使用深度神经架构搜索构建用于科学模拟的高精度仿真器
Building high accuracy emulators for scientific simulations with deep neural architecture search
摘要：
计算机模拟是科学发现的宝贵工具。然而，精确的模拟通常执行缓慢，这限制了它们对广泛的参数探索，大规模数据分析和不确定性量化的适用性。通过使用机器学习构建快速仿真器来加速模拟的一种有前途的途径需要大量的训练数据集，而使用慢速模拟来获得这些数据集可能非常昂贵。在这里，我们提出了一种基于神经结构搜索的方法，即使在训练数据数量有限的情况下也可以构建准确的仿真器。该方法使用相同的超级架构、算法和超参数，在10个科学案例中成功地将模拟加速了20亿倍，包括天体物理学、气候科学、地球化学、高能量密度物理学、聚变能和地震学。我们的方法本身也提供了仿真器的不确定性估计，增加了他们的使用进一步的信心。我们预计这项工作将加速涉及昂贵模拟的研究，允许更广泛的参数探索，并实现新的，以前不可行的计算发现。
英文摘要：
Computer simulations are invaluable tools for scientific discovery. However, accurate simulations are often slow to execute, which limits their applicability to extensive parameter exploration, large-scale data analysis, and uncertainty quantification. A promising route to accelerate simulations by building fast emulators with machine learning requires large training datasets, which can be prohibitively expensive to obtain with slow simulations. Here we present a method based on neural architecture search to build accurate emulators even with a limited number of training data. The method successfully accelerates simulations by up to 2 billion times in 10 scientific cases including astrophysics, climate science, biogeochemistry, high energy density physics, fusion energy, and seismology, using the same super-architecture, algorithm, and hyperparameters. Our approach also inherently provides emulator uncertainty estimation, adding further confidence in their use. We anticipate this work will accelerate research involving expensive simulations, allow more extensive parameters exploration, and enable new, previously unfeasible computational discovery.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
