Uav Remote Sensing For Plant Traits And Stress

Written by leading global experts, including pioneers in the field, the four-volume set on Hyperspectral Remote Sensing of Vegetation, Second Edition, reviews existing stateof- the-art knowledge, highlights advances made in different areas, and provides guidance for the appropriate use of hyperspectral data in the study and management of agricultural crops and natural vegetation. Hyperspectral remote sensing or imaging spectroscopy data has been increasingly used in studying and assessing the biophysical and biochemical properties of agricultural crops and natural vegetation. Volume III, Biophysical and Biochemical Characterization and Plant Species Studies demonstrates the methods that are developed and used to study terrestrial vegetation using hyperspectral data. This volume includes extensive discussions on hyperspectral data processing and how to implement data processing mechanisms for specific biophysical and biochemical applications such as crop yield modeling, crop biophysical and biochemical property characterization, and crop moisture assessments. The concluding chapter provides readers with useful guidance on the highlights and essence of Volume III through the editors’ perspective. Key Features of Volume III: Covers recent abilities to better quantify, model, and map plant biophysical, biochemical water, and structural properties. Demonstrates characteristic hyperspectral properties through plant diagnostics or throughput phenotyping of plant biophysical, biochemical, water, and structural properties. Establishes plant traits through hyperspectral imaging spectroscopy data as well as its integration with other data, such as LiDAR, using data from various platforms (ground-based, UAVs, and earth-observing satellites). Studies photosynthetic efficiency and plant health and stress through hyperspectral narrowband vegetation indices. Uses hyperspectral data to discriminate plant species and\or their types as well as their characteristics, such as growth stages. Compares studies of plant species of agriculture, forests, and other land use\land cover as established by hyperspectral narrowband data versus multispectral broadband data. Discusses complete solutions from methods to applications, inventory, and modeling considering various platform (e.g., earth-observing satellites, UAVs, handheld spectroradiometers) from where the data is gathered. Dwells on specific applications to detect and map invasive species by using hyperspectral data.

Machine vision applications in precision agriculture have attracted a great deal of attention. They focus on monitoring, protection, and management of various plant populations. These applications have shown potential value in reforming crucial components of plant production, including fine-grained ripeness recognition of all kinds of plants and detecting and classifying weeds, seeds, and pests for crop health, quality, and quantity enhancement. In recent decades, the extensive achievements of deep learning techniques have shown significant opportunities for almost all fields. Accordingly, many deep learning models have been presented for different types of images and have achieved promising outcomes. The deep learning-based approaches can contribute to gaining insights into the plants' inherent characteristics and the surrounding environmental elements. This research topic's primary value is providing a platform for deep learning-based applications for precision agriculture. These applications can be fairly evaluated and compared with each other. Accordingly, more effective and efficient detection and classification approaches for precision agriculture can be developed or optimized.

The advances in unmanned aerial vehicle (UAV) platforms and onboard sensors in the past few years have greatly increased our ability to monitor and map crops. The ability to register images at ultrahigh spatial resolution at any moment has made remote sensing techniques increasingly useful in crop management. These technologies have revolutionized the way in which remote sensing is applied in precision agriculture, allowing for decision-making in a matter of days instead of weeks. However, it is still necessary to continue research to improve and maximize the potential of UAV remote sensing in agriculture. This Special Issue of Remote Sensing includes different applications of UAV remote sensing for crop management, covering RGB, multispectral, hyperspectral and light detection and ranging (LiDAR) sensor applications aboard UAVs. The papers reveal innovative techniques involving image analysis and cloud points. However, it should be emphasized that this Special Issue is a small sample of UAV applications in agriculture and that there is much more to investigate.

Dynamic monitoring of crop phenotypic traits (e.g., LAI, plant height, biomass, nitrogen, yield et al.) is essential for exploring crop growth patterns, breeding new varieties, and determining optimized strategies for crop management. Traditional methods for determining crop phenotypic traits are mainly based on field sampling, handheld instrument measurement, and mechanized high-throughput platforms, which are time-consuming, and have low efficiency and incomplete spatial coverage. The development of crop science requires more rapid and accurate access to field-based crop phenotypes. Remote sensing provides a novel solution to quantify crop structural and functional traits in a timely, rapid, non-invasive and efficient manner. With the development of burgeoning remote sensing sensors and diversified algorithms, a range of crop phenotypic traits have been determined, including morphological parameters, spectral and textural characteristics, physiological traits, and responses to abiotic/biotic stresses in different environments. In addition, research advances in varying disciplines beyond agricultural sciences, such as engineering, computer science, molecular biology, and bioinformatics, have brought new opportunities for further development of remote sensing-based methods and technologies to gain more quantitative information on crop structure and function in complex environments

This book compiles a set of original and innovative papers included in the Special Issue on UAVs for vegetation monitoring, which proves the wide scope of UAVs in very diverse vegetation applications, both in agricultural and forestry scenarios, ranging from the characterization of relevant vegetation features to the detection of plant or crop stressors. New methods and techniques are developed and applied to diverse vegetation scenarios to meet the main challenge of sustainability.