Environmental Geocomputation with R

Environmental Geocomputation with R and its companion Laboratory Manual form a comprehensive educational package for geospatial data analysis. The textbook establishes theoretical foundations for visualization and modeling using both object-based and continuous field approaches, addressing spatial uncertainties while integrating spatial context into environmental analyses. The Lab Manual reinforces these concepts through practical exercises and case studies that follow a structured scientific workflow. Together, they enable students to progressively build skills in geocomputational techniques using R and its packages, from basic principles to complex real-world applications. FeaturesExplains the theory and applications of geocomputational methods for solving environmental problems involving spatial data and analysis.Covers big data, machine learning, methods for pattern recognition in spatial data, and tools and data analytics in the free and open-source (FOSS) R platform, making them accessible to everyone.Includes case studies from different environments and explains the diversity of big data and its applications.Provides hands-on exercises at the end of each chapter and encourages readers to understand both the potential and limitations of environmental systems.Is supplemented by a comprehensive laboratory manual with solved exercises, homework assignments, and research suggestions in geocomputation within an environmental science context.This set is intended for students in upper-level undergraduate or graduate programs using GIS, Geocomputation, Geoprocessing in environmental sciences and engineering, surveying, geosciences, and agriculture engineering. It is also an excellent resource for professionals in different areas who use geocomputation and image processing and wish to develop their skillset in these areas.

Dr. Marcelo de Carvalho Alves is a professor of Remote Sensing and Geoprocessing at the Federal University de Lavras, Brazil. He received his PhD in 2006 in Agricultural Engineering from the Federal University of Lavras, Brazil. He has published in topography, remote sensing, and geoprocessing. He has over 25 years of extensive experience in data science, digital image processing and modeling using multiscale, multidisciplinary, multispectral and multitemporal concepts applied to different environments. Experimental field-sites include a tropical forest, savanna, wetland, and agricultural fields in Brazil. Over the years, he has built up a large portfolio of research grants mostly relating to agroecosystem management, broadly in the context of vegetation, soil, water, atmosphere, climate, and pest-organisms.