Skip navigation

Document library

Bridging Global Language Models and Local Spatial Data

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.

topic: Others
type: Products & prototypes, Publication
language: English
Info4Agro Comprehensive tutorial

This document provides a practical and user-oriented tutorial for the Info4Agro web-based Decision Support System (DSS) for precision agriculture. It is intended to support farmers, agronomists, and advisors in understanding and effectively using the platform’s key functionalities. The document introduces Info4Agro as an integrated system combining IoT sensor data, satellite remote sensing, weather and climate information, and agronomic analytics to support data-driven agricultural decision-making. It describes the project-based workflow, including project creation, management of field boundaries, and the configuration of temporal parameters that influence data processing. Core sections of the document focus on sensor data visualization, explaining how users access real-time and historical meteorological data, explore time series, compare multiple sensors, and interpret basic statistical indicators. The tutorial also covers satellite imagery management, including image selection, handling of cloud-affected scenes, and the calculation of key vegetation indices such as NDVI, EVI, and SAVI. A dedicated part is devoted to the generation of Variable Rate Application (VRA) fertilization maps, outlining the required inputs, zoning workflow, and export of results in standard formats for precision farming machinery. In addition, the document describes climate-based planning tools, which enable users to analyze historical climate conditions, precipitation, temperature patterns, and water balance for strategic agricultural planning. The tutorial concludes with notes on user experience and interface design, emphasizing usability, clarity of visualization, and workflow efficiency. Overall, the document serves as a concise training and reference guide that supports the practical adoption of advanced digital technologies in precision agriculture.

topic: Agriculture
type: Workshops & webinars
language: English
OpenStreetMap as the Data Source for Territorial Innovation Potential Assessment

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.

topic: Others
type: Products & prototypes, Publication
language: English