Pinned Loading

1. 2x_temperature_sr_project 2x_temperature_sr_project Public

   Transformer-based super-resolution for AMSR-2 thermal satellite imagery using SwinIR + Real-ESRGAN. Achieves 2× native upsampling with cascaded 8× capability and physics-aware loss functions.

   Python

2. unet_resnet_sr unet_resnet_sr Public

   Deep-learning super-resolution model for AMSR-2 thermal imagery using a U-Net architecture with a ResNet encoder, bicubic-residual refinement, and physics-aware loss terms. Provides 2× native upsam…

   Python

3. L_U-Net_ResNet_2x L_U-Net_ResNet_2x Public

   This repository implements a neural network that upscales low-resolution brightness temperature data from AMSR2 satellite observations by 2×, 4×, or 8×. The model uses spatial attention mechanisms …

   Python

4. ZRRS_Attention ZRRS_Attention Public

   Self-supervised deep learning framework that trains on the input image itself to achieve 4×, 8×, or 16× super-resolution without external training data. Features CBAM-style attention mechanisms, mu…

   Python

5. amsr2_project amsr2_project Public

   Automated pipeline for downloading and archiving 13+ years of AMSR-2 brightness temperature observations from JAXA G-Portal. Parallel HDF5 processing with incremental backups, multiple storage form…

   Python

6. Server_SatelliteProcessor Server_SatelliteProcessor Public

   Desktop application and HPC framework for AMSR-2 thermal data. Features automated GPORTAL downloads, EASE-Grid 2.0 polar projection, and deep learning enhancement using cascaded SwinIR-ESRGAN archi…

   Python