Monitoring of vegetation structure and functioning is critical to modeling terrestrial ecosystems and energy cycles. In particular, leaf area index (LAI) is an important structural property of vegetation used in many land surface vegetation, climate, and crop production models. Canopy structure (LAI, fCover, plant height, and biomass) and biochemical parameters (leaf pigmentation and water content) directly influence the radiative transfer process of sunlight in vegetation, determining the amount of radiation measured by passive sensors in the visible and infrared portions of the electromagnetic spectrum. Optical remote sensing (RS) methods build relationships exploiting in situ measurements and/or as outputs of physical canopy radiative transfer models. The increased availability of passive (radar and LiDAR) RS data has fostered their use in many applications for the analysis of land surface properties and processes, thanks also to their insensitivity to weather conditions and the capability to exploit rich structural and textural information. Data fusion and multi-sensor integration techniques are pressing topics to fully exploit the information conveyed by both optical and microwave bands.

Monitoring of vegetation structure and functioning is critical to modeling terrestrial ecosystems and energy cycles. In particular, leaf area index (LAI) is an important structural property of vegetation used in many land surface vegetation, climate, and crop production models. Canopy structure (LAI, fCover, plant height, and biomass) and biochemical parameters (leaf pigmentation and water content) directly influence the radiative transfer process of sunlight in vegetation, determining the amount of radiation measured by passive sensors in the visible and infrared portions of the electromagnetic spectrum. Optical remote sensing (RS) methods build relationships exploiting in situ measurements and/or as outputs of physical canopy radiative transfer models. The increased availability of passive (radar and LiDAR) RS data has fostered their use in many applications for the analysis of land surface properties and processes, thanks also to their insensitivity to weather conditions and the capability to exploit rich structural and textural information. Data fusion and multi-sensor integration techniques are pressing topics to fully exploit the information conveyed by both optical and microwave bands.

Physiological plant ecology is primarily concerned with the function and performance of plants in their environment. Within this broad focus, attempts are made on one hand to understand the underlying physiological, biochemical and molecular attributes of plants with respect to performance under the constraints imposed by the environment. On the other hand physiological ecology is also concerned with a more synthetic view which attempts to under stand the distribution and success of plants measured in terms of the factors that promote long-term survival and reproduction in the environment. These concerns are not mutually exclusive but rather represent a continuum of research approaches. Osmond et al. (1980) have elegantly pointed this out in a space-time scale showing that the concerns of physiological ecology range from biochemical and organelle-scale events with time constants of a second or minutes to succession and evolutionary-scale events involving communities and ecosystems and thousands, if not millions, of years. The focus of physiological ecology is typically at the single leaf or root system level extending up to the whole plant. The time scale is on the order of minutes to a year. The activities of individual physiological ecologists extend in one direction or the other, but few if any are directly concerned with the whole space-time scale. In their work, however, they must be cognizant both of the underlying mechanisms as well as the consequences to ecological and evolutionary processes.

Kernel methods have long been established as effective techniques in the framework of machine learning and pattern recognition, and have now become the standard approach to many remote sensing applications. With algorithms that combine statistics and geometry, kernel methods have proven successful across many different domains related to the analysis of images of the Earth acquired from airborne and satellite sensors, including natural resource control, detection and monitoring of anthropic infrastructures (e.g. urban areas), agriculture inventorying, disaster prevention and damage assessment, and anomaly and target detection. Presenting the theoretical foundations of kernel methods (KMs) relevant to the remote sensing domain, this book serves as a practical guide to the design and implementation of these methods. Five distinct parts present state-of-the-art research related to remote sensing based on the recent advances in kernel methods, analysing the related methodological and practical challenges: Part I introduces the key concepts of machine learning for remote sensing, and the theoretical and practical foundations of kernel methods. Part II explores supervised image classification including Super Vector Machines (SVMs), kernel discriminant analysis, multi-temporal image classification, target detection with kernels, and Support Vector Data Description (SVDD) algorithms for anomaly detection. Part III looks at semi-supervised classification with transductive SVM approaches for hyperspectral image classification and kernel mean data classification. Part IV examines regression and model inversion, including the concept of a kernel unmixing algorithm for hyperspectral imagery, the theory and methods for quantitative remote sensing inverse problems with kernel-based equations, kernel-based BRDF (Bidirectional Reflectance Distribution Function), and temperature retrieval KMs. Part V deals with kernel-based feature extraction and provides a review of the principles of several multivariate analysis methods and their kernel extensions. This book is aimed at engineers, scientists and researchers involved in remote sensing data processing, and also those working within machine learning and pattern recognition.

This book presents practical information about hemispherical photography from the perspectives of field data acquisition, image processing and information retrieval methods. This book is organized into three sections. The first section describes what is hemispherical photography and what are the fundamental elements of forest structure and light interactions within the forest canopy. The second section provides practical information about the equipment, procedures and tools for procuring, processing and analyzing hemispherical photographs. Armed with this information, the third section describes several applications of hemispherical photographs to forestry and natural resource assessment. The book concludes with a discussion about modelling tools and future directions of this rapidly growing field. There is currently no information source on the market that has this comprehensive range of topics combined in a single book. The book will appeal to academics, graduate students, natural resource professionals and researchers alike.

Presents state-of-the-art research into leaf interactions with light, for scientists working in remote sensing, plant physiology, ecology and resource management.

An accessible yet rigorous introduction to remote sensing and its application to the study of vegetation for advanced undergraduate and graduate students. The underlying physical and mathematical principles of the techniques disucussed are explained in a way readily understood by those without a strong mathematical background.