Machine learning algorithms (MLAs) are used to solve complex non-linear and high-dimensional problems. The objective of this study was to identify the MLA that generates an accurate spatial distribution model of bark beetle (Ips typographus L.) infestation spots. We first evaluated the performance of 2 linear (logistic regression, linear discriminant analysis), 4 non-linear (quadratic discriminant analysis, k-nearest neighbors classifier, Gaussian naive Bayes, support vector classification), and 4 decision trees-based MLAs (decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier) for the study area (the Horní Planá region, Czech Republic) for the period 2003–2012. Each MLA was trained and tested on all subsets of the 8 explanatory variables (distance to forest damage spots from previous year, distance to spruce forest edge, potential global solar radiation, normalized difference vegetation index, spruce forest age, percentage of spruce, volume of spruce wood per hectare, stocking). The mean phi coefficient of the model generated by extra trees classifier (ETC) MLA with five explanatory variables for the period was significantly greater than that of most forest damage models generated by the other MLAs. The mean true positive rate of the best ETC-based model was 80.4%, and the mean true negative rate was 80.0%. The spatio-temporal simulations of bark beetle-infested forests based on MLAs and GIS tools will facilitate the development and testing of novel forest management strategies for preventing forest damage in general and bark beetle outbreaks in particular.
Ecosystem services represent the contributions and benefits of ecosystems. This paper aims to evaluate highly relevant ecosystem services in Trnava as a regionally significant city and in the functional area which consist of 15 surrounding villages. In this research we used our own progressive methods using complex spatial units (representative potential geoecosystems and representative real geoecosystems) to define the most important ecosystem services in the area. The results of our study consist of two types of outcomes. Firstly, we provide assessment for each spatial unit for various ecosystem services in urban functional area of Trnava and secondly, we have created maps which can help to see a broader image of spatial arrangement of benefits.
The main objective of this research was to develop a web-based geographic information system (GIS) based on a detailed analysis of user preferences from the perspective of forest research, management and education. An anonymous questionnaire was used to elicit user preferences for a hardware platform and evaluations of web-mapping applications, geographic data, and GIS tools. Mobile GIS was used slightly more often than desktop GIS. Web-mapping applications that provide information to the public and the present research results were rated higher than the forest management application. Orthophotos for general purposes and thematic layers such as forest stand maps, soils, protected areas, cadastre, and forest roads were preferred over highly specialized layers. Tools for data searching, map printing, measuring, and drawing on digital maps were rated higher than tools for online map editing and geographic analysis. The analysis of user preferences was used to design a new multipurpose GIS portal for the University Forest Enterprise. The GIS portal was designed with a three-tier architecture on top of the software library for managing user access, working interactively with digital maps, and managing web map applications. The web map applications focus on tools and geographic information not available elsewhere, specifically timber harvest and logistics, research plots, and hunting game management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.