arXiv subjects

Levente Juhasz

Publications and source records attributed to Levente Juhasz.

5 recordsLinked to original sources

arXiv2026

Accelerating Point-in-Polygon Predicates via Algebraic Hash-Joins and Discrete Global Grids at Scale: An interactive benchmark

Traditional vector-based point-in-polygon queries rely on computationally expensive geometric predicates that scale poorly for massive datasets, even when accelerated by spatial indices. Discrete Global Grid Systems (DGGS) offer a scalable alternative by discretizing geometries into hierarchical cells, transforming complex spatial relations into constant-time relational hash-joins. However, adopting a DGGS introduces an overhead to encode data, and current grid implementations exhibit a significant performance ``tooling gap.'' In this demonstration, we present an interactive dashboard that empirically evaluates these computational tradeoffs across four DGGS implementations (H3, S2, A5, and ISEA4H) using DuckDB. Through progressive scenarios, the platform visualizes the overhead of on-the-fly encoding and demonstrates how pre-indexing spatial datasets eliminates this overhead. Ultimately, the demo proves that when data is pre-indexed, all DGGS regardless of their mathematical complexity or tooling converge to sub-second join latencies, unlocking the throughput of modern vectorized execution engines.

cs.DB↗

arXiv2026

A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development

WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3-track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), roughly halved trial-to-trial output variance relative to static prompting in a controlled experiment, and prevented common infodemic mapping errors in a 5-condition COVID-19 cartography ablation study. Operationalized via the open-source AgentLoom toolkit, this externalized governance provides the stability necessary for production-level geospatial engineering.

cs.AI↗

arXiv2024

Correctness Comparison of ChatGPT-4, Gemini, Claude-3, and Copilot for Spatial Tasks

Generative AI including large language models (LLMs) has recently gained significant interest in the geo-science community through its versatile task-solving capabilities including programming, arithmetic reasoning, generation of sample data, time-series forecasting, toponym recognition, or image classification. Most existing performance assessments of LLMs for spatial tasks have primarily focused on ChatGPT, whereas other chatbots received less attention. To narrow this research gap, this study conducts a zero-shot correctness evaluation for a set of 76 spatial tasks across seven task categories assigned to four prominent chatbots, i.e., ChatGPT-4, Gemini, Claude-3, and Copilot. The chatbots generally performed well on tasks related to spatial literacy, GIS theory, and interpretation of programming code and functions, but revealed weaknesses in mapping, code writing, and spatial reasoning. Furthermore, there was a significant difference in correctness of results between the four chatbots. Responses from repeated tasks assigned to each chatbot showed a high level of consistency in responses with matching rates of over 80% for most task categories in the four chatbots.

cs.CY↗

arXiv2022

'I think I discovered a military base in the middle of the ocean' -- Null Island, the most real of fictional places

This paper explores Null Island, a fictional place located at 0$^\circ$ latitude and 0$^\circ$ longitude in the WGS84 geographic coordinate system. Null Island is erroneously associated with large amounts of geographic data in a wide variety of location-based services, place databases, social media and web-based maps. While it was originally considered a joke within the geospatial community, this article will demonstrate implications of its existence, both technological and social in nature, promoting Null Island as a fundamental issue of geographic information that requires more widespread awareness. The article summarizes error sources that lead to data being associated with Null Island. We identify four evolutionary phases which help explain how this fictional place evolved and established itself as an entity reaching beyond the geospatial profession to the point of being discovered by the visual arts and the general population. After providing an accurate account of data that can be found at (0, 0), geospatial, technological and social implications of Null Island are discussed. Guidelines to avoid misplacing data to Null Island are provided. Since data will likely continue to appear at this location, our contribution is aimed at both GIScientists and the general population to promote awareness of this error source.

cs.HC↗

arXiv2022

OpenStreetMap data use cases during the early months of the COVID-19 pandemic

Created by volunteers since 2004, OpenStreetMap (OSM) is a global geographic database available under an open access license and currently used by a multitude of actors worldwide. This chapter describes the role played by OSM during the early months (from January to July 2020) of the ongoing COVID-19 pandemic, which - in contrast to past disasters and epidemics - is a global event impacting both developed and developing countries. A large number of COVID-19-related OSM use cases were collected and grouped into a number of research frameworks which are analyzed separately: dashboards and services simply using OSM as a basemap, applications using raw OSM data, initiatives to collect new OSM data, imports of authoritative data into OSM, and traditional academic research on OSM in the COVID-19 response. The wealth of examples provided in the chapter, including an analysis of OSM tile usage in two countries (Italy and China) deeply affected in the earliest months of 2020, prove that OSM has been and still is heavily used to address the COVID-19 crisis, although with types and mechanisms that are often different depending on the affected area or country and the related communities.

cs.CY↗