cs.LGAug 27, 2026

TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements

Authors: Oktay Karakuş, Can Eyupoglu

Organizations: Department of Computer Science and Informatics, Cardiff University, Cardiff CF24 4AG, UK · Department of Computer Engineering, Turkish Air Force Academy, National Defence University, Istanbul 34149, Türkiye

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Place names provide persistent records of how landscapes have been described and organised, but their quantitative reuse requires explicit separation between mapped places, lexical annotations and environmental measurements. TEMPLAR Wales is a georeferenced environmental-toponymy dataset comprising 3,757 settlement records across Wales. The resource links a reproducible settlement frame to deterministic lexical screening and settlement-level environmental attributes through stable identifiers. It contains 1,350 lexical detections across 1,294 settlements, generated from a frozen registry of 24 Welsh place-name elements, while retaining exact- and prefix-token matches and their provenance separately. Environmental attributes describe river and coastal proximity, elevation and local terrain context at multiple spatial scales, land cover and neighbourhood woody cover, with parallel terrain measurements derived from independent elevation products. The dataset is distributed as four relational tables accompanied by a field-level data dictionary, source-provenance register and licensing metadata. Technical validation confirms relational integrity, deterministic lexical reconstruction, documented environmental coverage, strong agreement between independent terrain sources and reproducible reconstruction of the frozen release. TEMPLAR Wales provides a reusable foundation for research in toponymy, linguistic geography, historical and environmental landscape studies, GIS and spatial data analysis without treating computational lexical detections as verified etymologies or contemporary environmental measurements as historical landscape reconstructions.

Figures & tables

FileRowsColumnsContent
settlements.csv3,75723Settlement identity, source identifiers, original and analytical name fields, language-status metadata, settlement type, British National Grid coordinates, derived geographic coordinates and grouping fields for repeated names and coincident locations.
lexical_detections.csv1,35013Long-format deterministic ETDE v1 lexical detections linked to settlement records, including canonical element, matched token, token position, match type, semantic classification, preregistered role and analytical-name source.
environmental_attributes.csv3,75747Settlement-level hydrological, coastal, terrain and land-cover attributes, including OS Terrain 50 measures at multiple neighbourhood scales, Copernicus GLO-90-derived terrain attributes, CORINE-derived land-cover and woody-cover variables, and associated quality or eligibility fields.
lexical_registry.csv2411Frozen lexical registry containing canonical Welsh place-name elements, project-authored concise glosses, semantic domains, preregistered roles, source identifiers and locators, interpretation limitations and registry version information.
Table 1: Primary data records in the TEMPLAR Wales dataset.
Figure 1: Dataset overview and construction architecture. (a) Geographic distribution of the 3,757 retained Welsh settlement records. (b) The lexical stream applies analytical-name selection, the 24-element lexical registry and ETDE v1 to generate lexical_detections.csv ; the environmental stream derives settlement-level attributes from OS Open Rivers, OS Terrain 50, OS Boundary-Line, CORINE 2018 and Copernicus GLO-90. The lower portion shows the four released scientific tables and their principal templar_id and canonical-element relationships. Supporting metadata provide field definitions, provenance, licensing and release-integrity information. Contains OS data © Crown Copyright and database rights 2026.
Figure 2: Geographic coverage and composition of the released lexical resource. (a) Settlements with one or more registered ETDE v1 detections are shown in orange (n = 1,294); settlements with no registered detection are shown in grey (n = 2,463). (b) At settlement level, 1,238 records have one detection and 56 have two detections. At detection level, the long-format table contains 378 exact-token and 972 prefix-token detections. These are descriptive properties of the released lexical resource; absence of a registered detection does not imply absence of Welsh etymology or historical linguistic significance. Contains OS data © Crown Copyright and database rights 2026.
Attribute groupAvailable recordsCoverage (%)
Nearest-river distance (OS Open Rivers)3,757 / 3,757100.0
Coastal distance (OS Boundary-Line HWM)3,757 / 3,757100.0
OS Terrain 50 attributes3,757 / 3,757100.0
Copernicus GLO-90 2-km terrain attributes3,757 / 3,757100.0
CORINE point-level land-cover attributes3,757 / 3,757100.0
Woody-cover fraction, 500 m3,619 / 3,75796.3
Table 2: Coverage of the principal environmental attribute groups in the released settlement frame. Coverage refers to records with an eligible released measurement and should be interpreted together with the corresponding quality, coverage and eligibility fields.
Terrain measurePearson rrMean difference (m)MAE (m)RMSE (m)
Terrain reference0.99991581.051.181.63
Local terrain position0.99501850.172.704.04
Table 3: Agreement between settlement-level terrain attributes independently derived from OS Terrain 50 and Copernicus DEM GLO-90. All comparisons use the complete 3,757-settlement frame at the 2-km analysis scale.
Figure 3: Independent terrain-source technical validation. Agreement between terrain attributes independently derived from OS Terrain 50 and Copernicus DEM GLO-90 for all 3,757 settlements. (a) 2-km terrain reference and (b) 2-km local terrain position. In each column, the upper panel shows paired values with the 1:1 identity line; the lower panel shows the Copernicus-minus-OS difference against the paired mean. Solid horizontal lines show mean differences and dashed lines show 95% limits of agreement (mean difference ±1.96\pm 1.96 SD). Units are metres. This comparison is technical validation of independent terrain derivations and does not designate either source as absolute ground truth.

Explore similar work

CardsList
Aug 27, 2026

Terrain signatures in Welsh settlement names

Landscapes are named, but whether names retain measurable environmental information beyond broad geographic structure is rarely tested. We analysed 3,757 Welsh settlements using a frozen, source-audited 24-element lexical framework, preregistered outcome-specific models and geographically structured validation. The central comparison contrasted 101 settlements carrying high-terrain elements (bryn or mynydd) with 139 carrying low-terrain elements (cwm or pant). High-terrain names occupied locations 24.4 m higher relative to their 2-km surroundings (95% CI, 10.8--38.1 m; Holm-adjusted pp = 0.00137). The association remained positive across prespecified 1-, 2- and 5-km neighbourhood definitions and was reproduced using an independently produced elevation source (24.1 m; 95% CI, 10.6--37.6 m). Adding terrain-name polarity to a non-lexical spatial and settlement baseline reduced geographically held-out mean squared error by 4.63%, 6.22% and 7.30% under 10-, 25- and 50-km spatial blocking, respectively, although improvement varied among held-out regions. River-related names provided weaker, directionally consistent evidence, while the preregistered woodland model was non-estimable. Residual spatial structure, unresolved name language and the absence of independent external replication limit interpretation. Selected Welsh settlement-name categories therefore retain measurable information about present-day terrain within Wales, without establishing individual etymology, causal naming, historical environmental memory or transferability to other naming systems.

Oktay Karakuş, Can Eyupoglu

Department of Computer Science and Informatics, Cardiff University, Cardiff CF24 4AG, UK · Department of Computer Engineering, Turkish Air Force Academy, National Defence University, Istanbul 34149, Türkiye

Topic pending
AskPDF
Aug 7, 2026

Georeferencing Non-Gazetteered Place Names using Biological Specimen Records

Biological specimen records collected by natural history institutions constitute a rich source of temporal geographic knowledge, capturing biodiversity information about regional landscapes as they were recorded at different times. Using digitised data from the Allan Herbarium (New Zealand), this study identifies place names in these specimen locality descriptions that are absent from current gazetteers; we refer to these as non-gazetteer place names (NGPs). These place names are typically historical, vernacular, or colloquial and were used as landmarks to describe a specimen's location at the time of collection. We then investigate the problem of georeferencing the NGPs using only the limited information available in the specimen records. To resolve this, we leverage repeated occurrences of the same place name across specimen records with different specimen locations and spatial relation terms, extracting and inverting these relations to derive constraints on NGP locations. This approach is instantiated within deterministic, probabilistic, and LLM-based methods, enabling a comparative analysis of their strengths and limitations for text-based spatial inference. On a pseudo-NGP benchmark, probabilistic inference achieves the highest accuracy (median error 1.43 km; A@1 km 36%), while the LLM yields competitive but less precise estimates (median error 1.80 km; A@1 km 31%), indicating that, despite advances in LLMs, traditional modelling remains advantageous when high spatial precision is required.

Aneesha Fernando, Surangika Ranathunga, Kristin Stock +2

School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand · Joint Centre for Disaster Research, Massey University, Wellington, New Zealand · School of Computer Science and Informatics, Cardiff University, United Kingdom

Geospatial Reasoning
AskPDF
May 7, 2026

Tatarstan Toponyms: A Bilingual Dataset and Hybrid RAG System for Geospatial Question Answering

This paper addresses automatic geospatial question answering over multilingual toponymic data. An original bilingual dataset of toponyms of the Republic of Tatarstan is introduced, comprising 9,688 structured records with linguistic, etymological, administrative, and coordinate information (93.1% georeferenced). Based on this dataset, a question-answering corpus of approximately 39,000 question-context-answer triples is constructed with guaranteed answer localization. A hybrid retriever integrates dense semantic indexing (multilingual-e5-large) with geospatial filtering via KD-trees and haversine distance. On 500 test queries, the hybrid search achieves Recall@1=0.988, Recall@5=1.000, and MRR=0.994, significantly outperforming BM25 and purely spatial methods. Among tested reader architectures (RuBERT, XLM-RoBERTa-large, T5-RUS), XLM-RoBERTa-large attains the best quality: EM=0.992, F1=0.994. On raw outputs, RuBERT models fail on coordinate questions (F1=0) while XLM-RoBERTa-large reaches F1=0.984; however, simple post-processing eliminates numerical gaps and restores RuBERT accuracy to 100%. This discrepancy stems from tokenization differences and pre-training corpora composition. All resources (dataset, QA corpus, model weights, web demo) are openly published on Hugging Face. Results apply to geospatial QA services, geocoding, and digital humanities in multilingual regions.

Mullosharaf K. Arabov

Department of Data Analysis and Programming Technologies Institute of Computational Mathematics and Information Technologies Kazan (Volga Region) Federal University Kazan, Russia

Geospatial QAQuestion AnsweringGeospatial ReasoningMultilingual QAHybrid Retrieval
AskPDF