately predicting the molecular markers, the predictive molecular groups were obtained. Prognostic nomograms were developed based on the predictive molecular groups and clinicopathologic data to predict progression-free survival (PFS) and overall survival (OS). The results showed that the image fusion model incorporating radiomic signatures from contrast-enhanced T1-weighted imaging (cT1WI) and apparent diffusion coefficient (ADC) achieved an AUC of 0.884 and 0.669 for predicting IDH and TERT status, respectively. cT1WI-based radiomic signature alone yielded favorable performance in predicting 1p/19q status (AUC = 0.815). The predictive molecular groups were comparable to actual ones in predicting PFS (C-index: 0.709 vs. 0.722, P = 0.241) and OS (C-index: 0.703 vs. 0.751, P = 0.359). Subgroup analyses by grades showed similar findings. The prognostic nomograms based on grades and the predictive molecular groups yielded a C-index of 0.736 and 0.735 in predicting PFS and OS, respectively. Accordingly, MRI-based radiomics may be useful for noninvasively detecting molecular groups and predicting survival in gliomas regardless of grades.

Download Full-text

Two Optical Image Fusion Model of Transmission Line Based on DCGAN

2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2) ◽

10.1109/ei250167.2020.9347296 ◽

2020 ◽

Author(s):

Zhibo Jiang ◽

Hantao Tao ◽

Yue Chen ◽

Lei Zhang ◽

Dawei Wu ◽

...

Keyword(s):

Transmission Line ◽

Image Fusion ◽

Optical Image ◽

Fusion Model

Download Full-text

Spatiotemporal image fusion in Google Earth Engine for annual estimates of land surface phenology in a heterogenous landscape

International Journal of Applied Earth Observation and Geoinformation ◽

10.1016/j.jag.2021.102323 ◽

2021 ◽

Vol 99 ◽

pp. 102323

Author(s):

Ty C. Nietupski ◽

Robert E. Kennedy ◽

Hailemariam Temesgen ◽

Becky K. Kerns

Keyword(s):

Image Fusion ◽

Land Surface ◽

Google Earth ◽

Land Surface Phenology ◽

Google Earth Engine

Download Full-text

Role of Land-Surface Changes in Arctic Summer Warming

Science ◽

10.1126/science.1117368 ◽

2005 ◽

Vol 310 (5748) ◽

pp. 657-660 ◽

Cited By ~ 875

Author(s):

F. S. Chapin

Keyword(s):

Land Surface ◽

Summer Warming ◽

Arctic Summer ◽

Surface Changes

Download Full-text

Two parameters are required for a Budyko function to describe the land-atmosphere interaction

10.5194/egusphere-egu21-3554 ◽

2021 ◽

Author(s):

Daeha Kim ◽

Jong Ahn Chun

Keyword(s):

Land Surface ◽

River Basins ◽

Control Surface ◽

Primary Control ◽

Evaporative Demand ◽

Atmosphere Interaction ◽

The Mean ◽

Two Parameters ◽

Two Parameter ◽

Surface Changes

While the Budyko framework has been a simple and convenient tool to assess runoff (Q) responses to climatic and surface changes, it has been unclear how parameters of a Budyko function represent the vertical land-atmosphere interactions. Here, we explicitly derived a two-parameter equation by correcting a boundary condition of the Budyko hypothesis. The correction enabled for the Budyko function to reflect the evaporative demand (Ep) that actively responds to soil moisture deficiency. The derived two-parameter function suggests that four physical variables control surface runoff; namely, precipitation (P), potential evaporation (Ep), wet-environment evaporation (Ew), and the catchment properties (n). We linked the derived Budyko function to a definitive complementary evaporation principle, and assessed the relative elasticities of Q to climatic and land surface changes. Results showed that P is the primary control of runoff changes in most of river basins across the world, but its importance declined with climatological aridity. In arid river basins, the catchment properties play a major role in changing runoff, while changes in Ep and Ew seem to exert minor influences on Q changes. It was also found that the two-parameter Budyko function can capture unusual negative correlation between the mean annual Q and Ep. This work suggests that at least two parameters are required for a Budyko function to properly describe the vertical interactions between the land and the atmosphere.

Download Full-text

RASF and DEDR-POCS Image Fusion through Multi-layer Perceptron in SAR Imagery Systems

Journal of Computational Systems and ICTs ◽

10.35429/jcsi.2019.16.5.20.26 ◽

2019 ◽

pp. 20-26

Author(s):

Israel Yañez-Vargas ◽

Joel Quintanilla-Domínguez ◽

Gabriel Aguilera-Gonzalez

Keyword(s):

Synthetic Aperture Radar ◽

Image Fusion ◽

Low Cost ◽

Synthetic Aperture ◽

Discrete Wavelet ◽

Multi Layer Perceptron ◽

Robust Adaptive ◽

Sar Imagery ◽

Design Regularization ◽

Aperture Radar

This paper presents a novel multi-layer perceptron (MLP) based image fusion technique, which fuses two synthetic aperture radar (SAR) images, obtained from the same spatial reflectivity map, acquired with a conventional low-cost fractional synthetic aperture radar (Fr-SAR) system, enhanced via two different methodologies. The first image is enhanced using the traditional descriptive experiment design regularization (DEDR) framework through the projection onto convex solution sets (POCS) method; the second image is enhanced with the DEDR framework by incorporating the robust adaptive spatial filtering (RASF) solution operator. This work describes a MLP based technique applied to the pixel level multi-focus fusion problem characterized by the use of image windows with the idea of reducing noise and determining which pixel is clearer between the two images. Experimental results show that the proposed novel method outperforms the discrete wavelet transform based most competing approach.

Download Full-text