Advanced Applications in Remote Sensing of Agricultural Crops and Natural Vegetation

Prasad S. Thenkabail, John G. Lyon, Alfredo Huete, Prasad S. Thenkabail, John G. Lyon, Alfredo Huete

• Publisher: CRC Press
• Year: 2018
• ISBN:
  9780429775154
• Edition: 2
• Topic: Biological Sciences
• Subtopic: Botany
• Index: Biological Sciences

Written by leading global experts, including pioneers in the field, the four-volume set on Hyperspectral Remote Sensing of Vegetation, Second Edition, reviews existing state-of-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.

Volume IV, Advanced Applications in Remote Sensing of Agricultural Crops and Natural Vegetation discusses the use of hyperspectral or imaging spectroscopy data in numerous specific and advanced applications, such as forest management, precision farming, managing invasive species, and local to global land cover change detection. It emphasizes the importance of hyperspectral remote sensing tools for studying vegetation processes and functions as well as the appropriate use of hyperspectral data for vegetation management practices. The concluding chapter provides readers with useful guidance on the highlights and essence of Volume IV through the editors' perspective.

Key Features of Volume IV:

• 
  
  

• Guides readers to harness the capabilities of the most recent advances in applying hyperspectral remote sensing technology to the study of terrestrial vegetation.

• 
  
  

• Includes specific applications on agriculture, crop management practices, study of crop stress and diseases, crop characteristics based on inputs (e.g., nitrogen, irrigation), study of vegetation impacted by heavy metals, gross and net primary productivity studies, light use efficiency studies, crop water use and actual evapotranspiration studies, phenology monitoring, land use and land cover studies, global change studies, plant species detection, wetland and forest characterization and mapping, crop productivity and crop water productivity mapping, and modeling.

• 
  
  

• Encompasses hyperspectral or imaging spectroscopy data in narrow wavebands used across visible, red-edge, near-infrared, far-infrared, shortwave infrared, and thermal portions of the spectrum.

• 
  
  

• Explains the implementation of hyperspectral remote sensing data processing mechanisms in a standard, fast, and efficient manner for their applications.

• 
  
  

• Discusses cloud computing to overcome hyperspectral remote sensing massive big data challenges.
• Provides hyperspectral analysis of rocky surfaces on the earth and other planetary systems.

Section I

Detecting Crop Management Practices, Plant Stress, and Disease

1

Using Hyperspectral Data in Precision Farming Applications

Haibo Yao, Yanbo Huang, Lie Tang, Lei Tian, Deepak Bhatnagar, and Thomas E. Cleveland

Contents

1.1Introduction

1.1.1Precision Farming

1.1.2Hyperspectral Data

1.2Applications of Hyperspectral Data in Precision Agriculture

1.2.1Precision Farming Management Considerations

1.2.2Spatial, Spectral, and Temporal Considerations

1.2.3Hyperspectral Narrowband Vegetation Indices

1.2.4Application 1: Soil Management Zoning

1.2.5Application 2: Weed Sensing

1.2.6Application 3: Crop Herbicide Damage Detection

1.2.7Application 4: Hyperspectral Imagery for Crop Nitrogen Stress Detection

1.2.8Application 5: In-Season Crop Yield Estimation

1.2.8.1Corn Yield Estimation

1.2.8.2Grain Sorghum Yield Estimation

1.2.8.3Wheat Yield Estimation

1.2.8.4Other Crops

1.2.8.5Hyperspectral Imagery for Temporal Yield Analysis

1.2.9Application 6: Pest and Disease Detection

1.2.9.1Pest Infestation

1.2.9.2Bacterial

1.2.9.3Fungal Infection

1.2.10Current Trend: UAV in Precision Agriculture

1.3Conclusions

References

1.1Introduction

1.1.1Precision Farming

Rather than being managed as a single, uniform unit, a crop field can be handled site specifically based on local field needs. This is the concept behind using precision agriculture for in-field variability management. The goals of precision agriculture can be described as follows and are based on economic, productivity, and environmental considerations:

•Greater yield than traditional farming with the same amount of input;

•The same yields with reduced input;

•Greater yield than traditional farming with reduced input.

The precision agriculture concept has drawn significant attention from farmers and researchers around the world (National Research Council, 1997; Zhang et al., 2002; Hedley, 2015). A complete precision agriculture system can be described in terms of four indispensable parts: (a) field variability sensing and information extraction, (b) decision making, (c) precision field control, and (d) operation and result assessment. The success of any precision agriculture system depends on the correct implementation of these four parts. Among the four parts, the decision-making step is the central component (Stafford, 2000). The decision-making process involves making the right management decisions based on the variability information derived from data collected in the field.

To make sound decisions, the most important step is to obtain accurate information about in-field variabilities. Agricultural engineers devote significant efforts to field variability sensing and information extraction, as well as to precision field control and operation. Sensing and information extraction are crucial parts of the system requiring that the desired information be obtained at the right location at the right time. Sensing and information extraction involve using various sensors to capture data on field conditions. Once the raw data are obtained, appropriate algorithms can be used to extract field information. Sensing either from a close distance (ground) or remotely, such as from airborne or spaceborne sensors, is an import method of field data acquisition (Scotford and Miller, 2005; Larson et al., 2008; McIntyre and Corner, 2016; Skowronek et al., 2017). Agricultural remote sensing typically involves the use of surface reflectance information in the visible (VIS) and near-infrared (NIR) region of the electromagnetic spectrum. It provides a fast and economical way to acquire detailed field data in a short period of time. Remote sensing has thus been used in a broad range of applications in the farming industry. Mulla (2013) reviewed progress made in the previous 25 years on remote sensing in precision agriculture. The article pointed out the potential to collect massive amounts of data from different sensors and platforms for agricultural applications. Another review (Wolfert et al., 2017) further described scenarios in which big data influenced farm operations with its substantial impact on the entire food supply chain.

1.1.2Hyperspectral Data

Traditionally, agricultural remote sensing has used multispectral broadband imagery. With advances in sensor technology over the past two decades, t...

Table of contents

• Cover
• Half Title
• Series
• Title Page
• Copyright Page
• Dedication
• Contents
• Foreword to the First Edition
• Foreword to the Second Edition
• Preface
• Acknowledgments
• Editors
• Contributors
• Acronyms and Abbreviations
• Section I: Detecting Crop Management Practices, Plant Stress, and Disease
• Section II: Vegetation Processes and Function (ET, Water Use, GPP, LUE, Phenology)
• Section III: Land Cover, Forests, and Wetland and Urban Applications Using Hyperspectral Data
• Section IV: Thermal, SWIR, and Visible Remote Sensing
• Section V: Hyperspectral Data in Global Change Studies
• Section VI: Hyperspectral Remote Sensing of Other Planets
• Section VII: Conclusions
• Index