Article
Environmental Sciences
Jianxin Jia, Changhui Jiang, Wei Li, Haohao Wu, Yuwei Chen, Peilun Hu, Hui Shao, Shaowei Wang, Fan Yang, Eetu Puttonen, Juha Hyyppa
Summary: A hyperspectral LiDAR with wide-range wavelength was developed for vegetation spectral data acquisition, parameter extraction, and classification, showing great potential in precision agriculture application.
Article
Computer Science, Artificial Intelligence
Lihui Chen, Gemine Vivone, Jiayi Qin, Jocelyn Chanussot, Xiaomin Yang
Summary: In this article, a spectral-spatial transformer (SST) is proposed to explore the potential of transformers for hyperspectral (HS) and multispectral (MS) image fusion. The SST blocks are used to extract spectral and spatial features from HS and MS images, respectively, to capture the long-range dependence. The fused features are then utilized to reconstruct a high-resolution (HR) HS image, achieving superior performance compared to state-of-the-art methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xingqian Du, Xiangtao Zheng, Xiaoqiang Lu, Xin Wang
Summary: The study proposes a spectral-spatial graph network to integrate HSI and LiDAR data, capturing local and global spectral-spatial associations. The experiments demonstrate that the network achieves comparable performance to state-of-the-art methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Plant Sciences
Hibiki M. Noda, Hiroyuki Muraoka, Kenlo Nishida Nasahara
Summary: This paper reviews how plant ecophysiological processes affect optical properties of forest canopy and how optical remote sensing by Earth-observation satellites can measure these properties. It discusses the use of spectral reflectance measured by optical remote sensing to estimate the structure and productivity of canopy. The understanding of the relationship between plant ecophysiological processes and optical properties is essential for gaining ecophysiological information from satellite images at the landscape level.
JOURNAL OF PLANT RESEARCH
(2021)
Article
Geochemistry & Geophysics
Haishi Zhao, Lorenzo Bruzzone, Renchu Guan, Fengfeng Zhou, Chen Yang
Summary: Band selection using genetic algorithms can improve hyperspectral image classification by reducing redundancy and maximizing discriminability of selected bands. The proposed unsupervised approach outperforms traditional supervised methods by combining Fisher score and superpixel information for evaluating band subsets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Ge Zhang, Shaohui Mei, Yan Feng, Qian Du
Summary: This study introduces a spectral-spatial constrained unmixing method based on nonnegative matrix factorization (NMF), which improves the performance of unmixing by imposing spatial and spectral constraints. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of the proposed method in comparison to state-of-the-art NMF-based unmixing algorithms.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Jun Wang, Chang Tang, Xiao Zheng, Xinwang Liu, Wei Zhang, En Zhu
Summary: This paper proposes a graph regularized spatial-spectral subspace clustering method (GRSC) for hyperspectral band selection. The method preserves the spatial information of hyperspectral images through superpixel segmentation and generates discriminative latent features to represent the bands. It explores spectral correlation using a self representation subspace clustering model and regularization, and learns a similarity graph between region-aware latent features to preserve the spatial structure of the images.
Article
Environmental Sciences
Xizhen Han, Zhengang Jiang, Yuanyuan Liu, Jian Zhao, Qiang Sun, Yingzhi Li
Summary: The study proposed a spatial-spectral combination method for hyperspectral band selection (SSCBS) to reduce information redundancy in hyperspectral images. By dividing the image into subspaces, selecting the best band and constructing weight coefficients, the SSCBS approach achieved the highest classification accuracy on three benchmark datasets.
Article
Geochemistry & Geophysics
Mingyang Ma, Shaohui Mei, Fan Li, Yaoyang Ge, Qian Du
Summary: This article proposes a spectral correlation-based diverse band selection method for hyperspectral images, which improves the representativeness and diversity of the selected bands by utilizing spectral correlations. The method uses a correlation-derived weight for weighted sparse reconstruction to select bands that are more correlated with the whole HSI, and a correlation minimization term to remove highly correlated bands. Additionally, an adjustable sparse constraint is imposed by using an l(2,0<p<=1) norm. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods in HSI classification.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Weiying Xie, Jiaqing Zhang, Jie Lei, Yunsong Li, Xiuping Jia
Summary: In this paper, a spectral-spatial target detection framework in deep latent space based on self-spectral learning and spectral generative adversarial network technologies is proposed. A novel structure-to-structure selection rule is introduced to generate the optimal spectral band subset, improving the performance of target detection.
Article
Geochemistry & Geophysics
Xiaodi Shang, Chuanyu Cui, Xudong Sun
Summary: Due to the redundancy and sparsity of hyper spectral data, sparse representation (SR) is suitable for hyperspectral band selection (BS) and incorporating local structural information through graph regularizers can enhance SR. However, existing unsupervised BS approaches typically use a simple graph, while the hypergraph can better capture band adjacencies. This letter proposes a hypergraph-regularized self-representation (HyGSR) model for BS, which combines spectral similarity and band index as a new metric and utilizes a robust l(2,1)-norm for sparse properties. Experimental results on real hyperspectral data confirm the superiority of HyGSR over other competitors in terms of stability and usability.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Jing Hu, Yujing Zhang, Minghua Zhao, Peng Li
Summary: A novel hyperspectral anomaly detection method is proposed in this paper, which increases the discriminability from the spectral domain by eliminating redundant and noisy bands and highlights anomalies by eliminating the clustered result. The method effectively detects anomalies in hyperspectral images through spatial-spectral extraction.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Siyuan Hao, Yufeng Xia, Lijian Zhou, Yuanxin Ye, Wei Wang
Summary: In this study, a spectral and spatial feature fusion module (TransCNN) is proposed for hyperspectral image classification (HIC). By combining the advantages of CNN and Transformer, TransCNN can effectively extract spectral-spatial information and correlation of the three dimensions. Experimental results demonstrate that the proposed module achieves competitive performance on real hyperspectral images.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Sasha J. Kramer, David A. Siegel, Stephane Maritorena, Dylan Catlett
Summary: This study utilized hyperspectral remote sensing data to model phytoplankton pigment composition in the global open ocean. By using optimized principal components regression modeling, thirteen phytoplankton pigments representing five groups were successfully reconstructed. This work advances the development of global spectral models for phytoplankton pigment composition, but more high-quality data is needed for further improvement.
REMOTE SENSING OF ENVIRONMENT
(2022)
Editorial Material
Environmental Sciences
Andrew F. F. Feldman, Daniel J. Short J. Gianotti, Jianzhi Dong, Ruzbeh Akbar, Wade T. T. Crow, Kaighin A. A. McColl, Alexandra G. G. Konings, Jesse B. B. Nippert, Shersingh Joseph Tumber-Davila, Noel M. M. Holbrook, Fulton E. E. Rockwell, Russell L. L. Scott, Rolf H. H. Reichle, Abhishek Chatterjee, Joanna Joiner, Benjamin Poulter, Dara Entekhabi
Summary: A commonly expressed viewpoint is that satellite L-band measurements of global soil moisture only represent surface moisture and thus have limited value for studying global terrestrial ecosystems. However, based on peer-reviewed literature, this viewpoint is overly limiting. Microwave soil emission depth considerations and isotopic tracer field studies suggest that L-band measurements provide information about soil moisture beyond the commonly referenced 5 cm. Additionally, most vegetation, including grasslands and croplands, primarily draw moisture from the upper soil layers, making L-band satellite soil moisture estimates relevant for global vegetation water uptake.
WATER RESOURCES RESEARCH
(2023)
Article
Environmental Sciences
Itiya Aneece, Howard Epstein
Article
Remote Sensing
Itiya Aneece, Howard Epstein
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2017)
Article
Environmental Sciences
Itiya Aneece, Prasad Thenkabail
Article
Geography, Physical
Daniel J. Foley, Prasad S. Thenkabail, Itiya P. Aneece, Pardhasaradhi G. Teluguntla, Adam J. Oliphant
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2020)
Article
Engineering, Electrical & Electronic
Itiya Aneece, Daniel Foley, Prasad Thenkabail, Adam Oliphant, Pardhasaradhi Teluguntla
Summary: Thoroughly investigating the characteristics of new generation hyperspectral and high spatial resolution spaceborne sensors will advance the study of agricultural crops. The study compared the performances of hyperspectral DESIS and high spatial resolution PlanetScope in classifying eight crop types in California's Central Valley. The results showed that hyperspectral data outperformed high spatial resolution data in crop type classification. However, high spatial resolution data remains invaluable in assessing within-field variability and crop biophysical/biochemical modeling in precision agriculture.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)