for collecting large-scale observations of crops and related environment. Geospatial
information technology is the key technology for handling, analyzing, and applying
agro-geoinformatics. Traditional analysis tools such as GIS (geographical information system) analysis toolboxes are widely used in agro-geoinformatics researches.
Agro-geoinformatics is actively adopting the state-of-the-art data analysis methods
like big data parallel processing, machine learning, deep learning, expert system,
intelligent knowledge-based systems, genetic algorithms, fuzzy system, soft computing, etc. GEE is also widely used in agro-geoinformatics. Through combining
these advanced analysis tools with the observed datasets, agro-geoinformatics can
help farmers, consumers, scientists, industries, and government agencies to achieve
the strategic goals: ensuring food security, reducing poverty, and sustaining the
environment. Agro-geoinformatics researches target the information which can
assist farmers to make better decisions on planting, fertilizing, irrigating, harvesting,
marketing, and selling and will improve government agencies’ capacity on making
better policies on farm subsidies, stabling prices, large commodity purchase, smallholder farm support plan, crop insurance, disaster responses, etc.
8.3.3 Related Research
Agro-geodata is a kind of geospatial data, which is defined as data with associated location information. Studies have shown (or claimed) that more than 80% of
data the world has collected is geospatial data (Hahmann et al. 2011). Therefore, the
geospatial data is big data. In fact, geospatial data have all the five V characteristics
of big data. In the past several years, numerous big data management and analytic
technologies have been developed by computer and data science communities.
Many of them are general technologies that can be adopted by disciplinary big
data applications, including agro-geoinformatics.
One of the most notable technologies to deal with big data is the cloud computing
and associated Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and
Software as a Service (SaaS) (JoSEP et al. 2010). Numerous software packages to
deal with big data management and analytics, either on cloud or cluster platforms,
have been developed. A lot of those packages are released as open source software,
freely available to all interested users. In the agro-geoinformatics domain, those
general big data technologies have been adopted to deal with the agro-big data.
In addition to the common five V characteristics of big data, agro-big data also
have their special features, particularly, the multidimensionality and spatial/temporal
characteristics (Di 2004). The agro-big data may cover wide spatial area, up to the
entire Earth. Because of the special features of agro-big data, special big data
management, and analytics methods have to be developed. For example, both the
spatial and temporal co-registration processing of multisource and multimodal data
are essential for handling agro-big data.
150
L. Di and Z. Sun
information technology is the key technology for handling, analyzing, and applying
agro-geoinformatics. Traditional analysis tools such as GIS (geographical information system) analysis toolboxes are widely used in agro-geoinformatics researches.
Agro-geoinformatics is actively adopting the state-of-the-art data analysis methods
like big data parallel processing, machine learning, deep learning, expert system,
intelligent knowledge-based systems, genetic algorithms, fuzzy system, soft computing, etc. GEE is also widely used in agro-geoinformatics. Through combining
these advanced analysis tools with the observed datasets, agro-geoinformatics can
help farmers, consumers, scientists, industries, and government agencies to achieve
the strategic goals: ensuring food security, reducing poverty, and sustaining the
environment. Agro-geoinformatics researches target the information which can
assist farmers to make better decisions on planting, fertilizing, irrigating, harvesting,
marketing, and selling and will improve government agencies’ capacity on making
better policies on farm subsidies, stabling prices, large commodity purchase, smallholder farm support plan, crop insurance, disaster responses, etc.
8.3.3 Related Research
Agro-geodata is a kind of geospatial data, which is defined as data with associated location information. Studies have shown (or claimed) that more than 80% of
data the world has collected is geospatial data (Hahmann et al. 2011). Therefore, the
geospatial data is big data. In fact, geospatial data have all the five V characteristics
of big data. In the past several years, numerous big data management and analytic
technologies have been developed by computer and data science communities.
Many of them are general technologies that can be adopted by disciplinary big
data applications, including agro-geoinformatics.
One of the most notable technologies to deal with big data is the cloud computing
and associated Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and
Software as a Service (SaaS) (JoSEP et al. 2010). Numerous software packages to
deal with big data management and analytics, either on cloud or cluster platforms,
have been developed. A lot of those packages are released as open source software,
freely available to all interested users. In the agro-geoinformatics domain, those
general big data technologies have been adopted to deal with the agro-big data.
In addition to the common five V characteristics of big data, agro-big data also
have their special features, particularly, the multidimensionality and spatial/temporal
characteristics (Di 2004). The agro-big data may cover wide spatial area, up to the
entire Earth. Because of the special features of agro-big data, special big data
management, and analytics methods have to be developed. For example, both the
spatial and temporal co-registration processing of multisource and multimodal data
are essential for handling agro-big data.
150
L. Di and Z. Sun