251
Views
0
CrossRef citations to date
0
Altmetric
Articles

The application of artificial neural networks for the generalisation of military passability maps

ORCID Icon & ORCID Icon
Pages 638-654 | Received 12 May 2023, Accepted 27 Jun 2023, Published online: 25 Jul 2023
 

ABSTRACT

Passability maps are cartographic studies that are generally used by commanders in order to plan military operations. Pursuant to standardisation documents, they are developed by marking passable, hardly passable and impassable (GO, SLOW GO and NO GO) areas. This article presents a methodology for the generalisation of passability maps that are created automatically. For this purpose, artificial neural networks (ANN) were used, and, specifically, a multilayer perceptron. Teaching the network consisted in presenting the neural network examples of manual generalisation of source maps. The paper describes the manner of preparing teaching data to train artificial neural networks and their implementation, which leads to the creation of the resulting maps. The maps were generated in multiple input configurations of teaching data, which allowed us to conduct comparisons of the obtained maps. Areas of various levels of passability generalised manually by the operator were compared to maps generated by the ANN. In order to test the consistency of maps, Moran’s I spatial autocorrelation coefficient was determined. The conducted tests allowed us to obtain the optimum parameters of the generalisation process. The proposed methodology is fully automated and may be applied to any source data in any chosen area.

RÉSUMÉ

Les cartes de praticabilité sont des documents cartographiques utilisés par les commandants pour planifier des opérations militaires. Conformément aux documents de standardisation, elles sont réalisées en notant les zones franchissables, difficilement franchissables ou infranchissables (GO, SLOW GO, NO GO). Cet article présente une méthode pour la généralisation des cartes de praticabilité créées automatiquement. Pour cela, des réseaux de neurones (ANN) sont utilisés, en particulier un perceptron multicouche. Apprendre à un réseau consiste à présenter au réseau de neurones des exemples de généralisation manuelle des cartes initiales. Cet article décrit la façon de préparer les données d'apprentissage pour entrainer les réseaux de neurones artificiels et leur implémentation qui aboutit à la création des cartes résultats. Les cartes ont été générées dans de multiples configurations d'entrée de données d'entrainement, ce qui nous a permis d'effectuer les comparaisons des cartes obtenues. Des zones de différents niveaux de praticabilité, généralisées manuellement par des opérateurs, ont été comparées aux cartes générées par le réseau de neurone artificiel. Afin d'étudier la cohérence entre cartes, le coefficient d'autocorrélation spatiale de Morand I a été calculé. Les tests réalisés ont permis d'obtenir les paramètres optimaux pour le processus de généralisation. La méthode proposée est entièrement automatique et peut être utilisée pour toute source de données dans n'importe quelle zone choisie.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by Faculty of Civil Engineering and Geodesy, Military University of Technology: [Grant Number UGB/22-816/2023/WAT].

Notes on contributors

Krzysztof Pokonieczny

Krzysztof Pokonieczny is specialist in geoinformatics at the Faculty of Civil Engineering and Geodesy of the Military University of Technology. For 8 years he worked at the Military Geographic Centre, where was responsible for military projects associated with geoinformatics. His research work mainly focuses on the use of geostatistics and machine learning algorithms, especially in the military applications of GIS. Currently he is the Director of Institute of Geospatial Engineering and Geodesy.

Wojciech Dawid

Wojciech Dawid specialises in GIS and geoinformatics. His research focuses on the applications of modern IT technologies and GIS systems in the analysis of geospatial data mainly for the military purposes. He is the author and co-author of research articles concerning terrain passability, cartographic generalisation and land use prediction. Currently, he works at the Faculty of Civil Engineering and Geodesy of the Military University of Technology.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 61.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 487.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.