Liu Zhe

Solarizing the world

[Liu Zhe @LiuZhe_MIT]

We developed a two-step ML + Bayesian optimization framework to rapidly optimize eco-friendly, scalable #PerovskiteSolarCell fabrication in ambient air — no anti-solvent, low-toxicity TEP solvent, and 24.26% PCE achieved! Newly online in JEC @jenergychem: https://t.co/zlgedBqr4P

[Liu Zhe @LiuZhe_MIT]

Introducing you to the Co-PAS (Co-Plot for Additive Screening), an ML-driven framework designed to accelerate additive screening for perovskite solar cells. https://t.co/hRYHyM20ZW; https://t.co/JaOZcaQtZx .

[Liu Zhe @LiuZhe_MIT]

Hello, world! Are you looking for an AI copilot while searching the vast chemical space of organic additives for perovskite solar cells? Preprint at: https://t.co/tnBfzIFMvF; Open-source Code: https://t.co/RXGKhmFney

[Digital Discovery @digital_rsc]

Buonassisi et al. use transfer learning to overcome data scarcity in high-throughput, automated experimental work in thickness characterisation of optoelectronic thin films. Read more in today's featured article: https://t.co/O5vIxskKBt #openaccess

[Liu Zhe @LiuZhe_MIT]

Thanks to Curtis @cpbCleanEnergy & Tonio @toniobuonassisi, ASTAR, SERIS & SMART team.

[Liu Zhe @LiuZhe_MIT]

Finally, we got this thicknessML published in Digital Discovery @digital_rsc. We used transfer learning for thin film thickness analysis. Please see an early preview: https://t.co/vrlNqFW3ga. Great collaboration with many awesome researchers.

[Liu Zhe @LiuZhe_MIT]

@jpcorreabaena @BaenaLab @GTMSE5 @ACSEnergyLett @CarloPerini3 We are probably going to have papers published in the same issue. Looking forward to it.

[Liu Zhe @LiuZhe_MIT]

@Coolphoton @jpcorreabaena @BaenaLab @GTMSE5 @ACSEnergyLett @CarloPerini3 We probably have papers in the same issue.

[Liu Zhe @LiuZhe_MIT]

On ML side, inspired by a talk from @prashungorai on avoiding data bias, we supplemented the previous research-intuition-driven dataset with five Latin-Hypercube-sampled ammonium salts. The data diversity gets increased, and the model prediction becomes more robust.

[Liu Zhe @LiuZhe_MIT]

Following up our ML-assisted previous screening research led by @SunShijing @noortitan @toniobuonassisi, a new study found an ML-suggested molecule (2-phenylpropane-1- aminium iodide) experimentally achieves PCEs of 22.36% for FAMACs-based and 24.47% FAMA-based solar cells.

[ACSEnergyLett @ACSEnergyLett]

Machine-Learning-Assisted Screening of Interface Passivation Materials for Perovskite Solar Cells https://t.co/QlUv6YN8wo

[The Solar Move @TheSolarMove]

Initializing film homogeneity to retard phase segregation for stable perovskite solar cells - Science https://t.co/S09qMGDVSa

[Liu Zhe @LiuZhe_MIT]

@Sergei_Imaging @toniobuonassisi @SterlingBaird1 @JuliaHsu_UTD @UT_Dallas I’m still trying to formalise the idea. But, my intuition is to incorporate device physics into optimisation.

[Liu Zhe @LiuZhe_MIT]

Another demo of a quick and informed optimization with BO and SHAP analysis. This time we tackle the challenge of making flexible perovskite solar cells. Here is a link: https://t.co/jsoCSIRc1E. A great collaboration with Prof. @JuliaHsu_UTD 's team @UT_Dallas.

[Liu Zhe @LiuZhe_MIT]

@Sergei_Imaging @toniobuonassisi @SterlingBaird1 @JuliaHsu_UTD @UT_Dallas I've read these papers. I guess the idea is to use physical laws to accelerate BO, correct? I will be cool to try these concepts in solar cells.

[Liu Zhe @LiuZhe_MIT]

@SterlingBaird1 @JuliaHsu_UTD @UT_Dallas Cool idea! Lengthscale values are fitted independently for each input dimension. I will check how they are ranked. But, by definition, it should show the covariance on X values at different locations. Not the impact on the output y though. It would be a different perspective.

[Liu Zhe @LiuZhe_MIT]

See the figure

[Liu Zhe @LiuZhe_MIT]

Speaking of human-ML interaction, we expanded the search boundaries after the first round for the “PC length” variable. (Semi-)surprised to find out the PC tool have a limitation. So, the take-away: check your BO surrogate at every iteration with contour plot and SHAP analysis.

[Weijie Xu @JeremyWeijie]

I am happy to share with you our first trial using BO and SHAP in optimizing Photonically Cured flexible perovskite solar cells. Big shout-out to my collaborator
@LiuZhe_MIT and my advisor @JuliaHsu_UTD This demo shows a Good Human-Machine Partnership.
https://t.co/ZjQFoYdmYL

[Liu Zhe @LiuZhe_MIT]

@John_W_Ward @LivUni @livuniphyssci Congrats.

[Liu Zhe @LiuZhe_MIT]

@Yang1Bai @nanotransport @ASTARsg @Sargent_Group @A3MD_UofT Safe travels. Stay in touch.

[Liu Zhe @LiuZhe_MIT]

@WeiHe_1 @KCLEngineering @warwickuni Congratz, He Wei