Aluminosilicate glasses and melts are of paramount importance for geo- and materials sciences. They include most magmas, and are used to produce a wide variety of everyday materials, from windows to smartphone displays. Despite this importance, no general model exists with which to predict the atomic structure, thermodynamic and viscous properties of aluminosilicate melts. To address this, we introduce a deep learning framework, ‘i-Melt’, which combines a deep artificial neural network with thermodynamic equations. It is trained to predict 18 different latent and observed properties of melts and glasses in the K₂O-Na₂O-Al₂O₃-SiO₂ system, including configurational entropy, viscosity, optical refractive index, density, and Raman signals. Viscosity can be predicted in the 10⁰–10¹⁵ log₁₀ Pa·s range using five different theoretical frameworks (Adam-Gibbs, Free Volume, MYEGA, VFT, Avramov-Milchev), with a precision equal to, or better than, 0.4 log₁₀ Pa·s on unseen data. Density and optical refractive index (through the Sellmeier equation) can be predicted with errors equal or lower than 0.02 and 0.006, respectively. Raman spectra for K₂O-Na₂O-Al₂O₃-SiO₂ glasses are also predicted, with a relatively high mean error of ∼25% due to the limited data set available for training. Latent variables can also be predicted with good precisions. For example, the glass transition temperature, T_g, can be predicted to within 19 K, while the melt configurational entropy at the glass transition, S^conf(T_g), can be predicted to within 0.8 J mol⁻¹ K⁻¹.

Applied to rhyolite compositions, i-Melt shows that the rheological threshold separating explosive and effusive eruptions correlates with an increase in the fraction of non-bridging oxygens in rhyolite melts as their alkali/Al ratio becomes larger than 1. Exploring further the effect of the K/(K + Na) ratio on the properties of alkali aluminosilicate melts with compositions varying along a simplified alkali magmatic series trend, we observe that K-rich melts have systematically different structures and higher viscosities compared to Na-rich melts. Combined with the effects of the K/(K + Na) ratio on other parameters, such as the solubility, solution mechanisms and speciation of volatile elements, this could ultimately influence the eruptive dynamics of volcanic systems emitting Na-rich or K-rich alkali magmas.

铝硅酸盐玻璃和熔体对于地质和材料科学至关重要。它们包含大多数岩浆，用于生产从窗户到智能手机显示屏的各种日常材料。尽管如此重要，但不存在预测铝硅酸盐熔体的原子结构、热力学和粘性特性的通用模型。为了解决这个问题，我们引入了一个深度学习框架“i-Melt”，它将深度人工神经网络与热力学方程相结合。经过训练，可以预测 K ₂ O-Na ₂ O-Al ₂ O ₃ -SiO ₂中熔体和玻璃的 18 种不同的潜在和观察到的特性系统，包括配置熵、粘度、光学折射率、密度和拉曼信号。可以使用五种不同的理论框架（Adam-Gibbs、自由体积、MYEGA、VFT、Avramov-Milchev）在 10 ⁰ –10 ¹⁵ log ₁₀ Pa·s 范围内预测粘度，精度等于或优于 0.4在看不见的数据上记录₁₀ Pa·s。密度和光学折射率（通过 Sellmeier 方程）可以分别以等于或低于 0.02 和 0.006 的误差进行预测。K ₂ O-Na ₂ O-Al ₂ O ₃ -SiO _{2 的}拉曼光谱眼镜也被预测，由于可用于训练的数据集有限，平均误差相对较高，约为 25%。潜在变量也可以以良好的精度进行预测。例如，玻璃化转变温度，Ť_克，可以预测到第19面K内，而熔体构型熵在玻璃化转变，小号^CONF（T_克），可被内为0.8J摩尔预测为^-1 ķ ^-1。

应用于流纹岩组合物时，i-Melt 表明，当流纹岩熔体的碱/铝比大于 1 时，将爆炸性喷发和喷发性喷发分开的流变阈值与流纹岩熔体中非桥连氧比例的增加相关。 进一步探索K/(K + Na) 比对成分沿简化的碱性岩浆系列趋势变化的碱金属铝硅酸盐熔体的性质进行比较，我们观察到富钾熔体与富钠熔体相比具有系统不同的结构和更高的粘度。结合 K/(K + Na) 比对其他参数的影响，如溶解度、溶液机制和挥发性元素的形态，这可能最终影响排放富钠或富钾碱的火山系统的喷发动力学岩浆。