About this Research Topic
The application of advanced data analytics and geospatial technologies in soil management has rapidly increased. Geospatial technologies include remote/proximal soil sensing, the internet of things (IoT), machine learning (ML), and cloud computing, which are essential for soil management. More importantly, there is an increased demand for high-quality and reliable soil information systems for effective agricultural planning and management. The progress in proximal/remote sensing, ML, and cloud computing will considerably change and dominate the future of soil data collection, analysis, and management. Proximal soil sensing and spectroscopy combined with ML and advanced geospatial analysis, provide high-resolution soil layers. Besides, multi-sensor data fusion combined with ML methods is essential for accurately delineating management zones. The implementation of cloud computing offers a high-throughput method for efficiently storing, analyzing, and sharing geospatial data, allowing rapid mapping and monitoring of soil at the field and regional scales.
The rapid advancement of geospatial technologies in terms of speed, size, diversity, and complexity of digital data necessitates adaptation to existing processes in soil management. Therefore, it is critical to address the limitations of the current soil information system, and the implementation of advanced geospatial technologies, to build an intelligent geospatial system for sustainable soil management. This requires building a robust soil information system that transforms geospatial data into an accessible form. The application of the remarkable progress in geospatial technology–cloud computing–offers fast access and efficient use of big geospatial data. These data include optical/hyperspectral and radar remote sensing combined with ML, which allows better soil survey and mapping and better monitoring at the field and regional scales. Applying spectroscopy combined with ML is an alternative to traditional wet chemistry for soil properties and potentially toxic elements (PTEs) analysis and monitoring. Combined data fusion techniques with ML methods enhance the delineation of soil management zones for precision agriculture applications.
This Special Issue focuses on the potential of integrating advanced data analytics combined with geospatial technology, including remote and proximal sensing, to characterize soils' spatial variability for site-specific management. We invite submissions on basic and applied research concerning geospatial database, proximal soil sensing, remote sensing associated data, spectral, spatial, and temporal information based on multi- and hyperspectral imagery, combined with ML methods for soil analysis and management within-field variability. We also welcome submissions for review articles that provide an up-to-date overview of the current state of the art in various applications of proximal/remote sensing, combined with ML and cloud computing for proper soil analysis and management. In particular, research and literature articles may cover but are not limited to the following topics:
•Digital soil mapping
• Spectroscopy and ML for soil analysis
• Remote/proximal sensing for mapping soil contaminants
• Soil sensing and ML for delineation management zones
• Imaging spectroscopy for soil mapping and monitoring
• Cloud computing for mapping and monitoring soil contaminants
The rapid advancement of geospatial technologies in terms of speed, size, diversity, and complexity of digital data necessitates adaptation to existing processes in soil management. Therefore, it is critical to address the limitations of the current soil information system, and the implementation of advanced geospatial technologies, to build an intelligent geospatial system for sustainable soil management. This requires building a robust soil information system that transforms geospatial data into an accessible form. The application of the remarkable progress in geospatial technology–cloud computing–offers fast access and efficient use of big geospatial data. These data include optical/hyperspectral and radar remote sensing combined with ML, which allows better soil survey and mapping and better monitoring at the field and regional scales. Applying spectroscopy combined with ML is an alternative to traditional wet chemistry for soil properties and potentially toxic elements (PTEs) analysis and monitoring. Combined data fusion techniques with ML methods enhance the delineation of soil management zones for precision agriculture applications.
This Special Issue focuses on the potential of integrating advanced data analytics combined with geospatial technology, including remote and proximal sensing, to characterize soils' spatial variability for site-specific management. We invite submissions on basic and applied research concerning geospatial database, proximal soil sensing, remote sensing associated data, spectral, spatial, and temporal information based on multi- and hyperspectral imagery, combined with ML methods for soil analysis and management within-field variability. We also welcome submissions for review articles that provide an up-to-date overview of the current state of the art in various applications of proximal/remote sensing, combined with ML and cloud computing for proper soil analysis and management. In particular, research and literature articles may cover but are not limited to the following topics:
•Digital soil mapping
• Spectroscopy and ML for soil analysis
• Remote/proximal sensing for mapping soil contaminants
• Soil sensing and ML for delineation management zones
• Imaging spectroscopy for soil mapping and monitoring
• Cloud computing for mapping and monitoring soil contaminants
Keywords: Remote Sensing, Proximal Sensing, Precision Agriculture, Machine Learning, Data Fusion, Big Data, Cloud Computing
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
