TEMPLAR Wales is a georeferenced dataset of 3,757 Welsh settlements that links settlement locations to lexical annotations and environmental attributes. It contains 1,350 lexical detections derived from a fixed registry of 24 Welsh place-name elements, along with detailed environmental data such as river and coastal proximity, elevation, terrain context, land cover, and woody cover at multiple spatial scales. The resource is distributed as relational tables with accompanying documentation, and technical validation confirms its relational integrity, deterministic lexical reconstruction, and agreement between independent terrain sources.
By Oktay Karaku\c{s}, Can Eyupoglu
The study examined 3,757 Welsh settlements to determine whether place names encode measurable environmental information. Using a 24‑element lexical framework, researchers compared settlements with high‑terrain elements (e.g., *bryn*, *mynydd*) to those with low‑terrain elements (e.g., *cwm*, *pant*), finding that high‑terrain names were located on average 24.4 m higher than their 2‑km surroundings. Adding terrain‑name polarity to spatial models improved predictive accuracy by up to 7.3 % across various spatial blocking schemes, though results varied by region and were limited by residual spatial structure and lack of external replication.
By Oktay Karaku\c{s}, Can Eyupoglu
arXiv:2608. 03882v1 Announce Type: cross Abstract: Geospatial reasoning, i.
By Martin B\"ockling, Elizaveta Nosova, Heiko Paulheim, Andreea Iana
arXiv:2608. 07411v1 Announce Type: new Abstract: In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities.
By Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno, Lynda Tamine
Open-vocabulary Earth observation (EO) aims to localize geospatial concepts specified in natural language rather than a fixed label set. Existing benchmarks, however, usually cover narrow category vocabularies or limited query forms.
arXiv:2606. 08046v1 Announce Type: new Abstract: We present OSMGraphCLIP, a CLIP-style geospatial representation model that learns global location embeddings from freely available OpenStreetMap (OSM) data.
By Dimitrios Michail, Eleni Saka, Ioannis Giannopoulos, Ioannis Papoutsis
arXiv:2505. 18726v3 Announce Type: replace-cross Abstract: Can we determine someone's geographic location solely from the sounds they hear?
By Mustafa Chasmai, Wuao Liu, Subhransu Maji, Grant Van Horn
arXiv:2607. 14509v1 Announce Type: cross Abstract: This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images, where systems must predict every species present in high-resolution (~3000 x 3000 pixel) plot photographs while training only on single-label images of individual plants.
By Alper Erten, Murilo Gustineli, Adrian Cheung
ChiroEcho is a deep learning framework that jointly predicts bat species and genus, then uses genus predictions together with geographic species distributions to identify species not present in the training taxonomy. By incorporating geographic constraints, the system expands its effective taxonomy, enabling classification of 41 out of 48 native European bat species—an increase from 73% to 85% coverage. The study demonstrates that limited evaluation data can mask species‑level performance and that combining coarse predictions with external constraints can recover labels for unseen fine‑grained classes.
By Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum, Juan Sebasti\'an Ca\~nas, Vincent J. Kalkman, Dan Stowell, A. Leonie Baier
Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference imagery induce substantial cross-domain appearance and viewpoint shifts, challenging robust six-degree-of-freedom (6-DoF) pose estimation.
GTPred is a new benchmark for geo‑temporal prediction that evaluates multi‑modal large language models (MLLMs) on 370 images taken across 120 years worldwide. It assesses predictions by matching both the year and a hierarchical location sequence, and includes annotated reasoning chains to test intermediate reasoning. Experiments on 15 MLLMs show that while visual perception is strong, models still lack world knowledge and geo‑temporal reasoning, and that adding temporal data improves location inference.
By Jinnao Li, Tingzhu Chen, Changbo Wang
arXiv:2606. 02747v1 Announce Type: cross Abstract: Planning records define restrictions over geographic areas, but their source documents often provide only indirect spatial evidence rather than machine-readable boundaries.
By Fabian Degen, Oishi Deb, Jindong Gu, Junchi Yu, Samuele Marro, Philip Torr, Jialin Yu