Unveiling teleconnection drivers for heatwave prediction in South Korea using explainable artificial intelligence DOI Creative Commons
Yeonsu Lee, Dongjin Cho, Jungho Im

и другие.

npj Climate and Atmospheric Science, Год журнала: 2024, Номер 7(1)

Опубликована: Авг. 3, 2024

Abstract Increasing heatwave intensity and mortality demand timely accurate prediction. The present study focused on teleconnection, the influence of distant land ocean variability local weather events, to drive long-term predictions. complexity teleconnection poses challenges for physical-based prediction models. In this study, we employed a machine learning model explainable artificial intelligence identify drivers heatwaves in South Korea. Drivers were selected based their statistical significance with annual frequency ( | R > 0.3, p < 0.05). Our analysis revealed that two snow depth (SD) variabilities—a decrease Gobi Desert increase Tianshan Mountains—are most important predictive drivers. These exhibit high correlation summer climate conditions conducive heatwaves. lays groundwork further research into understanding land–atmosphere interactions over these SD regions significant impact patterns

Язык: Английский

Metal-organic frameworks for xenon and krypton separation DOI Creative Commons
Yuting Yang,

Chang‐Zheng Tu,

Licheng Guo

и другие.

Cell Reports Physical Science, Год журнала: 2023, Номер 4(12), С. 101694 - 101694

Опубликована: Ноя. 20, 2023

The separation of xenon and krypton has significance in industrial development, methods have environmental consequences. Compared to the present cryogenic distillation process, by metal-organic frameworks provides an efficient way save energy money. Studies this field increased rapidly recent years. In paper, overview progress adsorption using metal-organic-framework-based adsorbents is provided. We cover structural aspects that affect properties, strategies improve capture separation, evaluation techniques. Additionally, importance computational chemistry study mixtures highlighted. Finally, we elaborate on existing challenges prospects burgeoning field.

Язык: Английский

Процитировано

7

Accelerating Metal–Organic Framework Selection for Type III Porous Liquids by Synergizing Machine Learning and Molecular Simulation DOI

Lisha Sheng,

Yi Wang, Xinzhu Mou

и другие.

ACS Applied Materials & Interfaces, Год журнала: 2023, Номер 15(48), С. 56253 - 56264

Опубликована: Ноя. 21, 2023

MOF-based type III porous liquids, comprising MOFs dissolved in a liquid solvent, have attracted increasing attention carbon capture. However, discovering appropriate to prepare liquids was still limited experiments, wasting time and energy. In this study, we used the density functional theory molecular dynamics simulation methods identify 4530 MOF candidates as core database based on idea of prohibiting pore occupancy by [DBU-PEG][NTf2] ionic liquid. Based high-throughput simulation, random forest machine learning models were first trained predict CO2 sorption CO2/N2 selectivity screen liquids. The feature importance inferred Shapley Additive Explanations (SHAP) interpretation, ranking top 5 descriptors for sorption/selectivity trade-off (TSN) gravimetric surface area (GSA) > porosity metal fraction size distribution (PSD, 3.5–4 Å). RICBEM predicted be one candidate preparing with capacity 20.87 mmol/g 16.75. experimental results showed that RICBEM-based successfully synthesized 2.21 63.2, best capture performance known date. Such screening method would advance cores solvents different applications addressing corresponding factors.

Язык: Английский

Процитировано

7

Topological Data Analysis Combined with High-Throughput Computational Screening of Hydrophobic Metal–Organic Frameworks: Application to the Adsorptive Separation of C3 Components DOI Creative Commons

Yujuan Yang,

Shuya Guo,

Shuhua Li

и другие.

Nanomaterials, Год журнала: 2024, Номер 14(3), С. 298 - 298

Опубликована: Янв. 31, 2024

The shape and topology of pores have significant impacts on the gas storage properties nanoporous materials. Metal–organic frameworks (MOFs) are ideal materials with which to tailor needs specific applications, due such as their tunable structure high surface area. It is, therefore, particularly important develop descriptors that accurately identify topological features MOF pores. In this work, a data analysis method was used descriptor, based pore topology, combined Extreme Gradient Boosting (XGBoost) algorithm predict adsorption performance MOFs for methane/ethane/propane. final results show descriptor can MOFs, introduction also significantly improves accuracy model, resulting in an increase up 17.55% R2 value model decrease 46.1% RMSE, compared commonly models structural descriptor. study contribute deeper understanding relationship between provide useful guidelines strategies design high-performance separation

Язык: Английский

Процитировано

2

Performance Evaluation of Metal–Organic Frameworks in Adsorption Heat Pumps via Multiscale Modeling DOI
Tiangui Liang, Wei Li, Song Li

и другие.

ACS Sustainable Chemistry & Engineering, Год журнала: 2024, Номер 12(7), С. 2825 - 2840

Опубликована: Фев. 5, 2024

The adsorption heat pump (AHP) driven by low-grade thermal energy is a promising technology to reduce building consumption for sustainable energy. Using metal–organic frameworks (MOFs) as adsorbents has attracted widespread attention in AHPs due their large capacity of working fluids, stepwise isotherm that tends possess outstanding equilibrium performance (i.e., coefficient performance, COP). Nevertheless, the dynamic MOFs lacks quick evaluation and screening strategy, especially specific cooling power (SCP) equally important with COP during operation. Herein, multiscale modeling combining molecular simulation mathematical was proposed obtain SCP vast number MOF-based pairs high efficiency. Structure–property relationship obtained from high-throughput computational 1072 indicated relatively low density (<1 kg/m3), pore size (>10 Å), void fraction (∼0.6) benefited improvement (ΔW), leading eventually. From perspective, it also suggested adsorption/desorption fluids majorly occurring temperature ranges 305–325 330–345 K favorable achieve better COP. Furthermore, successful implementation several commonly used machine learning (ML) algorithms paves way accelerating assessment nanoporous materials reasonable computation time. During training ML algorithms, revealed ΔW transport diffusion were dominant descriptors predicting SCP, while MOF played vital role

Язык: Английский

Процитировано

2

Unveiling teleconnection drivers for heatwave prediction in South Korea using explainable artificial intelligence DOI Creative Commons
Yeonsu Lee, Dongjin Cho, Jungho Im

и другие.

npj Climate and Atmospheric Science, Год журнала: 2024, Номер 7(1)

Опубликована: Авг. 3, 2024

Abstract Increasing heatwave intensity and mortality demand timely accurate prediction. The present study focused on teleconnection, the influence of distant land ocean variability local weather events, to drive long-term predictions. complexity teleconnection poses challenges for physical-based prediction models. In this study, we employed a machine learning model explainable artificial intelligence identify drivers heatwaves in South Korea. Drivers were selected based their statistical significance with annual frequency ( | R > 0.3, p < 0.05). Our analysis revealed that two snow depth (SD) variabilities—a decrease Gobi Desert increase Tianshan Mountains—are most important predictive drivers. These exhibit high correlation summer climate conditions conducive heatwaves. lays groundwork further research into understanding land–atmosphere interactions over these SD regions significant impact patterns

Язык: Английский

Процитировано

2