Quan Zhang

Yanfei Xiang, Yuan Gao, Hao Wu et al.

Accurate and efficient global ocean state estimation remains a grand challenge for Earth system science, hindered by the dual bottlenecks of computational scalability and degraded data fidelity in traditional data assimilation (DA) and deep learning (DL) approaches. Here we present an AI-driven Data Assimilation Framework for Ocean (ADAF-Ocean) that directly assimilates multi-source and multi-scale observations, ranging from sparse in-situ measurements to 4 km satellite swaths, without any interpolation or data thinning. Inspired by Neural Processes, ADAF-Ocean learns a continuous mapping from heterogeneous inputs to ocean states, preserving native data fidelity. Through AI-driven super-resolution, it reconstructs 0.25$^\circ$ mesoscale dynamics from coarse 1$^\circ$ fields, which ensures both efficiency and scalability, with just 3.7\% more parameters than the 1$^\circ$ configuration. When coupled with a DL forecasting system, ADAF-Ocean extends global forecast skill by up to 20 days compared to baselines without assimilation. This framework establishes a computationally viable and scientifically rigorous pathway toward real-time, high-resolution Earth system monitoring.

Kaixuan Chen, Wei Luo, Shunyu Liu et al.

In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections. Specifically, our proposed approach, named Powerformer, develops a dedicated section-adaptive attention mechanism, separating itself from the self-attention used in conventional transformers. This mechanism effectively integrates power system states with transmission section information, which facilitates the development of robust state representations. Furthermore, by considering the graph topology of power system and the electrical attributes of bus nodes, we introduce two customized strategies to further enhance the expressiveness: graph neural network propagation and multi-factor attention mechanism. Extensive evaluations are conducted on three power system scenarios, including the IEEE 118-bus system, a realistic 300-bus system in China, and a large-scale European system with 9241 buses, where Powerformer demonstrates its superior performance over several baseline methods.

Yuze Sun, Wentao Luo, Yanfei Xiang et al.

With the growing role of artificial intelligence in climate and weather research, efficient model training and inference are in high demand. Current models like FourCastNet and AI-GOMS depend heavily on GPUs, limiting hardware independence, especially for Chinese domestic hardware and frameworks. To address this issue, we present a framework for migrating large-scale atmospheric and oceanic models from PyTorch to MindSpore and optimizing for Chinese chips, and evaluating their performance against GPUs. The framework focuses on software-hardware adaptation, memory optimization, and parallelism. Furthermore, the model's performance is evaluated across multiple metrics, including training speed, inference speed, model accuracy, and energy efficiency, with comparisons against GPU-based implementations. Experimental results demonstrate that the migration and optimization process preserves the models' original accuracy while significantly reducing system dependencies and improving operational efficiency by leveraging Chinese chips as a viable alternative for scientific computing. This work provides valuable insights and practical guidance for leveraging Chinese domestic chips and frameworks in atmospheric and oceanic AI model development, offering a pathway toward greater technological independence.

Wei Xie, Chen Zhang, Quan Zhang et al.

This paper address a new problem in RFID authentication research for the first time. That is, existing RFID authentication schemes generally assume that the backend server is absolutely secure, however, this assumption is rarely tenable in practical conditions. It disables existing RFID authentication protocols from being safely applied to a reallife scenario in which the backend server is actually vulnerable, compromised or even malicious itself. We propose an RFID authentication scheme against an unsecure backend server. It is based on hash chain, searching over encrypted data, and coprivacy, defending against the privacy revealing to the backend server. The proposed scheme is scalable, resistant to desynchronization attacks, and provides mutual authentication in only three frontend communication steps. Moreover, it is the first scheme meeting the special security and privacy requirement for a cloud-based RFID authentication scenario in which the backend server is untrustworthy to readers held by cloud clients.

Wei Xie, Chen Zhang, Quan Zhang et al.

Along with the development of internet of things and pervasive computing, researchers are increasingly focusing on server-less RFID authentication and searching protocols, which utilize mobile RFID readers. However, revealing privacy of mobile reader holders is a widely neglected problem in current research. This paper concentrates on preserving privacy of mobile reader holders in server-less RFID authentication and searching protocols. We propose a detailed requirement as a principle for future protocol designs, and a scheme to enhance most current protocols. We apply our scheme to two classical protocols. The comparisons between the original and our enhanced protocols show that our scheme is secure and effective.