been evaluated for the classification of the data sources. Conventional, cloud-based,
and crowdsourcing data sourcing options are also explained in this chapter.
A majority of the spatial data standards and models used in agro-geoinformation
systems are set and recommended by the international organizations, International
Organization for Standardization (ISO), Open Geospatial Consortium (OGC), and
Food and Agricultural Organization (FAO). Chapter 5, Standards and Interoperability, by Bai, focuses on the standards about data content, metadata, and a variety of
data services, including catalogue service, Web Mapping Service (WMS), Web
Feature Service (WFS), and Web Coverage Service (WCS).
Agricultural image data collection includes in-situ data collection, airborne data
collection, and space-borne data collection. How to manage and analyze volumes of
high-resolution agricultural image data captured by the different types of satellites is
becoming a new challenge. Chapter 6, Image Processing Methods in Agricultural
Observation Systems, by Zhang and Lin, explains the agricultural image processing
systems at different kinds of hardware and software platforms. Knowledge-based
expert systems, machine learning-based decision trees, and artificial neural networks
are evaluated for agricultural digital image processing in this chapter.
When some physical parameters are not feasible for direct monitoring at specified
spatial or temporal resolution, well-designed data fusion models enable their indirect
acquisition by using other types of existing data or alternative sensory mechanisms.
Data fusion is an increasing trend for information harvesting in accordance with
computational power and efficiency. Chapter 7, Data Fusion in Agricultural Information Systems, by Üstündağ, presents data fusion principles and methods used in
agriculture. Data fusion based on multiparameter regression, time-delay neural
networks, wavelet neural networks, and convolutional neural networks is explained
with example applications.
Agro-geoinformatics deals with collecting, managing, and analyzing agriculturalrelated geospatial data, which are domain-specific big data. Chapter 8, Big Data and
Its Applications in Agro-Geoinformatics, by Di and Sun, presents the development
of agro-big data-specific technology as a necessary supplement to the adoption of
general big data technology in agro-geoinformation systems.
EU has developed the land parcel identification system (LPIS) for agriculture
policy studies, while the national land parcel database has been established in the
United States for large-scale land parcel data services. Chapter 9, Land Parcel
Identification, by Lin and Zhang, explains the applications, benefits, problems, and
the requirements of land parcel information in agro-geoinformation systems. This
chapter also discusses the data size and performance issues of the large-scale land
parcel data structures as well as adopting new techniques such as remote sensing and
GIS that bring an alternative for measuring land parcel for agro-geoinformation
systems.
Chapter 10, Crop Pattern and Status Monitoring, by Yu and Yang, presents the
comparison of sampling framework-based statistical approaches and the remote
sensing methods in monitoring crop pattern and status. The advancements of remote
sensing and related processing capabilities make it possible to operationally monitor
crop pattern and crop status in very high spatial and temporal resolutions.
4
L. Di and B. Üstündağ
and crowdsourcing data sourcing options are also explained in this chapter.
A majority of the spatial data standards and models used in agro-geoinformation
systems are set and recommended by the international organizations, International
Organization for Standardization (ISO), Open Geospatial Consortium (OGC), and
Food and Agricultural Organization (FAO). Chapter 5, Standards and Interoperability, by Bai, focuses on the standards about data content, metadata, and a variety of
data services, including catalogue service, Web Mapping Service (WMS), Web
Feature Service (WFS), and Web Coverage Service (WCS).
Agricultural image data collection includes in-situ data collection, airborne data
collection, and space-borne data collection. How to manage and analyze volumes of
high-resolution agricultural image data captured by the different types of satellites is
becoming a new challenge. Chapter 6, Image Processing Methods in Agricultural
Observation Systems, by Zhang and Lin, explains the agricultural image processing
systems at different kinds of hardware and software platforms. Knowledge-based
expert systems, machine learning-based decision trees, and artificial neural networks
are evaluated for agricultural digital image processing in this chapter.
When some physical parameters are not feasible for direct monitoring at specified
spatial or temporal resolution, well-designed data fusion models enable their indirect
acquisition by using other types of existing data or alternative sensory mechanisms.
Data fusion is an increasing trend for information harvesting in accordance with
computational power and efficiency. Chapter 7, Data Fusion in Agricultural Information Systems, by Üstündağ, presents data fusion principles and methods used in
agriculture. Data fusion based on multiparameter regression, time-delay neural
networks, wavelet neural networks, and convolutional neural networks is explained
with example applications.
Agro-geoinformatics deals with collecting, managing, and analyzing agriculturalrelated geospatial data, which are domain-specific big data. Chapter 8, Big Data and
Its Applications in Agro-Geoinformatics, by Di and Sun, presents the development
of agro-big data-specific technology as a necessary supplement to the adoption of
general big data technology in agro-geoinformation systems.
EU has developed the land parcel identification system (LPIS) for agriculture
policy studies, while the national land parcel database has been established in the
United States for large-scale land parcel data services. Chapter 9, Land Parcel
Identification, by Lin and Zhang, explains the applications, benefits, problems, and
the requirements of land parcel information in agro-geoinformation systems. This
chapter also discusses the data size and performance issues of the large-scale land
parcel data structures as well as adopting new techniques such as remote sensing and
GIS that bring an alternative for measuring land parcel for agro-geoinformation
systems.
Chapter 10, Crop Pattern and Status Monitoring, by Yu and Yang, presents the
comparison of sampling framework-based statistical approaches and the remote
sensing methods in monitoring crop pattern and status. The advancements of remote
sensing and related processing capabilities make it possible to operationally monitor
crop pattern and crop status in very high spatial and temporal resolutions.
4
L. Di and B. Üstündağ