into one final output. The SDSS provides complex analytical functions for spatial
analysis. It provides multiple functions not only to perform various crop models and
map simulated outputs but also improve the visualization of the environment for
policy makers and integrating the database management system with expert
knowledge.
3.3.4.2 New Direction and Trends in Decision Support System
Data-driven SDSS leads to much more intelligent systems, a new research direction,
and a challenge to most of the current developers in SDSS. The success of the datadriven approach is reliant upon the effectiveness of its incorporated model and the
quality of the gathered data. For example, the agricultural SDSS needs the data not
only the current state but also the predicted future condition of crops and their
supporting resources and environment. In most of the cases, remote sensing can
provide real-time and cost-effective current condition as the initial status of the
model. A range of well-tested prediction model exist for almost all crop-related
parameters mentioned in the previous sections, e.g., environment model to determine the crop growth environment, growth model to predict the crop growth process,
etc. Although many researchers are working on the data-driven agricultural SDSS,
there is still a lack of synergetic system to integrate the broad individual research
areas into the SDSS system. One of the successful systems is the Climate
FieldView™ developed by the Climate Corporation to help farmers make datadriven decisions to sustainably increase and maximize their productivity. Most of
these data-driven systems are applied to precision agriculture or site-specific farming, in multiple applications from seed, fertilizer, pesticide, irrigation, yield
prediction, etc.
Another new trend in the agricultural DDS is providing an online, real-time, and
customized agricultural service to local farmers and policy makers. Web-based DSS
made the real-time monitoring and decision-making feasible through a serious
innovative web technologies, standard-based geospatial interoperability, sensor
web, geospatial processing modeling, Open Geospatial Consortium (OGC) technologies, and location-based service technologies. A successful web-based decision
support system should be fast and user-friendly, providing sufficient and highly
useful capabilities to the end user (Fernandez and Neal 2007). As an example, the
remote-sensing-based flood crop loss assessment service system (RF-CLASS) is a
web-based decision support system that automatically produces flood-related products to USDA NASS for supporting the post-flood decision-making such as crop
flood insurance policy (Di et al. 2017).
Currently, many agricultural information service companies are developing new
technologies which are promoted by the rapid growing smart farming industry in the
United States and the world. New technologies, such as advanced technologies for
big data and cloud computing for computing services, are leveraging this development and leading to more robots and artificial intelligence in farming industries.
34
J. Tang
analysis. It provides multiple functions not only to perform various crop models and
map simulated outputs but also improve the visualization of the environment for
policy makers and integrating the database management system with expert
knowledge.
3.3.4.2 New Direction and Trends in Decision Support System
Data-driven SDSS leads to much more intelligent systems, a new research direction,
and a challenge to most of the current developers in SDSS. The success of the datadriven approach is reliant upon the effectiveness of its incorporated model and the
quality of the gathered data. For example, the agricultural SDSS needs the data not
only the current state but also the predicted future condition of crops and their
supporting resources and environment. In most of the cases, remote sensing can
provide real-time and cost-effective current condition as the initial status of the
model. A range of well-tested prediction model exist for almost all crop-related
parameters mentioned in the previous sections, e.g., environment model to determine the crop growth environment, growth model to predict the crop growth process,
etc. Although many researchers are working on the data-driven agricultural SDSS,
there is still a lack of synergetic system to integrate the broad individual research
areas into the SDSS system. One of the successful systems is the Climate
FieldView™ developed by the Climate Corporation to help farmers make datadriven decisions to sustainably increase and maximize their productivity. Most of
these data-driven systems are applied to precision agriculture or site-specific farming, in multiple applications from seed, fertilizer, pesticide, irrigation, yield
prediction, etc.
Another new trend in the agricultural DDS is providing an online, real-time, and
customized agricultural service to local farmers and policy makers. Web-based DSS
made the real-time monitoring and decision-making feasible through a serious
innovative web technologies, standard-based geospatial interoperability, sensor
web, geospatial processing modeling, Open Geospatial Consortium (OGC) technologies, and location-based service technologies. A successful web-based decision
support system should be fast and user-friendly, providing sufficient and highly
useful capabilities to the end user (Fernandez and Neal 2007). As an example, the
remote-sensing-based flood crop loss assessment service system (RF-CLASS) is a
web-based decision support system that automatically produces flood-related products to USDA NASS for supporting the post-flood decision-making such as crop
flood insurance policy (Di et al. 2017).
Currently, many agricultural information service companies are developing new
technologies which are promoted by the rapid growing smart farming industry in the
United States and the world. New technologies, such as advanced technologies for
big data and cloud computing for computing services, are leveraging this development and leading to more robots and artificial intelligence in farming industries.
34
J. Tang