No abstract

Effective settlements generalization for small-scale maps is a complex and challenging task. Developing a consistent methodology for generalizing small-scale maps has not gained enough attention, as most of the research conducted so far has concerned large scales. In the study reported here, we want to fill this gap and explore settlement characteristics, named variables that can be decisive in settlement selection for small-scale maps. We propose 33 variables, both thematic and topological, which may be of importance in the selection process. To find essential variables and assess their weights and correlations, we use machine learning (ML) models, especially decision trees (DT) and decision trees supported by genetic algorithms (DT-GA). With the use of ML models, we automatically classify settlements as selected and omitted. As a result, in each tested case, we achieve automatic settlement selection, an improvement in comparison with the selection based on official national mapping agency (NMA) guidelines and closer to the results obtained in manual map generalization conducted by experienced cartographers.

<p><strong>Abstract.</strong> The decision about removing or maintaining an object while changing detail level requires taking into account many features of the object itself and its surrounding. Automatic generalization is the optimal way to obtain maps at various scales, based on a single spatial database, storing up-to-date information with a high level of spatial accuracy. Researchers agree on the need for fully automating the generalization process (Stoter et al., 2016). Numerous research centres, cartographic agencies as well as commercial companies have undertaken successful attempts of implementing certain generalization solutions (Stoter et al., 2009, 2014, 2016; Regnauld, 2015; Burghardt et al., 2008; Chaundhry and Mackaness, 2008). Nevertheless, an effective and consistent methodology for generalizing small-scale maps has not gained enough attention so far, as most of the conducted research has focused on the acquisition of large-scale maps (Stoter et al., 2016). The presented research aims to fulfil this gap by exploring new variables, which are of the key importance in the automatic settlement selection process at small scales. Addressing this issue is an essential step to propose new algorithms for effective and automatic settlement selection that will contribute to enriching, the sparsely filled small-scale generalization toolbox.</p><p>The main idea behind this research is using machine learning (ML) for the new variable exploration which can be important in the automatic settlement generalization in small-scales. For automation of the generalization process, cartographic knowledge has to be collected and formalized. So far, a few approaches based on the use of ML have already been proposed. One of the first attempts to determine generalization parameters with the use of ML was performed by Weibel et al. (1995). The learning material was the observation of cartographers manual work. Also, Mustière tried to identify the optimal sequence of the generalization operators for the roads using ML (1998). A different approach was presented by Sester (2000). The goal was to extract the cartographic knowledge from spatial data characteristics, especially from the attributes and geometric properties of objects, regularities and repetitive patterns that govern object selection with the use of decision trees. Lagrange et al. (2000), Balboa and López (2008) also used ML techniques, namely neural networks to generalize line objects. Recently, Sester et al. (2018) proposed the application of deep learning for the task of building generalization. As noticed by Sester et al. (2018), these ideas, although interesting, remained proofs of concepts only. Moreover, they concerned topographic databases and large-scale maps. Promising results of automatic settlement selection in small scales was reported by Karsznia and Weibel (2018). To improve the settlement selection process, they have used data enrichment and ML. Thanks to classification models based on the decision trees, they explored new variables that are decisive in the settlement selection process. However, they have also concluded that there is probably still more “deep knowledge” to be discovered, possibly linked to further variables that were not included in their research. Thus the motivation for this research is to fulfil this research gap and look for additional, essential variables governing settlement selection in small scales.</p>

The presented research concerns the methodology for selecting settlements and road networks from 1:250 000 to 1:500 000 and 1:1 000 000 scales. The developed methodology is based on the provisions of the Regulation of the Ministry of Interior from 17 November 2011. The correctness of the generalization principles contained in the Regulation has not yet been verified. Thus this paper aims to fulfil this gap by evaluating map specifications concerning settlement and road network generalizations. The goal was to automate the selection process by using formalized cartographic knowledge. The selection operators and their parameters were developed and implemented in the form of a generalization model. The input data was the General Geographic Object Database (GGOD), whose detail level corresponds to 1:250 000 scale. The presented research is in line with works on the automation of GGOD generalization performed by the National Mapping Agency (NMA) in Poland (GUGiK). The paper makes the following contributions. First, the selection methodology contained in the Regulation was formalised and presented in the form of a knowledge base. Second, the models for the generalization process were developed. The developed methodology was evaluated by generalizing the settlements and roads in the test area. The results of the settlement and road network generalization for both 1:500 000 and 1:1 000 000 detail levels were compared with the maps designed manually by experienced cartographers.

The complexity of a road network must be reduced after a scale change, so that the legibility of the map can be maintained. However, deciding whether to show a particular road section on the map is a very complex process. This process, called selection, constitutes the first step in a sequence of further generalization operations and it is a prerequisite to effective road network generalization. So far, not many comprehensive solutions have been developed for effective road selection specifically at small scales as the studies have mainly dealt with large-scale maps. The paper presents an experiment using machine learning (ML), specifically decision-tree-based (DT) models, to optimize the selection of the roads from 1:250,000 to 1:500,000 and 1:1,000,000 scales. The scope of this research covers designing and verifying road selection models on the example of three selected districts in Poland. The aim is to consider the problem of road generalization holistically, including numerous semantic, geometric, topological, and statistical road characteristics. The research resulted in a list of measurable road attributes that comprehensively describe the rank of a particular road section. The outcome also includes attribute weights, attribute correlation calculated for roads, and machine learning models designed for automatic road network selection. The performance of the machine learning models is very high and ranges from 80.94% to 91.23% for the 1:500,000 target scale and 98.21% to 99.86% for the 1:1,000,000 scale.