ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

• URL: http://arxiv.org/abs/2404.14712v1
• Date: Tue, 23 Apr 2024 03:39:57 GMT
• Title: ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability
• Authors: Xiao Wang, Aristeidis Tsaris, Siyan Liu, Jong-Youl Choi, Ming Fan, Wei Zhang, Junqi Yin, Moetasim Ashfaq, Dan Lu, Prasanna Balaprakash,
• Abstract summary: We introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT) ORBIT is the largest model of its kind and surpasses the current climate AI foundation model size by a thousandfold. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.
• Score: 11.212953738928531
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision-transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 230 to 707 PFLOPS, with scaling efficiency maintained at 78% to 96% across 24,576 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Related papers

• A Scalable Real-Time Data Assimilation Framework for Predicting Turbulent Atmosphere Dynamics [8.012940782999975]
  We introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF) and a vision transformer-based surrogate. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier.
  arXiv  Detail & Related papers  (2024-07-16T20:44:09Z)
• Aurora: A Foundation Model of the Atmosphere [56.97266186291677]
  We introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data. In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts.
  arXiv  Detail & Related papers  (2024-05-20T14:45:18Z)
• Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method [66.80344502790231]
  We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset. Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors. Our proposed method outperforms other specially designed baseline models on multiple surface variables.
  arXiv  Detail & Related papers  (2024-01-22T14:02:56Z)
• Foundation Models for Generalist Geospatial Artificial Intelligence [3.7002058945990415]
  This paper introduces a first-of-a-kind framework for the efficient pre-training and fine-tuning of foundational models on extensive data. We have utilized this framework to create Prithvi, a transformer-based foundational model pre-trained on more than 1TB of multispectral satellite imagery.
  arXiv  Detail & Related papers  (2023-10-28T10:19:55Z)
• STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning [82.03481509373037]
  Recently, model-based reinforcement learning algorithms have demonstrated remarkable efficacy in visual input environments. We introduce Transformer-based wORld Model (STORM), an efficient world model architecture that combines strong modeling and generation capabilities. Storm achieves a mean human performance of $126.7%$ on the Atari $100$k benchmark, setting a new record among state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-14T16:42:02Z)
• Simulation-based Inference for Exoplanet Atmospheric Retrieval: Insights from winning the Ariel Data Challenge 2023 using Normalizing Flows [0.0]
  We present novel machine learning models developed by the AstroAI team for the Ariel Data Challenge 2023. One of the models secured the top position among 293 competitors. We introduce an alternative model that exhibits higher performance potential than the winning model, despite scoring lower in the challenge.
  arXiv  Detail & Related papers  (2023-09-17T17:59:59Z)
• A machine learning and feature engineering approach for the prediction of the uncontrolled re-entry of space objects [1.0205541448656992]
  We present the development of a deep learning model for the re-entry prediction of uncontrolled objects in Low Earth Orbit (LEO) The model is based on a modified version of the Sequence-to-Sequence architecture and is trained on the average altitude profile as derived from a set of Two-Line Element (TLE) data of over 400 bodies. The novelty of the work consists in introducing in the deep learning model, alongside the average altitude, three new input features: a drag-like coefficient (B*), the average solar index, and the area-to-mass ratio of the object.
  arXiv  Detail & Related papers  (2023-03-17T13:53:59Z)
• Predictive World Models from Real-World Partial Observations [66.80340484148931]
  We present a framework for learning a probabilistic predictive world model for real-world road environments. While prior methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only.
  arXiv  Detail & Related papers  (2023-01-12T02:07:26Z)
• Earthformer: Exploring Space-Time Transformers for Earth System Forecasting [27.60569643222878]
  We propose Earthformer, a space-time Transformer for Earth system forecasting. The Transformer is based on a generic, flexible and efficient space-time attention block, named Cuboid Attention. Experiments on two real-world benchmarks about precipitation nowcasting and El Nino/Southerntemporaltion show Earthformer achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-07-12T20:52:26Z)
• Conditioned Human Trajectory Prediction using Iterative Attention Blocks [70.36888514074022]
  We present a simple yet effective pedestrian trajectory prediction model aimed at pedestrians positions prediction in urban-like environments. Our model is a neural-based architecture that can run several layers of attention blocks and transformers in an iterative sequential fashion. We show that without explicit introduction of social masks, dynamical models, social pooling layers, or complicated graph-like structures, it is possible to produce on par results with SoTA models.
  arXiv  Detail & Related papers  (2022-06-29T07:49:48Z)
• ProcTHOR: Large-Scale Embodied AI Using Procedural Generation [55.485985317538194]
  ProcTHOR is a framework for procedural generation of Embodied AI environments. We demonstrate state-of-the-art results across 6 embodied AI benchmarks for navigation, rearrangement, and arm manipulation.
  arXiv  Detail & Related papers  (2022-06-14T17:09:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.