2026-10-07T04:27:40Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33733438 2026-09-17T13:58:06Z category_25732 item_type_3 month_year_09_2026

Dataset for Deep Learning-Based Separation and Quantification of Overlapping Methane Plumes from Satellite Observations Hongzhi Zou (24781699) Atmospheric composition, chemistry and processes methane plume separation deep learning U-Net 3+ integrated mass enhancement <p dir="ltr">This dataset supports training a spatial-attention U-Net 3+ model, evaluating overlapping methane plume separation, and estimating individual source emission rates using integrated mass enhancement (IME).</p><p dir="ltr">The overlapping_plumes(2-8)-V2 directory includes 28,000 training, 2,800 validation and 700 test samples. The overlapping_plumes(2-8)-V2_Add_S10 directory contains the same 700-sample test subset with additional wind metadata. Each split includes paired combined_plumes and labels NPZ files and images_png previews.</p><p dir="ltr">The archive contains 96,601 files. No trained checkpoint is included. See DATASET_README.md and dataset_inventory.json for data organization and reproduction instructions. SHA-256 checksums are provided in SHA256SUMS.txt.</p><p dir="ltr">Code: https://github.com/zhz1234567890/Deep-Learning-Based-Separation-and-Quantification-of-Overlapping-Methane-Plumes</p><p dir="ltr">Download all 29 binary parts and the provided parts_manifest.json and reassemble_dataset.py into the same folder. Run python reassemble_dataset.py to verify each part and restore paper_dataset_complete.zip, then extract it normally. See DOWNLOAD_INSTRUCTIONS.md. Allow approximately 50 GB of free disk space for parts, the restored ZIP, and extracted data.</p> 2026-09-17T13:58:06Z Dataset Dataset 10.6084/m9.figshare.33733438.v1 https://figshare.com/articles/dataset/Dataset_for_Deep_Learning-Based_Separation_and_Quantification_of_Overlapping_Methane_Plumes_from_Satellite_Observations/33733438 CC BY 4.0