Methodologies Used in Remote Sensing Data Analysis and Remote Sensors for Precision Agriculture

Download Url(s)
https://mdpi.com/books/pdfview/book/6765Contributor(s)
Chang, Jiyul (editor)
Fuentes, Sigfredo (editor)
Language
EnglishAbstract
When adopting remote sensing techniques in precision agriculture, there are two main areas to consider: data acquisition and data analysis methodologies. Imagery and remote sensor data collected using different platforms provide a variety of information volumes and formats. For example, recent research in precision agriculture has used multispectral images from different platforms, such as satellites, airborne, and, most recently, drones. These images have been used for various analyses, from the detection of pests and diseases, growth, and water status of crops to yield estimations. However, accurately detecting specific biotic or abiotic stresses requires a narrow range of spectral information to be analyzed for each application. In data analysis, the volume and complexity of data formats obtained using the latest technologies in remote sensing (e.g., a cube of data for hyperspectral imagery) demands complex data processing systems and data analysis using multiple inputs to estimate specific categorical or numerical targets. New and emerging methodologies within artificial intelligence, such as machine learning and deep learning, have enabled us to deal with these increasing data volumes and the analysis complexity.
Keywords
vineyard; pesticide application; variable rate application; unmanned aerial vehicle; satellite; nanosatellite; monsoon crops; leaf area index; leaf chlorophyll concentration; crop water content; multispectral; hyperspectral; deep learning; forage dry matter yield; high-throughput phenotyping; Brazilian pasture; nitrogen indicator; nitrogen nutrition diagnosis; optical sensor; spectral index; UAV; wheat lodging; lightweight; digital surface model (DSM); winter wheat; fractional order differential; continuous wavelet transform; optimal subset regression; support vector machine; wheat powdery mildew; machine learning; information fusion; remote sensing monitoring; hyperspectral imaging; dimensionality reduction; LDA; PLS; PCA; RandomForest; ReliefF; XGB; Meloidogyne; Solanum tuberosum; soil salinity sensitive parameter; random forest; optimal retrieval model; remote sensing; high throughput phenotyping; UAV/drone; biomass estimation; oats; wheat; yield prediction; random forests; satellite imagery; Normalized Difference Vegetation Index (NDVI); n/aISBN
9783036566146, 9783036566153Publisher website
www.mdpi.com/booksPublication date and place
Basel, 2023Classification
Medicine and Nursing