Understanding the potential, uncertainties, and limitations of spatio-temporal fusion for monitoring chlorophyll-a concentration in inland eutrophic lakes DOI Creative Commons
Linwei Yue, Lei Zhang, Rui Peng

et al.

Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 4

Published: Jan. 1, 2024

The tradeoffs between the spatial and temporal resolutions for remote sensing instruments limit their capacity to monitor eutrophic status of inland lakes. Spatiotemporal fusion (STF) provides a cost-effective way obtain data with both high by blending multisensor observations. However, reflectance ( R rs ) over water surface relatively low signal-to-noise ratio is prone be contaminated large uncertainties in process. To present comprehensive analysis on influence processing modeling errors, we conducted an evaluation study understand potential, uncertainties, limitations using STF monitoring chlorophyll (Chla) concentration (Chaohu Lake, China). Specifically, comparative tests were Sentinel-2 Sentinel-3 image pairs. Three typical methods selected comparison, i.e., Fit-FC, nonlocal filter-based model, flexible spatiotemporal fusion. results show as follows: (a) among influencing factors, atmospheric correction geometric misregistration have larger impacts results, compared radiometric bias imaging sensors errors; (b) machine-learning-based Chla inversion accuracy [ 2 = 0.846 root mean square error (RMSE) 17.835 μg/l] comparable that real 0.856 RMSE 16.601 μg/l), temporally dense can produced integrated datasets. These findings will help provide guidelines design framework aquatic environment waters data.

Language: Английский

Deep learning in multimodal remote sensing data fusion: A comprehensive review DOI Creative Commons
Jiaxin Li, Danfeng Hong, Lianru Gao

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2022, Volume and Issue: 112, P. 102926 - 102926

Published: July 26, 2022

With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity are readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications fresh way. joint utilization EO data, much research on multimodal RS fusion has made tremendous progress recent years, yet these developed traditional algorithms inevitably meet performance bottleneck due lack ability comprehensively analyze interpret strongly heterogeneous data. Hence, this non-negligible limitation further arouses intense demand for alternative tool with powerful processing competence. Deep learning (DL), as cutting-edge witnessed remarkable breakthroughs numerous computer vision tasks owing its impressive representation reconstruction. Naturally, it been successfully applied field fusion, yielding improvement compared methods. This survey aims present systematic overview DL-based fusion. More specifically, some essential knowledge about topic is first given. Subsequently, literature conducted trends field. Some prevalent sub-fields then reviewed terms to-be-fused modalities, i.e., spatiospectral, spatiotemporal, light detection ranging-optical, synthetic aperture radar-optical, RS-Geospatial Big Data Furthermore, We collect summarize valuable resources sake development Finally, remaining challenges potential future directions highlighted.

Language: Английский

Citations

309
Inferring Radiometric Quality of Multispectral Airborne Laser Scanning Data DOI
Xinghua Cheng, Wai Yeung Yan

Journal of Geovisualization and Spatial Analysis, Journal Year: 2025, Volume and Issue: 9(1)

Published: Jan. 28, 2025

Language: Английский

Citations

2
Mapping understory plant communities in deciduous forests from Sentinel-2 time series DOI Creative Commons
Xiucheng Yang, Shi Qiu, Zhe Zhu

et al.

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 293, P. 113601 - 113601

Published: May 4, 2023

Language: Английский

Citations

37
ROBOT: A spatiotemporal fusion model toward seamless data cube for global remote sensing applications DOI
Shuang Chen, Jie Wang, Peng Gong

et al.

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 294, P. 113616 - 113616

Published: May 20, 2023

Language: Английский

Citations

32
Challenges in remote sensing of vegetation phenology DOI Creative Commons
Miaogen Shen,

Wei Zhao,

Nan Jiang

et al.

The Innovation Geoscience, Journal Year: 2024, Volume and Issue: 2(2), P. 100070 - 100070

Published: Jan. 1, 2024

Language: Английский

Citations

16
Improved field-scale drought monitoring using MODIS and Sentinel-2 data for vegetation temperature condition index generation through a fusion framework DOI
Mingqi Li, Pengxin Wang, Kevin Tansey

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 234, P. 110256 - 110256

Published: March 9, 2025

Language: Английский

Citations

1
Enhanced wavelet based spatiotemporal fusion networks using cross-paired remote sensing images DOI
Xingjian Zhang, Shuang Li, Zhenyu Tan

et al.

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2024, Volume and Issue: 211, P. 281 - 297

Published: April 17, 2024

Language: Английский

Citations

7
Using Enhanced Gap-Filling and Whittaker Smoothing to Reconstruct High Spatiotemporal Resolution NDVI Time Series Based on Landsat 8, Sentinel-2, and MODIS Imagery DOI Creative Commons

Jieyu Liang,

Chao Ren, Yi Li

et al.

ISPRS International Journal of Geo-Information, Journal Year: 2023, Volume and Issue: 12(6), P. 214 - 214

Published: May 23, 2023

Normalized difference vegetation index (NDVI) time series data, derived from optical images, play a crucial role for crop mapping and growth monitoring. Nevertheless, images frequently exhibit spatial temporal discontinuities due to cloudy rainy weather conditions. Existing algorithms reconstructing NDVI using multi-source remote sensing data still face several challenges. In this study, we proposed novel method, an enhanced gap-filling Whittaker smoothing (EGF-WS), reconstruct (EGF-NDVI) Google Earth Engine. EGF-WS, calculated MODIS, Landsat-8, Sentinel-2 satellites were combined generate high-resolution continuous data. The MODIS was employed as reference fill missing pixels in the Sentinel–Landsat (SL-NDVI) method. Subsequently, filled smoothed filter reduce residual noise SL-NDVI series. With all-round performance assessment (APA) metrics, of EGF-WS compared with conventional Savitzky–Golay approach (GF-SG) Fusui County Guangxi Zhuang Autonomous Region. experimental results have demonstrated that can capture more accurate details GF-SG. Moreover, EGF-NDVI exhibited low root mean square error (RMSE) high coefficient determination (R2). conclusion, holds significant promise providing resolution 10 m 8 days, thereby benefiting mapping, land use change monitoring, various ecosystems, among other applications.

Language: Английский

Citations

17
Agri-Fuse: A novel spatiotemporal fusion method designed for agricultural scenarios with diverse phenological changes DOI

Zhuoning Gu,

Jin Chen, Yang Chen

et al.

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 299, P. 113874 - 113874

Published: Oct. 27, 2023

Language: Английский

Citations

15
FastVSDF: An Efficient Spatiotemporal Data Fusion Method for Seamless Data Cube DOI
Chen Xu, Xiaoping Du,

Xiangtao Fan

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2024, Volume and Issue: 62, P. 1 - 22

Published: Jan. 1, 2024

Spatiotemporal data fusion provides an efficacious strategy for addressing gaps within time series datasets. This approach significantly enhances the feasibility of large-scale remote sensing applications by, example, enabling creation seamless Data Cubes (SDC). Nevertheless, strict input requirements and low computational efficiency current methods severely limit practicality SDC production. In this study, we propose efficient spatiotemporal method, Fast Variation-based Fusion (FastVSDF) method. FastVSDF consists 3 steps, i.e., unmixing, distributing global residuals, local residuals. unmixing process, introduces fast abundant variation classification (FAVC) to mitigate sample imbalance expedite unsupervised classification. Then, in-class Gaussian weight function is introduced accelerate distribution residuals by considering introduce information on spectral similarity. Besides, employs Guided Filter combat "block artifacts" efficiently. Results show that demonstrated superior performance over Fit-FC, STARFM, RASDF, FSDAF. More importantly, yields a remarkable improvement in efficiency, reducing predicting 43 573 times. As practical application, generated Sentinel-2 Yangtze River Basin, China. The process single period's Basin dataset was accomplished 20 minutes, with average 3.85 seconds each scene. Comprehensively accuracy, feasibility, universality, demonstrates potential constructing long-term SDC. Our code will be publicly available at https://github.com/ChenXuAxel/FastVSDF.

Language: Английский

Citations

6