arXiv subjects

Simon Ternes

Publications and source records attributed to Simon Ternes.

3 recordsLinked to original sources

arXiv2026

A green solvent screening tool for emerging materials via uncertainty aware, transformer enhanced transfer learning

Accurate prediction of solubility remains a central challenge across materials science and sustainable chemistry. In particular due to emerging technologies like organic and hybrid photovoltaics, batteries, and catalysis, solvent usage is expected to increase significantly within the coming years. Therefore, substituting solvents with greener alternatives is vital. This is where machine learning can have substantial impact. However, the limited data on critical parameters of solubility significantly constraints machine learning efficacy. In this work, we transfer a pre-trained foundational model on QM9 targets to our application with minimal data requirements. Additionally, the pipeline integrates uncertainty quantification, allowing the user to gauge the confidence of the predictions. As baseline, we succeed in predicting the Hansen solubility parameters and Dielectric Constant for which extensive databases exist. Importantly, we achieve high model performance on additional targets, such as Gutmann Donor and Acceptor numbers, where the available data is extremely limited. Overall, we augment data on solubility descriptors by orders of magnitude with high quality predictions. For effective dissemination, we deploy easy-to-use, easily integrateable with high throughput labs, customizable tool for ranking and screening possible solvent substitutes. Finally, we rediscovered known green solvent alternatives and proposed new candidates proving its relevance for finding eco-friendly solvents.

cs.LG↗

arXiv2026

Quantifying Perovskite Solar Cell Degradation via Machine Learning from Spatially Resolved Multimodal Luminescence Time Series

Perovskite solar cells achieve remarkable power conversion efficiencies, yet operational stability remains a major barrier to large-scale deployment. Reliable and rapid assessment of device state of health is therefore essential. Conventional electrical diagnostics, such as illuminated current-voltage (J--V) sweeps, provide accurate performance metrics but are time-consuming and do not resolve spatially localized degradation, motivating non-invasive imaging-based alternatives. A deep-learning framework is introduced to estimate PSC efficiency retention, $R_\mathrm{PCE}=\mathrm{PCE}_t/\mathrm{PCE}_0$, directly from multimodal luminescence imaging acquired during device aging. Each sample combines electroluminescence (EL), open-circuit photoluminescence (PLoc), and short-circuit photoluminescence (PLsc) at an aged state with device-specific reference images at $t=0$, enabling learning of degradation-relevant spatial changes. LumPerNet, a compact convolutional neural network, is benchmarked against a spatially homogenized control in which each luminescence channel is replaced by its spatial average while retaining the same learning framework and leakage-aware protocol. The comparison indicates that global luminescence evolution contains most of the predictive signal, while spatial information provides a secondary contribution to robustness. These results establish spatially resolved luminescence imaging as a practical route for accelerated stability testing and non-invasive degradation monitoring in perovskite photovoltaics.

cond-mat.mtrl-sci↗

arXiv2025

Consistent control of drying rates of solution thin films on wafer-sized substrates by dynamic air-knife drying with optimal trajectories

This work tackles the problem of achieving consistent drying rates of a solution film deposited on a $20\,\rm{cm}$-wide substrate ($\approx $ silicon-wafer size) that is driven under a narrow air flow ejected by a slot nozzle (or "air knife"). The main prerequisite of the work is that the drying rate of the solution film is highly decisive for a certain performance indicator of the deposited film at a particular, critical concentration $c_{\rm crit.}$. Empirically, this concentration can be associated with the visual observation of "the drying front" as, for the example of hybrid perovskite thin films, caused by the onset of a crystallization process. As a main result, a set of equations for achieving consistent drying rates, $\dot{d}_{\rm crit.}$, at critical concentration is presented that is solved by a simple two-staged least-squares gradient decent. From the resulting velocity vector, an optimal trajectory of the air knife, $\hat{x}(t)$, depending on the initial wet film thickness distribution over the substrate is derived. It is demonstrated that scenarios where the wet film thickness increases along the movement direction of the air knife have a consistent set of equations. Wet thin films that do not obey this constraint, as in the demonstrated scenarios with convex and concave shapes of wet film thickness over the substrate area, cannot always be dried in a fully consistent way by optimizing the air-knife trajectory alone. However, with the presented methods, optimal trajectories can still be derived that enable more homogeneous drying results.

physics.flu-dyn↗