构建首个跨模态多任务地理表征评测基准，支持全球城市数据统一评估。
OBSR: Open Benchmark for Spatial Representations
- 设计跨模态、多任务的地理表征评测框架，覆盖7个全球城市数据集。
- 在3大洲7个城市数据上验证模型性能，支持多种地理现象建模。
- 提供简洁任务基线，便于复杂模型对比，适合地理人工智能研究者使用。
GeoAI 正迅速发展，得益于交通模式、环境数据及众包的 OpenStreetMap（OSM）等多样化地理空间数据。尽管先进 AI 模型不断涌现，现有评测基准仍集中于单一任务且局限于特定模态，限制了 GeoAI 的系统性评估。本文提出一个新型基准，用于评估地理嵌入模型的性能、准确性和效率。该基准具有模态无关性，包含来自三大洲7个不同城市的多样化数据集，确保泛化能力并减少人口偏差。它支持对体现地理过程的各种现象进行嵌入模型评估。此外，我们建立了简单直观的任务导向模型基线，为更复杂方案的比较提供关键参考。
原文摘要 · Abstract (English)
GeoAI is evolving rapidly, fueled by diverse geospatial datasets like traffic patterns, environmental data, and crowdsourced OpenStreetMap (OSM) information. While sophisticated AI models are being developed, existing benchmarks are often concentrated on single tasks and restricted to a single modality. As such, progress in GeoAI is limited by the lack of a standardized, multi-task, modality-agnostic benchmark for their systematic evaluation. This paper introduces a novel benchmark designed to assess the performance, accuracy, and efficiency of geospatial embedders. Our benchmark is modality-agnostic and comprises 7 distinct datasets from diverse cities across three continents, ensuring generalizability and mitigating demographic biases. It allows for the evaluation of GeoAI embedders on various phenomena that exhibit underlying geographic processes. Furthermore, we establish a simple and intuitive task-oriented model baselines, providing a crucial reference point for comparing more complex solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。