Journal of Remote Sensing

A Hybrid Spatiotemporal Fusion Method for High Spatial Resolution Imagery: Fusion of Gaofen-1 and Sentinel-2 over Agricultural Landscapes Highlights: 1. This study proposes a novel spatiotemporal fusion method, the StarFusion model, designed to fuse Gaofen-1 and Sentinel-2 data to produce high spatial-temporal resolution images. 2. The StarFusion model combines deep learning-based super-resolution techniques and Partial Least Squares Regression (PLSR) models through an Edge and Color Weighted (ECW) loss function to achieve high fusion accuracy. 3. Experimental results indicate that the StarFusion model outperforms traditional spatiotemporal fusion methods (e.g., STARFM, FSDAF) and deep learning-based methods (e.g., SRGAN) in three different experimental sites, showing better overall performance and temporal transferability. 4. The StarFusion method holds significant potential for agricultural applications, providing high-quality high-resolution data for crop monitoring. https://lnkd.in/gT8NBNfu #Spatiotemporal #fusion #Highspatialresolution #image, #Gaofen-1 #DeepLearning

A new study indicates the attention mechanism, multi-scale feature fusion, physical knowledge and data-driven methods, and diffusion modeling can further enhance the impact of U-Net model in different ocean remote sensing tasks. https://lnkd.in/gY8suusS #AI #UNet #ocean #remotesensing

Recent advancements in satellite observation techniques and retrieval algorithms for tropospheric ozone have substantially enhanced product accuracy and spatial resolution, playing a crucial role in air quality management and pollution control, underscoring the need for ongoing innovation. (By Prof. Jian Xu). https://lnkd.in/gUpS-Wze #Troposphericozone #Satellite #remotesensing #Retrievalalgorithms

New paper out on using cameras and satellites to measure dryland grass and shrub responses to rainfall! https://lnkd.in/gYFfx83d Novel Use of Image Time-Series to Distinguish Dryland Vegetation Responses to Wet and Dry Years #RemoteSensing #drylands #phenology #PhenoCam #Harmonized #Landsat #Sentinel

Reconstructing Long-Term Synthetic Aperture Radar Backscatter in Urban Domains Using Landsat Time Series Data: A Case Study of Jing–Jin–Ji Region The framework for reconstructing SAR backscatter data from optical data offers a new insight to addressing the issue of missing multi-scale, long-term, and high-resolution backscatter data in urban studies. https://lnkd.in/eqmSTt5g #SAR #reconstruction #backscatter #coefficient #longterm #buildingheight #remotesensing #research #city #beijing

A new approach to the reconstruction of Clear-Sky Land Surface Temperature Vegetation Areas ----- Using Synthetic Aperture Radar, Digital Elevation Mode, and Machine Learning https://lnkd.in/gS4Pvvyv #LST #SAR #DEM #MachineLearning #remotesensing

Discover how cutting-edge drone technology and machine learning are revolutionizing the mapping and preservation of our vital coastal wetlands https://lnkd.in/guzQSef6 Narcisa Pricope #UncrewedAerialSystem #UAS #LiDAR #Multispectral #Hyperspatial #FunctionalWetlandClasses #Wetland

We're excited to share our latest publication in the Journal of Remote Sensing: 📄 "Predicting Foliar Nutrient Concentrations across Geologic Materials and Tree Genera in the Northeastern United States Using Spectral Reflectance and Partial Least Squares Regression Models" 🔬 This study explores the potential of spectral data (400 to 2450 nm) for rapid nutrient assessment in leaves and uncovering the geologic history of soils. By using Partial Least Squares Regression (PLSR), we've successfully estimated essential foliar macro- and micronutrients (Ca, Mg, K, P, Mn, and Zn) across diverse geologic materials and tree genera in the northeastern United States. 🌿 This innovative approach could revolutionize how we understand and manage forest health and soil fertility. Don't miss out on these groundbreaking findings! 🔗 Read the full article here： https://lnkd.in/gk7H47GA #remotesensing #spectraldata #foresthealth #soilscience #nutrientmanagement #environmentalresearch #scientificInnovation

🚀 Exciting News! The Journal of Remote Sensing, sponsored by the Aerospace Information Research Institute (AIR) under the Chinese Academy of Sciences, has achieved its first impact factor of 8.8, ranking fifth globally in the remote sensing field according to the latest Journal Citation Reports (JCR). 🌍📡 Since its launch in October 2020, this journal has rapidly gained recognition, being included in prestigious databases like Web of Science ESCI, Scopus, and more. It's the first partner journal in the remote sensing field of Science 👏🎉 [Link to the journal: https://lnkd.in/gmHsfuff] #RemoteSensing #ImpactFactor #ScientificResearch #ChineseAcademyOfSciences #Aerospace

Performance of XGBoost Ensemble Learning Algorithm for Mangrove Species Classification with Multisource Spaceborne Remote Sensing Data https://lnkd.in/gVgmb4S6 #learning #algorithms #remotesenisng #Mangrove #data #research