Grant: Discovery Grants Program - Individual
Simon Fraser University
$47,000.00
Coupling GeoAI and GeoSimulation approaches to model and analyze complex dynamic spatial systems from local to global scales
FY 2023-24
Summary
Land Use and Land Cover (LULC) changes directly impact the human and natural environment. Despite past advances and multidisciplinary research efforts in the scientific study, understanding, analysis and modeling of LULC change processes, there is still a continuous need for further improvements of this research domain. LULC changes are involving many interrelated elements that are conceptualized as complex dynamic spatial systems. They are driven by human-environment interactions from local to global scales due to socioeconomic and biophysical factors that impose rising risks for further natural environment degradation and projected climate change. The long-term objective of this research program is to continue advancing the novel work on geosimulation modeling approaches within the geographic information systems and science (GIS), artificial intelligence (AI) and land use science disciplines to better understand and analyze the LULC process. The short-term objectives are to: (a) improve existing AI methods by incorporating geospatial components that explicitly consider spatial relationships and local effects, thereby generating spatially-explicit GeoAI approaches; (b) design and implement novel hybrid models that couple GeoAI, geosimulation, and GIS methodologies with capabilities to represent and simulate LULC change processes at various spatial extents and scales; and (c) continue progressing model calibration and validation methods to test the new generation of hybrid GeoAI geosimulation models. The proposed research will use geographic automata systems (GAS) with their related geosimulation approaches such as cellular automata and agent-based modeling. These are well-suited for modeling complex spatial dynamic systems to represent LULC change processes and individual interactions driving the changes on mostly small-scale study areas. Spatialization of machine and deep learning (ML/DL) algorithms will be integrated by parameter tuning and by adding local effects to adjust them to account for spatial heterogeneity, adapting them to accommodate the nature of geospatial data and become explainable. Coupled GeoAI with GAS and GIS will improve the capabilities of the geosimulation models to use large volumes of data, consider a multitude of actors, and learn causal relationships that drive large-scale LULC processes. Consequently, the novel hybrid modeling methods will leverage the advantages from both GeoAI and GAS to significantly expand our abilities to analyze and understand the LULC change process from local to global levels. Given the contentious issues associated with population growth, urbanization and land degradation, the outcomes of this research program will contribute to the development of scientific tools to support effective management and conservation strategies addressing the dynamic interconnectedness of the natural and built environments in Canada and beyond.
Program
Discovery Grants Program - Individual
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-04052
Name nom
Dragicevic, Suzana
Department département
Geography
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
47000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1506
Committee name en
Geosciences
Committee name fr
Géosciences
Area of application code
605
Area of application group en
Construction, urban and rural planning
Area of application group fr
Construction, urbanisme et aménagement rural
Area of application en
Land development
Area of application fr
Aménagement du territoire
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Not available
Research subject en
Non disponible
Research subject fr
Non disponible
Application title
Coupling GeoAI and GeoSimulation approaches to model and analyze complex dynamic spatial systems from local to global scales
Keyword
3D modeling; agent-based systems and cellular automata; artificial intelligence; complex systems; geocomputation; geographic information systems and science (GIS); geospatial modeling and geosimulations; land use and land cover change; soft computing; spatial decision support systems
Application summary
Land Use and Land Cover (LULC) changes directly impact the human and natural environment. Despite past advances and multidisciplinary research efforts in the scientific study, understanding, analysis and modeling of LULC change processes, there is still a continuous need for further improvements of this research domain. LULC changes are involving many interrelated elements that are conceptualized as complex dynamic spatial systems. They are driven by human-environment interactions from local to global scales due to socioeconomic and biophysical factors that impose rising risks for further natural environment degradation and projected climate change. The long-term objective of this research program is to continue advancing the novel work on geosimulation modeling approaches within the geographic information systems and science (GIS), artificial intelligence (AI) and land use science disciplines to better understand and analyze the LULC process. The short-term objectives are to: (a) improve existing AI methods by incorporating geospatial components that explicitly consider spatial relationships and local effects, thereby generating spatially-explicit GeoAI approaches; (b) design and implement novel hybrid models that couple GeoAI, geosimulation, and GIS methodologies with capabilities to represent and simulate LULC change processes at various spatial extents and scales; and (c) continue progressing model calibration and validation methods to test the new generation of hybrid GeoAI geosimulation models. The proposed research will use geographic automata systems (GAS) with their related geosimulation approaches such as cellular automata and agent-based modeling. These are well-suited for modeling complex spatial dynamic systems to represent LULC change processes and individual interactions driving the changes on mostly small-scale study areas. Spatialization of machine and deep learning (ML/DL) algorithms will be integrated by parameter tuning and by adding local effects to adjust them to account for spatial heterogeneity, adapting them to accommodate the nature of geospatial data and become explainable. Coupled GeoAI with GAS and GIS will improve the capabilities of the geosimulation models to use large volumes of data, consider a multitude of actors, and learn causal relationships that drive large-scale LULC processes. Consequently, the novel hybrid modeling methods will leverage the advantages from both GeoAI and GAS to significantly expand our abilities to analyze and understand the LULC change process from local to global levels. Given the contentious issues associated with population growth, urbanization and land degradation, the outcomes of this research program will contribute to the development of scientific tools to support effective management and conservation strategies addressing the dynamic interconnectedness of the natural and built environments in Canada and beyond.