Learning the laws of lithium-ion transport in electrolytes using symbolic regression

Flores, Eibar; Wölke, Christian; Yan, Peng; Winter, Martin; Vegge, Tejs; Cekic‐Laskovic, Isidora; Bhowmik, Arghya

doi:10.1039/d2dd00027j

Cited by 12 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We followed the SR approach implemented by Flores et al, originally used to develop correlations for lithium-ion electrolyte conductivity . The full K s set of 168 data points was split into ten testing and training groups for cross validation.…”

Section: Resultsmentioning

confidence: 99%

“…We followed the SR approach implemented by Flores et al, originally used to develop correlations for lithium-ion electrolyte conductivity. 46 The full K s set of 168 data points was split into ten testing and training groups for cross validation. The SR algorithm was then run on the training sets, searching through combinations of √, ∧ 1, ∧ 2, and ∧ 3 operators.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Compressibility of Lithium Hexafluorophosphate Solutions in Two Carbonate Solvents

et al. 2023

View full text Add to dashboard Cite

Speed-of-sound measurements are performed to establish how the isentropic bulk modulus K s of the electrolyte system comprising lithium hexafluorophospate (LiPF6) in blends of propylene carbonate (PC) and ethyl methyl carbonate (EMC) varies with salt molality m, mass fraction of PC in the PC:EMC cosolvent f, and temperature T. Bulk moduli are calculated by combining acoustic time-of-flight data between parallel walls of a liquid-filled cuvette with densitometric data for a sequence of binary and ternary salt solutions. Correlations are presented to yield K s (m, f, T) accurately for nine compositions spanning the range m = 0–2 mol kg–1 and f = 0–1, at temperatures T ranging from 283.15 to 313.15 K. Electrolyte compressibility varies most with solvent ratio, followed by salt content and temperature, with K s ranging from 1 to 3 GPa. Composition-dependent acoustical properties elucidate the nature of speciation and solvation states in bulk electrolytes, and could be useful to identify the features of individual phases within solution-permeated porous electrodes.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Compressibility of Lithium Hexafluorophosphate Solutions in Two Carbonate Solvents

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Furthermore, it can help to gain deeper insights regarding composition-property-performance relationships. Fractions of this dataset served as the basis for several machine learning models published elsewhere 11,13,14 . The automated high-throughput experimentation system 13 available at the Helmholtz Institute Münster is used to formulate a variety of electrolyte solutions based on EC, EMC, PC and LiPF 6 .…”

Section: Background and Summarymentioning

confidence: 99%

Conductivity experiments for electrolyte formulations and their automated analysis

et al. 2023

Self Cite

View full text Add to dashboard Cite

Electrolytes are considered crucial for the performance of batteries, and therefore indispensable for future energy storage research. This paper presents data that describes the effect of the electrolyte composition on the ionic conductivity. In particular, the data focuses on electrolytes composed of ethylene carbonate (EC), propylene carbonate (PC), ethyl methyl carbonate (EMC), and lithium hexafluorophosphate (LiPF6). The mass ratio of EC to PC was varied, while keeping the mass ratio of (EC + PC) and EMC at fixed values of 3:7 and 1:1. The conducting salt concentration was also varied during the study. Conductivity data was obtained from electrochemical impedance spectroscopy (EIS) measurements at various temperatures. Based on the thus obtained temperature series, the activation energy for ionic conduction was determined during the analysis. The data is presented here in a machine-readable format and includes a Python package for analyzing temperature series of electrolyte conductivity according to the Arrhenius equation and EIS data. The data may be useful e.g. for the training of machine learning models or for reference prior to experiments.

show abstract

“…Several methods enhancing the so-called symbolic regression approach have been developed recently [3], where the goal was to reconstruct 100 formulas from Feynman's lectures on Physics. Also in resent paper symbolic regression was applied to find thermodynamic description of ionic transport out of experimental data [4] the resulting formula reflects physical principles of underpinning ionic transport. Symbolic regression is akin to a simple regression, as it fits experimental data.…”

Section: Introductionmentioning

confidence: 99%

Symbolic expression generation via Variational Auto-Encoder

Попов¹,

Lazarev²,

Belavin³

et al. 2023

Preprint

View full text Add to dashboard Cite

There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. A widespread Deep Neural Networks do not provide interpretable solutions. Meanwhile, symbolic expressions give us a clear relation between observations and the target variable. However, at the moment, there is no dominant solution for the symbolic regression task, and we aim to reduce this gap with our algorithm. In this work, we propose a novel deep learning framework for symbolic expression generation via variational autoencoder (VAE). In a nutshell, we suggest using a VAE to generate mathematical expressions, and our training strategy forces generated formulas to fit a given dataset. Our framework allows encoding apriori knowledge of the formulas into fast-check predicates that speed up the optimization process. We compare our method to modern symbolic regression benchmarks and show that our method outperforms the competitors under noisy conditions. The recovery rate of SEGVAE is 65% on the Ngyuen dataset with a noise level of 10%, which is better than the previously reported SOTA by 20%. We demonstrate that this value depends on the dataset and can be even higher.

show abstract

Learning the laws of lithium-ion transport in electrolytes using symbolic regression

Abstract: High-throughput experiments (HTE) enable fast exploration of advanced battery electrolytes over vast compositional spaces. Among the multiple properties considered for optimal electrolyte performance, the conductivity is critical. An analytical expression...

Cited by 12 publications

References 43 publications

Compressibility of Lithium Hexafluorophosphate Solutions in Two Carbonate Solvents

Compressibility of Lithium Hexafluorophosphate Solutions in Two Carbonate Solvents

Conductivity experiments for electrolyte formulations and their automated analysis

Symbolic expression generation via Variational Auto-Encoder

Contact Info

Product

Resources

About