registration, data fusion, nowcasting, forecasting, estimation, and optimization problems. Cloud-based services enable high-performance computational platforms and
reliable data processing capabilities in a cost-efficient way to users connected
through mobile applications and web services or machine-to-machine (M2M) communication interfaces. The number of connected devices is expected to reach
29 billion by year 2022, and 18 billion of them will be related to the IoT.
Sensor technology is also in a rapid development trend. There are various types of
single-chip spectrometers with spectral resolution finer than 20 nm at different
bands. Lab-on-a-chip solutions are used for DNA and RNA sequencing, protein
analysis, and food monitoring. Biosensors are intended to be used in the agricultural
and food sectors to ensure food quality and safety. They are promising alternatives to
conventional analytical tools since they offer advantages in size, rapid response,
specificity, and cost. The increasing performance of embedded processors enables
advanced sensor fusion techniques in real-time even on low-power devices.
Satellite remote sensing technology enables very high spatial resolution down to
0.3 m at optical bands. Recent hyperspectral imaging satellites have more than
200 bands. Multi-temporal multispectral data availability increases through the
Sentinel and Landsat Missions. Hyperspectral image acquisition is also available
with drone, unmanned aerial vehicle (UAV), and other airborne platforms. This rich
data availability requires efficient and reliable methods and platforms for monitoring, processing, and utilization for agriculture. Well-organized, structural data with
contextual connections provide new capabilities in a big data environment. Machine
learning solutions begin to take the place of plant-specific models, or they are used to
adapt the models.
This book summarizes the theoretical aspects and practical applications in agrogeoinformatics. The topics covered by the book include the recent and established
methods for the development of monitoring and data processing systems in agrogeoinformation systems.
Chapter 2, Remote Sensing for Agriculture, by Gao, introduces basic remote
sensing concepts and applications in agriculture. Major freely available remote
sensing data sources used in agricultural applications (MODIS, Landsat, Sentinel,
etc.) and the properties of the relevant data products are presented here. Remote
sensing applications for crop-type classification, crop growth monitoring, crop yield
estimation, crop water use, and soil moisture estimation are introduced in this
chapter.
The past decades have witnessed the rapid growth of GIS application in agriculture. Chapter 3, GIS Fundamentals for Agriculture, by Tang, introduces GIS-based
modeling and spatial database for agricultural systems. The current and future
characteristics of GIS-based agricultural information systems are evaluated in this
chapter.
Chapter 4, Agro-Geoinformatics Data Sources and Sourcing, by Sun et al.,
summarizes the state-of-the-art data sources and the sourcing methods in agrogeoinformatics. Data sources from satellite, airborne, in situ, and human reports
are investigated and introduced. Spatial coverage, long observation history, and
case-specific, site-specific, and question-specific concise nouns and numbers have
1 Introduction to Agro-Geoinformatics: Theory and Practices
3
reliable data processing capabilities in a cost-efficient way to users connected
through mobile applications and web services or machine-to-machine (M2M) communication interfaces. The number of connected devices is expected to reach
29 billion by year 2022, and 18 billion of them will be related to the IoT.
Sensor technology is also in a rapid development trend. There are various types of
single-chip spectrometers with spectral resolution finer than 20 nm at different
bands. Lab-on-a-chip solutions are used for DNA and RNA sequencing, protein
analysis, and food monitoring. Biosensors are intended to be used in the agricultural
and food sectors to ensure food quality and safety. They are promising alternatives to
conventional analytical tools since they offer advantages in size, rapid response,
specificity, and cost. The increasing performance of embedded processors enables
advanced sensor fusion techniques in real-time even on low-power devices.
Satellite remote sensing technology enables very high spatial resolution down to
0.3 m at optical bands. Recent hyperspectral imaging satellites have more than
200 bands. Multi-temporal multispectral data availability increases through the
Sentinel and Landsat Missions. Hyperspectral image acquisition is also available
with drone, unmanned aerial vehicle (UAV), and other airborne platforms. This rich
data availability requires efficient and reliable methods and platforms for monitoring, processing, and utilization for agriculture. Well-organized, structural data with
contextual connections provide new capabilities in a big data environment. Machine
learning solutions begin to take the place of plant-specific models, or they are used to
adapt the models.
This book summarizes the theoretical aspects and practical applications in agrogeoinformatics. The topics covered by the book include the recent and established
methods for the development of monitoring and data processing systems in agrogeoinformation systems.
Chapter 2, Remote Sensing for Agriculture, by Gao, introduces basic remote
sensing concepts and applications in agriculture. Major freely available remote
sensing data sources used in agricultural applications (MODIS, Landsat, Sentinel,
etc.) and the properties of the relevant data products are presented here. Remote
sensing applications for crop-type classification, crop growth monitoring, crop yield
estimation, crop water use, and soil moisture estimation are introduced in this
chapter.
The past decades have witnessed the rapid growth of GIS application in agriculture. Chapter 3, GIS Fundamentals for Agriculture, by Tang, introduces GIS-based
modeling and spatial database for agricultural systems. The current and future
characteristics of GIS-based agricultural information systems are evaluated in this
chapter.
Chapter 4, Agro-Geoinformatics Data Sources and Sourcing, by Sun et al.,
summarizes the state-of-the-art data sources and the sourcing methods in agrogeoinformatics. Data sources from satellite, airborne, in situ, and human reports
are investigated and introduced. Spatial coverage, long observation history, and
case-specific, site-specific, and question-specific concise nouns and numbers have
1 Introduction to Agro-Geoinformatics: Theory and Practices
3