Loading...
Projects / Programmes source: ARRS

Algorithms for modelling ecosystems' dynamics based on mathematical morphology and lattice theory

Research activity

Code Science Field Subfield
2.07.00  Engineering sciences and technologies  Computer science and informatics   

Code Science Field
T120  Technological sciences  Systems engineering, computer technology 

Code Science Field
1.02  Natural Sciences  Computer and information sciences 
Keywords
computer science, dynamics of ecosystems, mathematical morphology, lattice theory, complex networks, remote sensing, algorithms, geographical information systems.
Evaluation (rules)
source: COBISS
Researchers (14)
no. Code Name and surname Research area Role Period No. of publications
1.  37956  PhD Marko Bizjak  Computer science and informatics  Researcher  2016 - 2017  34 
2.  36450  PhD Denis Horvat  Computer science and informatics  Junior researcher  2014 - 2017  26 
3.  37447  PhD David Jesenko  Computer science and informatics  Junior researcher  2015 - 2017  39 
4.  27605  PhD Milan Kobal  Forestry, wood and paper technology  Researcher  2014  339 
5.  21318  PhD Bogdan Lipuš  Computer science and informatics  Researcher  2014 - 2017  46 
6.  33709  PhD Niko Lukač  Computer science and informatics  Researcher  2014 - 2017  173 
7.  29243  PhD Domen Mongus  Computer science and informatics  Researcher  2014 - 2017  249 
8.  28150  Blaž Repnik  Computer science and informatics  Researcher  2014 - 2017  29 
9.  08638  PhD Krista Rizman Žalik  Computer science and informatics  Researcher  2015 - 2017  180 
10.  10264  PhD Primož Simončič  Forestry, wood and paper technology  Researcher  2014 - 2017  680 
11.  28590  PhD Mitja Skudnik  Forestry, wood and paper technology  Researcher  2016 - 2017  327 
12.  26035  PhD Denis Špelič  Computer science and informatics  Researcher  2014 - 2017  58 
13.  22592  PhD Urša Vilhar  Forestry, wood and paper technology  Researcher  2015 - 2017  398 
14.  06671  PhD Borut Žalik  Computer science and informatics  Principal Researcher  2014 - 2017  807 
Organisations (2)
no. Code Research organisation City Registration number No. of publications
1.  0404  Slovenian Forestry Institute  Ljubljana  5051673000  11,778 
2.  0796  University of Maribor, Faculty of Electrical Engineering and Computer Science  Maribor  5089638003  26,908 
Abstract
Sustainable management of the environment is a major challenge facing not only Slovenia, but also the entire mankind. Large ecosystems, especially forests, play a major role when addressing this task, having critical impact on the quality of life and obvious social-economic benefits for the society. Systematic and complete monitoring of the evolution of such ecosystems is extremely difficult, up to now even impossible, due to their vast geographic scales and huge amounts of their miniature basic elements. Only recent advances in remote sensing technologies that have revolutionized the area of Earth observations provide us with possible insights into the dynamics of such ecosystems. Sophisticated satellite observation systems from the Copernicus program and state-of-the-art laser scanning technologies like LiDAR, allow for periodical monitoring of large geographical areas with high enough resolution and precision to distinguish the smallest basic elements of ecosystems, such as trees, undergrowth, and shrubs. However, the huge amounts of heterogeneous and complex data they acquire remains a major challenge for the future as contemporary software solutions are incapable to deliver data analytics in a systematic, organized manner. Before a holistic information space for efficient management of large ecosystems can be developed, major issues have to be addressed, regarding integration of heterogeneous Earth observations data, implementation of relevant analytic tools for their processing and, finally, relevant models of their dynamics. The proposed project meets these challenges by introducing a new paradigm for data integration based on the decomposition of heterogeneous Earth observations into the contained basic semantic elements, their fusing and enrichment with complementary information from within different data types, and their inter-linking into a complex network. Through advanced concepts of mathematical morphology, formalizing arithmetic of shapes for sophisticated pattern analysis, the decomposition of specific data types and the recognition of the basic ecosystems’ elements will be achieved. Their geometric features will be used to determine their social status, and consequently the likelihood of their mutual influence. These will be represented with a complex network, enabling us to develop a wide range of new algorithms based on up to now unexploited mathematical and analytical methods at such large scale. This new type of data analytics will be derived primarily from methodological studies of partially ordered sets based on lattice theory and statistical-topological features based on the theory of complex networks. Such fundamental shift in the design of the pattern recognition algorithms will provide the thoughtfully required capabilities for the development of new approaches to recognition of complex structures, composed of multiple basic elements, while comparison of complex networks will allow for systematic monitoring of their evolution. Hence, the foundation for recognizing interactions between the basic elements will be established, giving us the framework for modelling dynamics of large ecosystems. While in-situ measurements will be used to validate these algorithms, a study of forest dynamics due to the competition of trees for accessing resources and leaving space will provide the proof of concept. All the developed methods will be implemented in the form of weakly coupled service for this purpose and integrated into an existing platform for geographic data management and processing. A user-friendly environment for services orchestration and execution of analytic scenarios on-demand will be provided to experts in a form of end-user application.
Significance for science
During the project, various new methodologies and algorithms concerning a forest ecosystem were developed. A new methodology for recognition of basic entities of a vegetation by using locally fitted surfaces was considered firstly. Then, an evolutionary-based multicriteria algorithm for integration of basic entities into a complex network was developed on the basis of common features in the nodes or their mutual interleaving. Finally, a functional representation of the complex network was done by a new two-phase evolution algorithm. This presentation enables domain experts to use traditional mathematical and statistical tools to study complex network’s processes. These algorithms were applied on a forest ecosystem for a prediction of development of individual trees in dependence on their neighbours. The input data and the evaluation of the obtained results were provided by the domain researchers from the Slovene Forestry Institute, who were the partners in this project. The performed research activities and results were published in prestigious journals with impact factors. The number of publications have outdone the dissemination objectives from the project proposal. The papers directly originating from the project, have received more than 30 pure citations already through the project duration. We were also granted with the US patent. Our research achievements were also awarded with the respected Danubius Young Scientist Award, which additionally contributes to the international reputation of the completed research.
Significance for the country
Earth observation technologies provide huge amounts of heterogeneous data and possibilities for various analyses and planning, but new methodological approaches and tools have to be developed firstly. Within the project, we have systematically explored large ecosystems, built their representation with complex networks and validated it in the forest ecosystems domain. Management of forests, which cover almost 60% of the area of Slovenia, faces several challenges where our project’s results can facilitate the solution. The importance of these results for Slovenia can be assessed from: 1. Their utilisation by decision makers, forest owners and the Slovenia Forestry Institute. The latter is the only Slovene institution, coping with in-depth research in sustainable forest management. Our application helps it with, e.g. production of a digital crown model, assessment of biodiversity or carbon cycling indicators, damage caused by sleet, pests or diseases, with studying the forest management impacts on microclimate, and monitoring invasive alien species. These studies assist the Ministry of Agriculture, Forestry and Food, the Slovenia Forest Service and forest owners in passing the forest management plans and decisions about, e.g. forest security or forest roads planning. 2. Usability for Slovene companies. We expect that the results of the projects will be used for improved forest management what would positively affect the Slovene wood processing industry and produced energy from the wood biomass. In the most developed countries, 100m3 of processed wood means a new workplace, while the woodcutting in Slovenia is far below the maximum limit of 6.5M m3, still providing the stability of forests and habitats. 3. Promotion of Slovenia and internationalisation. The results of the project were published in 8 papers in prestigious international journals. Their relevance was confirmed with 31 citations. We have also participated at 13 international conferences and obtained a US patent, while one of our researchers won the respected Danubius Young Scientist Award. The internationalisation of the project results is best achieved with transferring them into international projects. UM FERI has strengthened its position in EUROGI – European Umbrella Organisation for Geographic Information and GISIG – Geographical Information Systems International Group, and regularly cooperates in joint project proposals within the domains of geospatial data and Earth observation (H2020, ESA, InterReg). It also became a permanent member in a strong consortium with the Fraunhofer institute and DLR. Being aware that the European Space Agency – ESA has invested €3.5G into the Copernicus programme for satellite Earth observation and that industry and science are currently not capable of using all acquired data, we see an opportunity for a long-term placement of Slovenia among the most developed countries in this field. We also expect that our partners, export-oriented software companies (e.g. XLab, d.o.o., DatCon, d.o.o., IGEA, d.o.o., Inova IT, d.o.o.), will assist the promotion of the developed tools and exploit this new opportunity to present themselves at foreign markets. 4. Integration into education. We are integrating presentations of the developed methodology and its application to forest ecosystems into two courses GIS Principles and Algorithms of Big Data Analysis at the MSc programme of Computer Science and Information Technologies at UM FERI. We also expect that they will be addressed in e.g. forestry and ecology studies. Several young researchers and Ph.D. students have actively participated in the project. One of them obtained the degree in the meantime and already utilized the gathered knowledge and experience to find a job in the software company in Slovenia.
Most important scientific results Annual report 2014, 2015, final report
Most important socioeconomically and culturally relevant results Annual report 2014, 2015, final report
Views history
Favourite