Professor Yue Peng from the School of Remote Sensing and Information Engineering at Wuhan University (WHU) has led the drafting of the world's first international standard for geographic information artificial intelligence, titled Geographic Information - Training Data Markup Language for Artificial Intelligence - Part 1: Conceptual Model (ISO 19178-1:2025). The draft was recently released by the International Organization for Standardization (ISO).

Focusing on sample data in Earth observation AI, the standard defines a unified modeling language to standardize data annotation, metadata, provenance, quality control, and updates for sample datasets. It enhances the interoperability and usability of remote sensing image samples, supporting applications such as image processing, spatial analysis, autonomous driving, and high-precision mapping, while providing a unified foundation for AI/ML model training and validation.

Initiated in 2024 under ISO/TC 211 and developed in collaboration with CEN/TC 287, OGC, and international experts, the standard has gained recognition from organizations including the European Space Agency, NASA, and NOAA. Its release marks a key milestone in establishing global standards for geographic AI.