Tsinghua–Berkeley Shenzhen Institute

Pectin–Protein Complexes: A Design‐Oriented Platform for Tailoring Food Texture Modification

ABSTRACT Pectin–protein complexes have emerged as promising functional ingredients in texture‐modified foods (TMF) due to their multifunctional roles in gelation, emulsification, and water retention. These properties enable the design of customized textures for applications such...

Toeplitz-structured deep unfolding network for TomoSAR 3-D reconstruction

Urban area 3-D imaging is a key application of synthetic aperture radar (SAR). Classical compressive sensing-based tomographic SAR methods rely on iterative optimization, which is computationally expensive and sensitive to hyperparameter tuning, limiting its scalability for large...

Interpretable GraphDeep Learning Reveals EcologicalRisks and Attribution Patterns of Polycyclic Aromatic Hydrocarbonsin Urban Greenspace Soils across China

Abstract Characterizing the complex environmental and socioeconomic associations underlying risks related to polycyclic aromatic hydrocarbons (PAHs) in urban greenspace soils is important for ecosystem health, yet conventional tabular models do not explicitly represent these cros...

Hierarchical Enzyme Function Prediction Based on Structural Confidence and Active-Site-Aware Attention

Accurate enzyme function prediction is important for protein functional annotation, drug discovery, metabolic-pathway analysis, and synthetic biology. Although recent structure-based methods have improved Enzyme Commission (EC) number prediction, they still have several limitatio...

Research on the Online Diagnosis Method for Heating Types of Composite Insulator

ABSTRACT In response to the current challenge of accurately determining the specific heating status of composite insulators with localised temperature rise using infrared detection technology, this paper proposes a novel diagnostic method. This method involves applying a disturba...

Pan-retinal pathology detection in oct scans integrating natural language synthesis with diagnostic annotation

Abstract While OCT is pivotal for macular disease diagnosis, its adoption in primary care is limited by AI systems that cannot simultaneously analyze multi-sectional scans across the full spectrum of maculopathies or generate diagnostically integrated reports. Here we present iOC...

Impacts of Future Oil Palm Expansion on Carbon and Hydrological Fluxes Across the Tropics

Abstract Future oil palm expansion could substantially alter tropical carbon and water cycles, but its regional impacts remain unclear. Using CLM5‐palm, we simulate large‐scale oil palm expansion from 2023 to 2100 in Southeast Asia, Africa and the Amazon. Expansion increases tota...

Unraveling the Ionic Adsorption and Migration Mechanism of Inverse Opal Capacitive Deionization Electrode

ABSTRACT Developing advanced capacitive deionization electrodes for desalination requires the concurrent enhancement of thermodynamic and kinetic properties. Despite extensive research on improving thermodynamic features represented by adsorption capacity, the investigation on th...

A Self‐Adaptive Multipole Receiver for Interoperable Wireless Electric Vehicle Charging with Enhanced Misalignment Tolerance

ABSTRACT In wireless power transfer (WPT) for electric vehicles (EVs), interoperability issues often arise when the transmitter and receivers are of different types such as Q and DD coils. Misalignment between coils is inevitable in practical applications, leading to a sharp decl...