7.1 Introduction
Arable land per capita has decreased by more than 40% in the last 50 years since
1970 (World Bank 2019). Data has an increasing role in agricultural production and
management at all scales depending on the rising importance of yield efficiency and
sustainability. Precision agriculture and good agricultural practices are based on the
evaluation of various types of data and knowledge. Basin-level agricultural planning, management, and optimization also depend on the acquisition and processing
of various types of data. Remote sensing systems provide spatial information at some
observation instants, and real-time terrestrial monitoring systems provide temporal
information at some observation points. There is not yet a feasible and accurate
spatiotemporal direct monitoring method for the crop, soil, and other terrestrial
resources over the large areas at continuous sampling time intervals. Data fusion
methods appear as a way of multitemporal mapping of information depending on the
evaluation of spatial, temporal, and multitemporal datasets via computational
models. Besides the spatial and temporal features of the datasets, knowledge-driven
data, administrative records, workflow processes, and real-time communication
systems provide additional dimensions for data fusion systems. Data fusion systems
can evaluate data in time domain, frequency domain, state space, wavelet domain
(Jin et al. 2014), or spatial domain, while the outputs can be mixed-domain data such
as spatiotemporal data or spatial frequency data.
Data fusion is the process of integration of multiple data and knowledge
representing the same real-world object into a consistent, accurate, and useful
representation which can significantly increase the application values of the data
(Ghannam et al. 2014). This chapter presents the basics and some examples of data
fusion applications in agriculture.
By having a systems theory approach, agricultural systems require observability
of states as well as imposed input patterns for accurate forecasts and optimal
management. Statistical data is very important for agriculture since common contextual information is helpful against the variational and conditional complexities.
Since many of the required monitoring parameters are usually not feasible for realtime data acquisition, data fusion methods enable estimated parameters indirectly
from the correlated set of available data.
In contrary to distributed characteristics of data and the users in agriculture,
computational systems have centralized trends through “Data as a Service”
(DaaS), “Software as a Service” (SaaS), “Platform as a Service” (PaaS), and finally
“Artificial Intelligence as Service” (AIaaS).
When increasing the coverage of mobile wireless networks and smartphone use
rate, even in rural areas are considered, centralized computational systems well
matches for more talent services with affordable operational cost per user. In
addition to big data and scale value addition, recent standards for energy efficient
IoT services, such as the narrowband Internet of Things (NB-IoT) in GSM cellular
networks, complete the value addition cycle for monitoring and automation in field.
104
B. Üstündağ
Arable land per capita has decreased by more than 40% in the last 50 years since
1970 (World Bank 2019). Data has an increasing role in agricultural production and
management at all scales depending on the rising importance of yield efficiency and
sustainability. Precision agriculture and good agricultural practices are based on the
evaluation of various types of data and knowledge. Basin-level agricultural planning, management, and optimization also depend on the acquisition and processing
of various types of data. Remote sensing systems provide spatial information at some
observation instants, and real-time terrestrial monitoring systems provide temporal
information at some observation points. There is not yet a feasible and accurate
spatiotemporal direct monitoring method for the crop, soil, and other terrestrial
resources over the large areas at continuous sampling time intervals. Data fusion
methods appear as a way of multitemporal mapping of information depending on the
evaluation of spatial, temporal, and multitemporal datasets via computational
models. Besides the spatial and temporal features of the datasets, knowledge-driven
data, administrative records, workflow processes, and real-time communication
systems provide additional dimensions for data fusion systems. Data fusion systems
can evaluate data in time domain, frequency domain, state space, wavelet domain
(Jin et al. 2014), or spatial domain, while the outputs can be mixed-domain data such
as spatiotemporal data or spatial frequency data.
Data fusion is the process of integration of multiple data and knowledge
representing the same real-world object into a consistent, accurate, and useful
representation which can significantly increase the application values of the data
(Ghannam et al. 2014). This chapter presents the basics and some examples of data
fusion applications in agriculture.
By having a systems theory approach, agricultural systems require observability
of states as well as imposed input patterns for accurate forecasts and optimal
management. Statistical data is very important for agriculture since common contextual information is helpful against the variational and conditional complexities.
Since many of the required monitoring parameters are usually not feasible for realtime data acquisition, data fusion methods enable estimated parameters indirectly
from the correlated set of available data.
In contrary to distributed characteristics of data and the users in agriculture,
computational systems have centralized trends through “Data as a Service”
(DaaS), “Software as a Service” (SaaS), “Platform as a Service” (PaaS), and finally
“Artificial Intelligence as Service” (AIaaS).
When increasing the coverage of mobile wireless networks and smartphone use
rate, even in rural areas are considered, centralized computational systems well
matches for more talent services with affordable operational cost per user. In
addition to big data and scale value addition, recent standards for energy efficient
IoT services, such as the narrowband Internet of Things (NB-IoT) in GSM cellular
networks, complete the value addition cycle for monitoring and automation in field.
104
B. Üstündağ