| intro = '''Remote sensing images from NASA's fleet of Earth-observing satellites are pivotal for applications as broad as land cover mapping, | |
| disaster monitoring, urban planning, and environmental analysis. The potential of AI-based geospatial foundation models for performing | |
| visual analysis tasks on these remote sensing images has garnered significant attention. To realize that potential, the crucial first | |
| step is to develop foundation models – computer models that acquire competence in a broad range of tasks, which can then be specialized | |
| with further training for specific applications. In this case, the foundation model is based on a large-scale vision transformer model | |
| trained with satellite imagery. | |
| Vision transformers employ AI/deep learning techniques to fine-tune the model to answer specific science questions. Through training | |
| on extensive remote sensing datasets, vision transformers can learn general relationships between the spectral data given as inputs, | |
| as well as capture high-level visual patterns, semantics, and spatial relationships that can be leveraged for a wide range of analysis tasks. | |
| Trained vision transformers can handle large-scale, high-resolution data; learn global reorientations; extract robust features; and support | |
| multi-modal data fusion – all with improved performance. | |
| The Data Science Group at NASA Goddard Space Flight Center's Computational and Information Sciences and Technology Office (CISTO) | |
| has implemented an end-to-end workflow to generate a pre-trained vision transformer which could evolve into a foundation model. | |
| A training dataset of over 2 million 128x128 pixel “chips” has been created from NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS) | |
| surface reflectance products (MOD09). These data were used to train a SwinV2 vision transformer that we call SatVision. | |
| ''' | |