The purpose of this paper is to provide an overview of the application of DSS in the field of precision agriculture. It describes and analyzes the development of agricultural DSS from rule-driven to data-driven, from handling simple input to complex inputs, show that the use of modern information technologies such as multi-sensor fusion, Internet of Things, data mining, cloud computing, RTK high-precision composite positioning, unmanned aerial vehicles, machine learning, and graphical recognition can promote precision agriculture in the direction of more refined, more intelligent, and more intensive development.

This DSS can acquire real-time ambient temperature and humidity to assess the risk of potato late blight disease.  

When the monitored ambient temperature and humidity reach the risk threshold.  the DSS sends treatment notifications to relevant staff via SMS.

This DSS has multiple complex data input sources, including climate change information, satellite imagery, fusion databases, real-time data from sensor environments, multispectral data, and infrared thermal imaging data.
 The data mining engine handles large-scale complex input data that can be used in agriculture for monitoring pests and diseases, soil fertility, crop growth, etc. For example, thermal imaging monitors crop hydrogen content threshold and issues warnings, multispectral assessment of fruit ripeness, UV detection of pests and diseases.

This intelligent Greenhouse DSS that integrates IoT and machine learning. It can be used to perform real-time monitoring of environmental variables and can automatically perform different tasks  by Central actuator manager , it also provides an interface to communicate with experts and workers to engage them when necessary. It supports AI decision making in addition to using rules to make decisions. For example: image recognition to determine if plants are growing in a good state or identify if there are weeds, predict abnormal conditions that may arise in the nearest future based on environmental variables and given recommendations

a smart agriculture DSS based on a novel wireless communication technology LoRaWAN for optimizing crop yield. This DSS has multiple environmental status data inputs including air temperature and humidity, soil conductivity, NPK content, pH, soil moisture, and air quality. It can be used for automatic crop irrigation, water oversupply warning, nutrient deficiency & oversupply warning. It uses LoRaWAN, a low-cost open-source wireless technology with long-range communication capability.