The project of the Ministry of Science and Higher Education of the Russian Federation the grant No. 075-15-2020-787
Personal Knowledge Base Designer was used when performing work under the project of the Ministry of Science and Higher Education of the Russian Federation the grant
No. 075-15-2020-787 "Fundamentals, methods and technologies for digital monitoring and forecasting of the environmental situation on the Baikal natural territory". In particular, when developing a thematic WPS service for digital monitoring, analysis, modeling and forecasting of the environmental situation, as well as the risk of natural and technogenic fires.
In particular, we solve the task of prototyping knowledge bases for determining the risk (probability) of fire and the defining the class of forest fire hazard.
Information on fires in the Baikal natural territory for the period from 2017-2020, weather data, as well as information on infrastructure (roads, settlements) and the type of vegetation were used as initial data. The database on fires included more than 45 thousand records describing information about heat points identified as a result of the analysis of satellite images.
The knowledge base consisted of two segments solving the following subtasks:
1) forming a conclusion on the fire hazard class of a certain forest area based on the average monthly weather data, current weather conditions, information about the time of year, the proximity of rivers, lakes, roads, settlements, terrain and vegetation type;
2) forming a conclusion on the risk (probability) of a fire according to the fire hazard class of a certain forest area using fire statistics and information about the time of year (season).
The development process is similar to case study 3 and can be presented in the form of the following scheme (Fig.1).
Fig.1 Knowledge base development scheme using PKBD
Next, we will consider the stages in more detail.
Step 1. As a model of the domain, a conceptual model was created that describes the factors affecting the class of fire hazard of a forest area and the risk (probability) of a fire. A fragment of the model is shown in Fig. 2.
Fig.2 A fragment of the conceptual model
Step 2. Next, decision tables were developed that describe the structural aspect of the domain. These tables contain information about combinations of features describing the fire hazard class of a forest area and the risk (probability) of a fire. In particular, the following table structure (headers) is used to define the class: Road::distance_to_car_road, Road::distance_to_railway, River::distance_to_river, Lake::distance_to_lake, Meteostation::id, Meteostation::name, Meteodata::rrr, Meteodata::ff, Meteodata::u, Meteodata::t, Settlement::distance_to_settlement, Settlement::population, Region::population, Region::average_annual_temperature, Season::name, Forestry::staff_number, Square::landform, Square::forest_type, Square::underlying_surface_type, #Square::name, #Square::fire_hazard_class. To determine the risk (probability) of a fire, the following table structure (headers) is used: Square:: name, Square:: fire_hazard_class, Season::name, #Fire::risk[probability]. The decision table with intermediate data is shown in Fig. 3.
Fig.3 A fragment of the decision table with intermediate data
Step 3. Next, with the aid of PKBD, the decision tables were imported and presented in the form of logical rules. The imported decision tables were refined in the RVML form (Fig. 4).
Fig.4 Rule templates (generalized rules) for the formation of specific knowledge base rules
Step 4. For two segments of the knowledge base, a code was generated on CLIPS, which was used to debug the obtained knowledge bases, later presented in the form of PHP codes (Fig. 5).
Fig.5 Fragments of generated codes
