Large Language Models (LLMs) excel at synthesising globally documented knowledge but lack the fine-grained, real-time awareness required for field-level agricultural and rural-planning decisions. This paper introduces JackDaw, a spatially enabled chat-agent architecture that couples foundation-model reasoning with multi-modal geospatial data streams and a retrieval-augmented generation (RAG) pipeline. JackDaw implements a tool-prefiltering mechanism that selects only those data connectors whose topical, temporal and spatial metadata match the current query, thereby mitigating the diminishing returns observed when LLMs are exposed to large, flat toolsets. Through LangChain-based orchestration the platform dynamically assembles workflows that range from lightweight natural-language processing models to domain-specific analytic kernels, while a value-engineering strategy allocates computationally intensive models (e.g., GPT-4-class) only to tasks that require broad contextual reasoning. Benchmark experiments on forestry-asset discovery and vineyard-site assessment demonstrate that JackDaw delivers location-specific, traceable answers that outperform a standalone proprietary LLM, which provides only generic or spatially misattributed responses. The results confirm that bridging global language models with local spatial intelligence markedly reduces hallucination rates and enhances the operational readiness of AI for sustainable agriculture and rural development. Index Terms—Large language models; geospatial AI; retrieval-augmented generation; context-aware agriculture; spatial decision support; tool prefiltering; JackDaw system; rural planning.
The stakeholders to be identified in this deliverable D2.1 database of the PoliRuralPlus project include local communities, governments, farmers, SMEs, industry associations, research institutions, NGOs, civil society groups, infrastructure providers, digital technology companies, financial institutions, and tourism sector representatives. These stakeholders play crucial roles in driving and shaping rural-urban linkages and opportunities within the project area. The database of the PoliRuralPlus stakeholders in the 9 pilot regions is defined, and how communication channels will be established with them, as the basis for the project’s analysis of the rural-urban linkages and opportunities as well as the Impact of COVID19, to identify the most appropriate integrated urban-rural strategies.
The PoliRuralPlus Platform Design (D4.1) outlines the development of a modular, scalable digital ecosystem aimed at fostering sustainable, balanced, and inclusive rural-urban development. Building on the foundations of the original PoliRural project, the platform integrates advanced geospatial tools, AI technologies, and data sources to address regional development challenges. Key components include AI-driven models, data management services, and collaborative applications tailored to enhance policy-making, foresight analysis, and stakeholder engagement. The design emphasizes interoperability, real-time data integration, and user-centric development, ensuring adaptability within existing regional infrastructures. The platform supports objectives aligned with the European Green Deal, promoting innovation, resilience, and evidence-based governance strategies across diverse rural and urban regions.
Deliverable D4.2 documents the Beta version of the PoliRuralPlus platform. It follows D4.1 Platform Design and reports the first integrated implementation of former PoliRural components with AI/DL services, Data Spaces and EOSC-oriented infrastructures. The deliverable describes the Beta architecture, implemented services, component status, data and metadata flows, pilot testing approach, limitations and the roadmap towards the final platform release.
Centered around strengthening rural-urban linkages, this video demonstrates how integrated data analysis - powered by geospatial and AI components - can help policymakers and local communities gain a more holistic view of regional development prospects. At the core of the approach is JackDaw, a geo-enabled chat agent that merges location-specific data with large language model (LLM) reasoning. Key themes and features Multi-dimensional spatial insights: By gathering structured data on a variety of spatial attributes - ranging from population distribution to the presence of cultural sites - JackDaw helps users assess the interdependencies between rural and urban areas, highlighting mutual benefits such as tourism flows or service accessibility. Rural-urban linkage analysis: One exemplary scenario shows how to evaluate a location’s weekend tourism potential, taking into account the number of nearby urban residents, local amenities, and driving distances. This data-driven lens underscores the extent to which rural areas can attract visitors (and thus investment) from surrounding cities. Real-time, context-aware decision support: Unlike generic AI solutions, JackDaw dynamically retrieves up-to-date geospatial information before advising on policy or strategic investments. This ensures the conversation remains contextually grounded in current rural-urban realities, whether in planning new facilities or aligning local services with urban demand. Bridging analytical gaps: The video illustrates how bridging the information asymmetry between rural and urban territories can spur proactive solutions - like improved transport connections or marketing campaigns - ultimately enhancing the well-being of both communities. By demonstrating how robust data analysis can expose latent development opportunities - particularly in the context of rural-urban synergies - this video reinforces PoliRuralPlus’s broader goal of empowering decision-makers to adopt targeted, evidence-based measures that foster balanced, sustainable growth in Europe’s diverse regions.
This video compares pure large language model (LLM) outputs, such as those generated by ChatGPT, with the JackDaw (agentic tool-calling) approach. Through three real-world use cases, viewers see how incorporating domain-specific data and specialized tools yields more accurate, context-aware, and actionable answers: Weather Query Pure LLM: Provides only a generic explanation or refers to external sources, lacking direct real-time data. JackDaw (Agentic System): Dynamically calls a weather API tied to a specific area on the map, integrating real-time geospatial information. This ensures precise, location-focused forecasts rather than vague or outdated responses. Agricultural Suitability Analysis Pure LLM: Offers broad advice for potato farming, without factoring in specific local attributes like climate or soil characteristics. JackDaw: Merges real-time environmental data (land cover, elevation, weather) and LLM reasoning to assess whether a particular plot is suitable for potatoes. By pinpointing topographical and meteorological conditions, it delivers targeted, evidence-based recommendations. Identifying Water Bodies Pure LLM: May produce incorrect or incomplete references (e.g., citing the wrong river or distant city). JackDaw: Leverages land cover tools to examine hydrological layers in the specified area, accurately detecting water features. This results in data-driven, localized insights and avoids errors that arise when relying on a general model alone. Overall, the video illustrates how the JackDaw approach outperforms a standard LLM in terms of reliability, specificity, and practical utility. By integrating specialized data sources and real-time analysis into the decision-making workflow, the agent-based system consistently delivers more relevant, location-aware responses—demonstrating a clear advantage over purely text-based AI outputs.
PoliRuralPlus website Hub4Everybody integrates following components: Wagtail CMS, Map Management which includes Micka, HSLayers NG and Layman, QGIS - A Comprehensive GIS Software and QField - Mobile GIS and Data Collection App. The content of the Hub4Everybody is a feed for the AI solutions of the project. www.poliruralplus.eu https://wagtail.org
Spatially Enhanced Attractiveness Mapping Toolbox
This tool is designed to merge the capabilities of Large Language Models (LLMs) with spatial predictors and an agentic approach to enhance geospatial decision-making. While LLMs excel at generating human-like responses, they sometimes struggle with domain-specific or complex tasks. To address this, the tool uses Retrieval-Augmented Generation (RAG), allowing LLMs to retrieve specific context from specialized data sources like geospatial information.
Mallusjoki Rural Event Industry Strategy 2040 and Ecosystem This result presents the strategic outcome of the PoliRuralPlus Mallusjoki pilot, demonstrating how a rural community can strengthen long-term vitality through an event-based ecosystem approach. Developed collaboratively by Mallusjoki Youth Association, regional stakeholders and Smart & Lean Hub within the Horizon Europe PoliRuralPlus project, the strategy combines community-led development, ecosystem thinking and territorial planning into a practical implementation framework. The document introduces the Mallusjoki Rural Event Industry Ecosystem, identifying the actors, interaction flows and enabling conditions that together create a resilient rural event economy. It also presents a Regional Action Plan (RAP) extending to 2040, outlining phased actions for strengthening cultural tourism, volunteer engagement, digital transformation, sustainable mobility, green transition and local entrepreneurship. Rather than viewing individual events as isolated activities, the strategy demonstrates how recurring cultural events can become drivers of regional attractiveness, community wellbeing, economic development and rural resilience. The model highlights governance through distributed leadership, ecosystem orchestration and continuous monitoring instead of hierarchical management. The result is intended for rural communities, municipalities, regional development organisations, LEADER groups, cultural associations, policymakers and researchers seeking practical approaches to community-led rural development and event ecosystem planning. Although developed for Mallusjoki in Finland, the framework is transferable to other rural regions aiming to strengthen local identity, visitor economy and long-term territorial competitiveness through collaborative ecosystem development.
Abstract: This study explores a methodology for assessing territorial innovation potential using OpenStreetMap (OSM) data and geoinformation technologies. Traditional assessment methods often rely on aggregated statistical data, which provide a generalized view but overlook the spatial heterogeneity within regions. To address this limitation, the proposed methodology utilizes open, up-to-date OSM data to identify key infrastructure elements, such as universities, research institutions, and data centers, which drive regional innova- tion. The methodology includes data extraction, harmonization, and spatial analysis using tools like QGIS and kernel density estimation. Results from the PoliRuralPlus project pilot regions highlight significant differences in innovation potential between urban centers and rural areas, emphasizing the importance of detailed spatial data in policy making and regional development planning. The study concludes that OSM-based assessments provide spatially detailed targeted, flexible, and replicable insights into regional innovation potential compared to traditional methods. However, the limitations of crowdsourced data, such as variability in quality and completeness, are acknowledged. Future devel- opments aim to integrate OSM with official statistical data and other data resources to support more efficient and fair resource allocation and strategic investments in regional innovation ecosystems.
The PoliRuralPlus project has launched an innovative tool designed to support regional action plans, offering a digital "caddy" to guide stakeholders through complex data and planning processes. This tool, known as the PoliRuralPlus GPT, leverages the capabilities of advanced language models to provide tailored advice and insights specific to the needs of rural-urban regional planners.
SYLVAN-AI Pamphlet