When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System
arXiv:2309.06799 · doi:10.1109/MGRS.2024.3496478
Abstract
Artificial intelligence (AI) has significantly advanced Earth sciences, yet its full potential in to comprehensively modeling Earth's complex dynamics remains unrealized. Geoscience foundation models (GFMs) emerge as a paradigm-shifting solution, integrating extensive cross-disciplinary data to enhance the simulation and understanding of Earth system dynamics. These data-centric AI models extract insights from petabytes of structured and unstructured data, effectively addressing the complexities of Earth systems that traditional models struggle to capture. The unique strengths of GFMs include flexible task specification, diverse input-output capabilities, and multi-modal knowledge representation, enabling analyses that surpass those of individual data sources or traditional AI methods. This review not only highlights the key advantages of GFMs, but also presents essential techniques for their construction, with a focus on transformers, pre-training, and adaptation strategies. Subsequently, we examine recent advancements in GFMs, including large language models, vision models, and vision-language models, particularly emphasizing the potential applications in remote sensing. Additionally, the review concludes with a comprehensive analysis of the challenges and future trends in GFMs, addressing five critical aspects: data integration, model complexity, uncertainty quantification, interdisciplinary collaboration, and concerns related to privacy, trust, and security. This review offers a comprehensive overview of emerging geoscientific research paradigms, emphasizing the untapped opportunities at the intersection of advanced AI techniques and geoscience. It examines major methodologies, showcases advances in large-scale models, and discusses the challenges and prospects that will shape the future landscape of GFMs.
accpeted by IEEE Geoscience and Remote Sensing Magazine
References in corpus (21)
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Learning to Prompt for Vision-Language Models
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- A Survey on Large Language Model based Autonomous Agents
- Self-supervised Learning: Generative or Contrastive
- Skillful Precipitation Nowcasting using Deep Generative Models of Radar
- SpectralGPT: Spectral Remote Sensing Foundation Model
- Revisiting Pre-Trained Models for Chinese Natural Language Processing
- Differentiable modeling to unify machine learning and physical models and advance Geosciences
- Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
- Will Artificial Intelligence supersede Earth System and Climate Models?
- The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
- Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images
- Bridging observation, theory and numerical simulation of the ocean using Machine Learning
- Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
- A Billion-scale Foundation Model for Remote Sensing Images
- Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis
- Learning from models beyond fine-tuning
- When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges
- Visual Tuning
- Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models