scholarly journals How machine learning can help select capping layers to suppress perovskite degradation

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Noor Titan Putri Hartono ◽  
Janak Thapa ◽  
Armi Tiihonen ◽  
Felipe Oviedo ◽  
Clio Batali ◽  
...  
Keyword(s):  
Machine Learning ◽  
Perovskite Solar Cells ◽  
Supervised Machine Learning ◽  
Environmental Stability ◽  
Lead Iodide ◽  
Film Stability ◽  
Organic Halide ◽  
Capping Layer ◽  
Shapley Values ◽  
Low Dimensional

Abstract Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI3) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules’ low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI3 film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI3 stability lifetime by 4 ± 2 times over bare MAPbI3 and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss.

scholarly journals How machine learning can help select capping layers to suppress perovskite degradation

2020 ◽  
Author(s):  
Noor Titan Putri Hartono ◽  
Janak Thapa ◽  
Armi Tiihonen ◽  
Felipe Oviedo ◽  
Clio Batali ◽  
...  
Keyword(s):  
Machine Learning ◽  
Perovskite Solar Cells ◽  
Hole Transport ◽  
Transport Layer ◽  
Environmental Stability ◽  
Hole Transport Layer ◽  
Lead Iodide ◽  
Film Stability ◽  
Organic Halide ◽  
Capping Layer

Environmental stability of perovskite solar cells (PSCs) can be improved by a thin layer of low-dimensional (LD) perovskite sandwiched between the perovskite absorber and the hole transport layer (HTL). This layer, called ‘capping layer,’ has mostly been optimized by trial and error. In this study, we present a machine-learning framework to rationally design and optimize perovskite capping layers. We ‘featurize’ 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI<sub>3</sub>) thin films, age them under accelerated conditions combining illumination and increased humidity and temperature, and determine features governing stability using random forest regression and SHAP (SHapley Additive exPlanations). We find that a low number of hydrogen-bonding donors and a small topological polar surface area of the organic molecules correlate with increased MAPbI<sub>3</sub> film stability. The top performing organic halide salt, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI<sub>3</sub> stability lifetime by 4±2 times over bare MAPbI<sub>3</sub> and 1.3±0.3 times over state-of-the-art octylammonium bromide (OABr). Through morphological and synchrotron-based structural characterization, we found that this capping layer consists of a Ruddlesden-Popper perovskite structure and stabilizes the photoactive layer by “sealing off” the grain boundaries and changing the lead surface chemistry, through the suppression of lead (II) iodide (PbI<sub>2</sub>) formation and methylammonium loss.

scholarly journals How machine learning can help select capping layers to suppress perovskite degradation

2020 ◽  
Author(s):  
Noor Titan Putri Hartono ◽  
Janak Thapa ◽  
Armi Tiihonen ◽  
Felipe Oviedo ◽  
Clio Batali ◽  
...  
Keyword(s):  
Machine Learning ◽  
Perovskite Solar Cells ◽  
Hole Transport ◽  
Transport Layer ◽  
Environmental Stability ◽  
Hole Transport Layer ◽  
Lead Iodide ◽  
Film Stability ◽  
Organic Halide ◽  
Capping Layer

Environmental stability of perovskite solar cells (PSCs) can be improved by a thin layer of low-dimensional (LD) perovskite sandwiched between the perovskite absorber and the hole transport layer (HTL). This layer, called ‘capping layer,’ has mostly been optimized by trial and error. In this study, we present a machine-learning framework to rationally design and optimize perovskite capping layers. We ‘featurize’ 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI<sub>3</sub>) thin films, age them under accelerated conditions combining illumination and increased humidity and temperature, and determine features governing stability using random forest regression and SHAP (SHapley Additive exPlanations). We find that a low number of hydrogen-bonding donors and a small topological polar surface area of the organic molecules correlate with increased MAPbI<sub>3</sub> film stability. The top performing organic halide salt, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI<sub>3</sub> stability lifetime by 4±2 times over bare MAPbI<sub>3</sub> and 1.3±0.3 times over state-of-the-art octylammonium bromide (OABr). Through morphological and synchrotron-based structural characterization, we found that this capping layer consists of a Ruddlesden-Popper perovskite structure and stabilizes the photoactive layer by “sealing off” the grain boundaries and changing the lead surface chemistry, through the suppression of lead (II) iodide (PbI<sub>2</sub>) formation and methylammonium loss.

scholarly journals Tailoring capping-layer composition for improved stability of mixed-halide perovskites

2022 ◽  
Author(s):  
Noor Titan Putri Hartono ◽  
Marie-Hélène Tremblay ◽  
Sarah Wieghold ◽  
Benjia Dou ◽  
Janak Thapa ◽  
...  
Keyword(s):  
Solar Cells ◽  
Perovskite Solar Cells ◽  
Capping Layer ◽  
Improved Stability ◽  
Halide Perovskites ◽  
The Stability ◽  
Low Dimensional ◽  
Layer Composition

Incorporating a low dimensional (LD) perovskite capping layer on top of perovskite absorber, improves the stability of perovskite solar cells (PSCs). However, in the case of mixed-halide perovskites, which can...

scholarly journals Combining trajectory optimization, supervised machine learning, and model structure for mitigating the curse of dimensionality in the control of bipedal robots

2019 ◽  
Vol 38 (9) ◽  
pp. 1063-1097 ◽  
Author(s):  
Xingye Da ◽  
Jessy Grizzle
Keyword(s):  
Machine Learning ◽  
Trajectory Optimization ◽  
Open Loop ◽  
Supervised Machine Learning ◽  
High Dimensional ◽  
Dimensional Model ◽  
Bipedal Robots ◽  
State Variable ◽  
Walking Motion ◽  
Low Dimensional

To overcome the obstructions imposed by high-dimensional bipedal models, we embed a stable walking motion in an attractive low-dimensional surface of the system’s state space. The process begins with trajectory optimization to design an open-loop periodic walking motion of the high-dimensional model and then adding to this solution a carefully selected set of additional open-loop trajectories of the model that steer toward the nominal motion. A drawback of trajectories is that they provide little information on how to respond to a disturbance. To address this shortcoming, supervised machine learning is used to extract a low-dimensional state-variable realization of the open-loop trajectories. The periodic orbit is now an attractor of the low-dimensional state-variable model but is not attractive in the full-order system. We then use the special structure of mechanical models associated with bipedal robots to embed the low-dimensional model in the original model in such a manner that the desired walking motions are locally exponentially stable. The design procedure is first developed for ordinary differential equations and illustrated on a simple model. The methods are subsequently extended to a class of hybrid models and then realized experimentally on an Atrias-series 3D bipedal robot.

scholarly journals The Effect of Structural Dimensionality on Carrier Mobility in Lead-Halide Perovskites

2019 ◽  
Author(s):  
Noor Titan Putri Hartono ◽  
Shijing Sun ◽  
María Gélvez-Rueda ◽  
Polly Pierone ◽  
Matthew Erodici ◽  
...  
Keyword(s):  
Solar Cells ◽  
Charge Carrier ◽  
Carrier Mobility ◽  
Perovskite Solar Cells ◽  
Charge Carrier Mobility ◽  
Lead Iodide ◽  
Optical Pump ◽  
Structural Dimensionality ◽  
Low Dimensional ◽  
Lower Dimensional

<p>Methylammonium lead iodide (MAPI) is a prototypical photo absorber in perovskite solar cells (PSCs), reaching efficiencies above 20%. However, its hygroscopic nature has prompted the quest to find water-resistant alternatives. Recent studies have suggested that mixing MAPI with lower dimensional, bulky-<i>A</i>-site-cation perovskites helps mitigate this environmental instability. On the other hand, low dimensional perovskites suffer from poor device performance, which has been suggested to be due to limited out-of-plane charge carrier mobility resulting from structural dimensionality and large binding energy of the charge carriers. To understand the effects of dimensionality on performance, we systematically mixed MA-based 3D perovskites with larger <i>A</i>-site cation, dimethylammonium, iso-propylammonium, and t-butylammonium lead iodide perovskites. During the shift from MAPI to lower dimensional (LD) PSCs, the efficiency is significantly reduced by 2 orders of magnitude, with short-circuit currents decreasing from above 20 mA/cm<sup>2</sup> to less than 1 mA/cm<sup>2</sup>. In order to explain these decrease in performance, we studied the charge carrier mobilities of these materials using optical-pump/ terahertz-probe, time-resolved microwave photoconductivity, and photoluminescence measurements. The results show that as we add more of the low dimensional perovskites, the mobility decreases by a factor of 20 when it reaches pure LD perovskites. In addition, the photoluminescence decay fitting is slightly slower for the mixed perovskites, suggesting some improvement in the recombination dynamics. These findings indicate that changes in structural dimensionality by mixing<i> A</i>-site cations play an important role in measured charge carrier mobility, and in the performance of perovskite solar cells.</p>

High performance low-dimensional perovskite solar cells based on a one dimensional lead iodide perovskite

2019 ◽  
Vol 7 (15) ◽  
pp. 8811-8817 ◽  
Author(s):  
Chunqing Ma ◽  
Dong Shen ◽  
Bin Huang ◽  
Xiaocui Li ◽  
Wen-Cheng Chen ◽  
...  
Keyword(s):  
Solar Cells ◽  
High Performance ◽  
Perovskite Solar Cells ◽  
Lead Iodide ◽  
One Dimensional ◽  
Low Dimensional

One-dimensional perovskites enable high performance low-dimensional perovskite solar cells.

scholarly journals Advances in Dion-Jacobson phase two-dimensional metal halide perovskite solar cells

Nanophotonics ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Tianqi Niu ◽  
Qifan Xue ◽  
Hin-Lap Yip
Keyword(s):  
Solar Cells ◽  
Perovskite Solar Cells ◽  
Three Dimensional ◽  
Metal Halide ◽  
Environmental Stability ◽  
Two Dimensional ◽  
Structure Property ◽  
Photovoltaic Efficiency ◽  
Functional Behavior ◽  
Low Dimensional

Abstract Low-dimensional metal halide perovskites have emerged as promising alternatives to the traditional three-dimensional (3D) components, due to their greater structural tunability and environmental stability. Dion-Jacobson (DJ) phase two-dimensional (2D) perovskites, which are formed by incorporating bulky organic diammonium cations into inorganic frameworks that comprises a symmetrically layered array, have recently attracted increasing research interest. The structure-property characteristics of DJ phase perovskites endow them with a unique combination of photovoltaic efficiency and stability, which has led to their impressive employment in perovskite solar cells (PSCs). Here, we review the achievements that have been made to date in the exploitation of DJ phase perovskites in photovoltaic applications. We summarize the various ligand designs, optimization strategies and applications of DJ phase PSCs, and examine the current understanding of the mechanisms underlying their functional behavior. Finally, we discuss the remaining bottlenecks and future outlook for these promising materials, and possible development directions of further commercial processes.

scholarly journals Engineering fluorinated-cation containing inverted perovskite solar cells with an efficiency of >21% and improved stability towards humidity

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Xiao Wang ◽  
Kasparas Rakstys ◽  
Kevin Jack ◽  
Hui Jin ◽  
Jonathan Lai ◽  
...  
Keyword(s):  
Solar Cells ◽  
Perovskite Solar Cells ◽  
Three Dimensional ◽  
Environmental Stability ◽  
Lead Salt ◽  
Two Dimensional ◽  
High Concentration ◽  
Lead Iodide ◽  
Mole Percent ◽  
Improved Stability

AbstractEfficient and stable perovskite solar cells with a simple active layer are desirable for manufacturing. Three-dimensional perovskite solar cells are most efficient but need to have improved environmental stability. Inclusion of larger ammonium salts has led to a trade-off between improved stability and efficiency, which is attributed to the perovskite films containing a two-dimensional component. Here, we show that addition of 0.3 mole percent of a fluorinated lead salt into the three-dimensional methylammonium lead iodide perovskite enables low temperature fabrication of simple inverted solar cells with a maximum power conversion efficiency of 21.1%. The perovskite layer has no detectable two-dimensional component at salt concentrations of up to 5 mole percent. The high concentration of fluorinated material found at the film-air interface provides greater hydrophobicity, increased size and orientation of the surface perovskite crystals, and unencapsulated devices with increased stability to high humidity.

Thermodynamic-informed machine learning for pressure-sensitive plasticity model

2021 ◽  
Author(s):  
WaiChing Sun ◽  
Nikolas Vlassis
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Plastic Flow ◽  
Yield Function ◽  
Supervised Machine Learning ◽  
Internal Variables ◽  
Elasto Plasticity ◽  
Path Dependent ◽  
Speed Function ◽  
Low Dimensional

&lt;p&gt;This talk will present a machine learning framework that builds interpretable macroscopic surrogate elasto-plasticity models inferred from sub-scale direction numerical simulations (DNS) or experiments with limited data. To circumvent the lack of interpretability of the classical black-box neural network, we introduce a higher-order supervised machine learning technique that generates components of elasto-plastic models such as elasticity functional, yield function, hardening mechanisms, and plastic flow. The geometrical interpretation in the principal stress space allows us to use convexity and smoothness to ensure thermodynamic consistency. The speed function from the Hamilton-Jacobi equation is deduced from the DNS data to formulate hardening and non-associative plastic flow rules governed by the evolution of the low-dimensional descriptors. By incorporating a non-cooperative game that determines the necessary data to calibrate material models, the machine learning generated model is continuously tested, calibrated, and improved as new data guided by the adversarial agents are generated. A graph convolutional neural network is used to deduce low-dimensional descriptors that encodes the evolutional of particle topology under path-dependent deformation and are used to replace internal variables. The resultant constitutive laws can be used in a finite element solver or incorporated as a loss function for the physical-informed neural network run physical simulations.&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document