Conference Agenda

Human-wildlife conflict constitutes a critical challenge in biodiversity-rich yet densely populated regions, where rapid land-use change compromises both ecological integrity and human safety. In Sri Lanka, escalating encounters between humans and elephants reflect deeper spatial tensions rooted in habitat fragmentation, land-use competition, and policy misalignment. This study proposes an advanced geospatial decision-support framework that integrates Geographic Information Science (GIS), geospatial artificial intelligence (GeoAI), spatial negotiation, and cellular automata to model and mitigate land-use conflicts at the landscape scale.

The research builds upon and enhances the Land Use Conflict Identification Strategy (LUCIS), introducing a multi-layered modeling approach that evaluates land suitability for three competing uses: wildlife conservation, agriculture, and human settlements. Suitability models are developed using ecological, topographic, climatic, and infrastructural variables, informed by stakeholder consultations and institutional priorities. Spatial overlay analysis on a 1 km² grid resolution revealed that 48.8% of documented human-elephant conflict incidents occur in areas concurrently suitable for agriculture and elephant habitats. A further 21.6% occur in zones where all three land uses intersect, signifying spatial hotspots of acute ecological vulnerability and socio-economic pressure.

Case-specific findings provide critical insights into conflict drivers. First, smallholder agricultural expansion into elephant corridors emerges as the dominant spatial pressure, fragmenting key migration routes. Second, settlement encroachment along forest edges contributes to over 30% of recent conflict incidents. Third, unbuffered infrastructure development intensifies landscape impermeability, obstructing animal movement. Fourth, current administrative boundaries are misaligned with ecological zones, complicating cross-jurisdictional coordination. The spatial model demonstrates that by reallocating land based on ecological and anthropocentric suitability, high-conflict zones can be reduced by 15%, while preserving over 70% of identified elephant migratory pathways.

The framework's core innovation lies in its conflict-sensitive land allocation process. A game-theoretic spatial negotiation model assigns dynamic weights to land-use priorities derived from stakeholder perspectives and biophysical constraints. This enables fine-tuned trade-offs between conservation and development, generating land-use zones that are not only functionally coherent but also socially and ecologically legitimate. Cellular automata are employed to simulate adjacency-based transitions and reduce patch-level fragmentation, thereby reinforcing spatial continuity and landscape permeability.

By incorporating a predictive, data-driven methodology, the framework addresses critical landscape phenomena including habitat fragmentation, biodiversity loss, impaired animal movement, and reduced ecosystem connectivity. The approach transcends conventional reactive measures by offering proactive spatial interventions that prioritize long-term sustainability and coexistence. The integration of AI-enhanced modeling, participatory zoning logic, and dynamic land simulation positions this study as a significant contribution to the discourse on spatial interactions, scaling, and ecological resilience in contested landscapes.

In aligning with the ILUS 2025 sub-theme on Critical Landscape Phenomena, this research provides an innovative, transferable methodology for resolving land-use conflicts in biodiversity hotspots. It advances spatial planning practice by embedding ecological intelligence into land governance, and contributes to a broader understanding of how digital tools can mediate between development imperatives and conservation ethics in a rapidly transforming world.

Introduction

Moutain natural areas are the stage for diverse wildlife and human usage that often conflict. In the past years, outdoor leisure communities have particularly grown, leading to ecological pressure on wildlife. Scientists use different types of data to understand these ecosystems and elaborate recommendations to achieve sustainable ecosystems where land is shared. They spend a lot of time engineering data properly before being able to produce new knowledge.

The IntForOut project reunites ecologists and geodata scientists to use data from various sources to study human impact on mountain ecosystems in Mont Blanc and investigate innovative uses of stakeholder-generated data. We present the data engineering challenges encountered by ecologists and potential solutions investigated in the project.

Challenges in discovering and integrating data relevant to alpine ecology studies

Scientists studying alpine ecology use many data: hikers tracks, camera trap data, animals GPS tracks, habitat data computed by protected areas authorities, land cover and land use data, weather data, points of interest. These are different types of sources, publicly mandated authorities products, volunteered geography, crowd sourced data, scientific studies or private sector. The data is served from different portals, sometimes through a visualization interface only. The expertise required to use raw data, like for example the explicit meaning of terms like “acquisition campaign”, is not explicated online.

Two highly important criteria for these scientists are : 1) the temporality of data, i.e. when was the data acquired and what is the temporal validity of it (which can be seasonal), when is it updated, 2) the sensitivity of data and the conditions under which the results can be published. Both criteria are hard to evaluate on current portals.

The raw data must be transformed and integrated before analysis, for example computing the human frequentation for each segment of hiking trail, or human–wildlife coexistence places. This often necessitates database manipulation and can also require spatial analysis operations.

Scientists encounter the following categories of challenges while deriving consistent data for their analysis :

• various temporal and spatial granularities across datasets,

• incomplete data,

• outdated data and different update mechanisms.

Approaches developed in IntForOut project to integrate this data

To address these issues, we define a dedicated open ETL (Extract, Transform, Load) process that assists in discovering, cleaning, updating, linking and documenting the different data used by these scientists. It consists in :

- an IntForOut ontology that describe data –including underlying concepts- and integration methods,

- a unified data warehouse, that can be replicated by scientists,

- a metadata information infrastructure, where metadata is any data about the data at stakes: structured metadata, official documentation, project description, readme files, fragments in meetings minutes

The next set of challenges involves defining a user interface to access the ETL operations, a generic process for integrating new data, as well as establishing an automated metadata generation workflow to document both the data and the associated transformation procedures.

The contemporary landscape is undergoing rapid urbanisation and intensive human intervention, significantly affecting biodiversity and ecosystem stability. Several studies (e.g. Aronson et al. 2017; Beninde et al. 2015) suggest that biodiversity in urban green spaces can often exceed that of the surrounding open landscape, primarily due to the extensive agricultural use and homogenisation of rural areas. Urban environments can thus serve as important refugia for a variety of plant and animal species, including threatened taxa. The importance of newly emerging spontaneous semi-cultural ecosystems is highlighted (Kowarik et al. 2018, Bonthoux et al. 2024).

This research aims to compare the biodiversity of urban green spaces of similar size (approximately 1 ha) in various urban contexts in protected (stabilized) areas and those planned for development or conversion. The study focuses on spontaneously occurring plant species differences and socio-ecological value between these areas. Data are collected through habitat mapping, and species richness assessments, using standardised methodologies applicable in both urban contexts and surrounding landscapes.

The goal is to gain a deeper understanding of the role of urban green spaces in biodiversity conservation and to provide evidence to support their effective integration into spatial planning and landscape management. The results are expected to contribute to the identification of valuable sites and to inform strategies that promote ecological stability both within cities and in their surrounding regions.

Recent work highlights the importance of recognising and managing urban biodiversity as part of green infrastructure planning (Aronson et al. 2017; Ives et al. 2016; Niemelä et al. 2011, Kowarik et al. 2025). By comparing urban and peri-urban habitats, this study aims to contribute to the evidence base necessary to balance human needs and perceptions with the conservation of ecological processes.

Many pathogens are transmitted by vectors, as is the case with Malaria, Lyme disease and West Nile virus, for example. Vectors can include arthropods such as mosquitoes, ticks and fleas, but also flies. From a landscape epidemiological perspective, vector-borne diseases illustrate particularly clearly how the structure of the landscape can affect transmission pathways and consequently the likelihood of pathogens being transmitted via a vector.

The transmission path of vector-borne diseases consists of three components: the host animal (usually wild or farm animals); the vector with its spatial dispersal; and the receptor (such as humans). From a spatial perspective, short distances between hosts, receptors and vectors can lead to greater spatial overlap and hence increased spatial likelihood of transmission. The study focuses on vector dispersal and provides a conceptual classification of theories underlying animal dispersal behaviour and the spatial transmission risk of vector-borne diseases. It shows that the landscape's structure, particularly with regard to the availability and permeability of resources, can have a strong influence on the spread of the vector.

To analyse the extent to which landscape structure affects the transmission between host and receptor from a spatial perspective, an agent-based model for the common housefly (Musca domestica) as a vector for antimicrobial-resistant microorganisms is developed. To this end, the landscape surrounding of selected pig farms in Eastern Germany— potential sources of antimicrobial resistance — was empirically analysed in terms of its resource availability, permeability and dispersal potential for the fly. The focus was on the impact of various land cover types and landscape (linear) elements, such as hedges. For the agent-based model, the landscape within a three kilometres radius of the selected pig farms was modelled in terms of its structure and the availability of resources using various data sets (e.g. a land cover model, LiDAR data, and information on specific land uses). The results so far indicate, that the landscape structure with its arrangement of land cover and the presence of linear landscape elements has influences the spread of the common housefly.