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.
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
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.
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.