MaNN: Multiple Artificial Neural Networks for modelling the Interstellar Medium
MaNN: Multiple Artificial Neural Networks for modelling the Interstellar Medium
复制标题
MaNN：用于建模星际介质的多个人工神经网络
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
C. Chiosi
中科院分区：
文献类型：
--
作者：
T. Grassi;E. Merlin;L. Piovan;U. Buonomo;C. Chiosi
Department of Astronomy, Padova University, Vicolo dell’Osservatorio 3, I-35122, Padova, Italye-mail: tommaso.grassi@unipd.it, cesare.chiosi@unipd.it 收到日期：2011 年 3 月；修改： *** ***;已接受：*** ***摘要。在大规模数值模拟的背景下对星际介质 (ISM) 的复杂物理进行建模是一项具有挑战性的任务。已经提出了多种方法来将 ISM 的描述嵌入到不同的代码中。我们提出了一种实现此任务的新方法：人工神经网络（ANN）。方法。人工神经网络已经在预编译的模型数据库上进行了训练，并将其预测与预期的理论预测进行了比较，在使用 Padova Tree-SPH 代码 EvoL 运行的静态和动态测试中都发现了良好的一致性。结果。神经网络可以重现星际气体演化的细节，需要有限的计算资源。我们建议这种算法可以取代质量元素化学演化的实时计算 流体动力学代码。关键词。 ISM：演化 - 方法：数值 - 星系：演化
Department of Astronomy, Padova University, Vicolo dell’Osservatorio 3, I-35122, Padova, Italye-mail: tommaso.grassi@unipd.it, cesare.chiosi@unipd.itReceived: March 2011; Revised: *** ***; Accepted: *** ***ABSTRACTAims.Modelling the complex physics of the Interstellar Medium (ISM) in the context of large-scale numerical simulations is achallenging task. A number of methods have been proposed to embed a description of the ISM into different codes. We proposea new way to achieve this task: Artificial Neural Networks (ANNs).Methods. The ANN has been trained on a pre-compiled model database, and its predictions have been compared to theexpected theoretical ones, finding good agreement both in static and in dynamical tests run using the Padova Tree-SPH codeEvoL.Results.A neural network can reproduce the details of the interstellar gas evolution, requiring limited computational resources.We suggest that such an algorithm can replace a real-time calculation of mass elements chemical evolution in hydrodynamicalcodes.Key words. ISM: evolution - methods: numerical - galaxies: evolution