Global XCH₄ Data Product (2024–2025) from TROPOMI and GOSAT using Transfer Learning

Global XCH₄ Dataset (2024–2025) is generated using a multi-satellite transfer learning framework, covering the period from 1 January 2024 to 31 December 2025. The retrieval algorithm employs a probabilistic multilayer perceptron neural network pretrained on TROPOMI observations and fine-tuned with high-accuracy GOSAT retrievals. The data product is stored in Parquet format with native TROPOMI spatial resolution, containing six variables: longitude, latitude, scanline, and pixel (extracted from original TROPOMI products), along with methane_mixing_ratio (XCH₄ in ppb) and uncertainty (pixel-level uncertainty estimates) provided by this study. Data files are named by sensing start and end times extracted from original TROPOMI filenames (e.g., 20240101T074458_20240101T092629.parquet), with a geographical domain spanning 60°S–90°N and 180°W–180°E (global terrestrial regions, excluding Antarctica). For detailed access information, contact the corresponding author ([e-mail]).