Geodeziya, kartografiya, geografiya

What other types of data do I need?
In addition to satellite or aerial imagery, other data can be used to increase the accuracy of the classification. Some possible ancillary data are digital elevation models (DEMs) and their derived datasets (slope and aspect), climate data such as rainfall and temperature, and vector overlays such as roads, rivers, and populated places. If there is an attribute that effects the distribution of land cover that exists in a mapped form it should be incorporated into the classification process. For example, DEMs often supplement satellite data when mapping land cover since vegetation classes are often limited to specific elevations or aspects.
Sometimes, however, we might be aware of an attribute that we want to incorporate into the classification but there is not an available dataset that is appropriate for the study. For example, vegetation distribution is affected by rainfall but many rainfall datasets are too coarse to be useful in classifying vegetation. As time goes on more of these environmental layers are being improved so that they can be used to map vegetation more accurately.
Incorporating these ancillary data into the classification process is not always easy. Some of the classification methods discussed below allow the incorporation of assorted datasets but others are more restrictive. For the more restrictive methods there are still some ways to utilize ancillary data. One is to use these data to stratify the study area into regions based on one or more environmental variables. We might use slope and aspect and create unique strata for different slope and aspect ranges. For example we could create two elevation categories-- below 500 meters and 500 meters or above -- and four aspect categories-- north, east, south, and west-- and from these create the following 8 strata: below 500m north aspect, below 500m east aspect, below 500m south aspect, below 500m west aspect, 500m or above north aspect, 500m or above east aspect, 500m or above south aspect, and 500m or above west aspect. The classification can then be carried out within each of the individual strata. Defining strata will generally have a positive effect on the accuracy of a classification.