Remote sensing has a vital role in environmental monitoring and analysis. Among modern remote sensing techniques, hyperspectral imaging is a prominent tool in environmental science application areas. Hyperspectral sensors can acquire spectrally rich information from the scene that helps identify different materials effectively. Providing precise, high-resolution datasets of hyperspectral images along with data fusion strategies can fill the gap between sparse field observations and coarse resolution spaceborne images. It also enables real-time analysis and decision-making in many environmental mapping and monitoring contexts. Optimal bands selection, classification, segmentation, spectral unmixing, target detection, and anomaly and change detection are some common tasks in applications of hyperspectral imaging. The synergistic combination of deep learning models and large-scale hyperspectral images promises significant advances in Earth observation.
With the rapid development of imaging sensors, hyperspectral data have been successfully applied to a plethora of applications, e.g., environmental monitoring, precision agriculture, and climate change. Recently, different airborne and spaceborne hyperspectral sensors have been developed such as already launched or planned to launch PRISMA, EnMAP, HyspIRI, Hyperion (EO-1), and Copernicus Hyperspectral Imaging Mission for The Environment (CHIME). The key goal of this Research Topic is to advance sophisticated hyperspectral imaging methodologies to ensure sustainable development of the economy and society. Some of the main challenges to tackle are hyperspectral sensor technology development to design robust low-cost hyperspectral imagers, integration and fusion of different remote sensing datasets for example hyperspectral imaging and microwave remote sensing datasets, and addressing uncertainty in ecological parameters. The key to the success of the aforementioned applications is studies on hyperspectral data processing using multivariate statistics and artificial intelligence such as machine learning and deep learning.
The aim of this Research Topic is to cover recent advances in hyperspectral imaging for environmental monitoring and analysis, including novel data processing algorithms, development, and interpretation of hyperspectral datasets. This Research Topic welcomes both original research and review articles related to hyperspectral imaging technology in diversified areas of environmental science. The main topics of this Research Topic are, but are not limited to, the following areas:
Hyperspectral Imaging Technologies and Applications:
• Precision agriculture, crop science, and phenotyping
• Natural resources (forestry, wetlands, geology, coastal regions, snow, ice, etc.)
• Hyperspectral aquatic (underwater) remote sensing
• Hyperspectral microwave remote sensing
• Proximal and UAV-based hyperspectral imaging
• Airplane-Based and Satellite-Based Hyperspectral Imaging
• Pollution and particulate monitoring (trace gases, forensics)
• Extreme environment monitoring
• Hyperspectral imaging in climate change and ecosystem modeling
• Survey and comparison study of recent technologies in hyperspectral imaging
Hyperspectral Data Processing Algorithms:
• Pre-Processing of Hyperspectral Images
• Dimensionality reduction and feature extraction methods
• Hyperspectral image classification and segmentation
• Hyperspectral mixed pixel analysis and endmember extraction algorithms
• Hyperspectral target detection methods
• Hyperspectral data fusion and decision-making strategies
• Machine learning and deep learning algorithms for hyperspectral imaging
• Survey and comparison study of recent developments in the hyperspectral data processing
Remote sensing has a vital role in environmental monitoring and analysis. Among modern remote sensing techniques, hyperspectral imaging is a prominent tool in environmental science application areas. Hyperspectral sensors can acquire spectrally rich information from the scene that helps identify different materials effectively. Providing precise, high-resolution datasets of hyperspectral images along with data fusion strategies can fill the gap between sparse field observations and coarse resolution spaceborne images. It also enables real-time analysis and decision-making in many environmental mapping and monitoring contexts. Optimal bands selection, classification, segmentation, spectral unmixing, target detection, and anomaly and change detection are some common tasks in applications of hyperspectral imaging. The synergistic combination of deep learning models and large-scale hyperspectral images promises significant advances in Earth observation.
With the rapid development of imaging sensors, hyperspectral data have been successfully applied to a plethora of applications, e.g., environmental monitoring, precision agriculture, and climate change. Recently, different airborne and spaceborne hyperspectral sensors have been developed such as already launched or planned to launch PRISMA, EnMAP, HyspIRI, Hyperion (EO-1), and Copernicus Hyperspectral Imaging Mission for The Environment (CHIME). The key goal of this Research Topic is to advance sophisticated hyperspectral imaging methodologies to ensure sustainable development of the economy and society. Some of the main challenges to tackle are hyperspectral sensor technology development to design robust low-cost hyperspectral imagers, integration and fusion of different remote sensing datasets for example hyperspectral imaging and microwave remote sensing datasets, and addressing uncertainty in ecological parameters. The key to the success of the aforementioned applications is studies on hyperspectral data processing using multivariate statistics and artificial intelligence such as machine learning and deep learning.
The aim of this Research Topic is to cover recent advances in hyperspectral imaging for environmental monitoring and analysis, including novel data processing algorithms, development, and interpretation of hyperspectral datasets. This Research Topic welcomes both original research and review articles related to hyperspectral imaging technology in diversified areas of environmental science. The main topics of this Research Topic are, but are not limited to, the following areas:
Hyperspectral Imaging Technologies and Applications:
• Precision agriculture, crop science, and phenotyping
• Natural resources (forestry, wetlands, geology, coastal regions, snow, ice, etc.)
• Hyperspectral aquatic (underwater) remote sensing
• Hyperspectral microwave remote sensing
• Proximal and UAV-based hyperspectral imaging
• Airplane-Based and Satellite-Based Hyperspectral Imaging
• Pollution and particulate monitoring (trace gases, forensics)
• Extreme environment monitoring
• Hyperspectral imaging in climate change and ecosystem modeling
• Survey and comparison study of recent technologies in hyperspectral imaging
Hyperspectral Data Processing Algorithms:
• Pre-Processing of Hyperspectral Images
• Dimensionality reduction and feature extraction methods
• Hyperspectral image classification and segmentation
• Hyperspectral mixed pixel analysis and endmember extraction algorithms
• Hyperspectral target detection methods
• Hyperspectral data fusion and decision-making strategies
• Machine learning and deep learning algorithms for hyperspectral imaging
• Survey and comparison study of recent developments in the hyperspectral data processing
