Longfeng Nie

Longfeng Nie

Auto-generated profile, based on publicly available information

Longfeng Nie

Pengcheng Laboratory, Shenzhen, P. R. China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2024 in Physics of Fluids
Verified
Journal Article
Open access
PDF file
MDMengge Du
Mengge Du
YCYuntian Chen
Yuntian Chen
ZWZhongzheng Wang
Zhongzheng Wang
LNLongfeng Nie
Longfeng Nie
DZDongxiao Zhang
Dongxiao Zhang
Equation discovery aims to directly extract physical laws from data and has emerged as a pivotal research domain in nonlinear systems. Previous methods based on symbolic mathematics have achieved substantial advancements, but often require handcrafted representation rules and complex optimization algorithms. In this paper, we introduce a novel framework that utilizes natural language-based prompts to guide large language models (LLMs) in automatically extracting governing equations from data. Specifically, we first utilize the generation capability of LLMs to generate diverse candidate equations in string form and then evaluate the generated equations based on observations. The best equations are preserved and further refined iteratively using the reasoning capacity of LLMs. We propose two alternately iterated strategies to collaboratively optimize the generated equations. The first strategy uses LLMs as a black-box optimizer to achieve equation self-improvement based on historical samples and their performance. The second strategy instructs LLMs to perform evolutionary operations for a global search. Experiments are conducted on various nonlinear systems described by partial differential equations, including the Burgers equation, the Chafee–Infante equation, and the Navier–Stokes equation. The results demonstrate that our framework can discover correct equations that reveal the underlying physical laws. Further comparisons with state-of-the-art models on extensive ordinary differential equations showcase that the equations discovered by our framework possess physical meaning and better generalization capability on unseen data.

1 May 2024 in Physics of Fluids
Verified
Journal Article
Closed access
PDF file
MDMengge Du
Mengge Du
YCYuntian Chen
Yuntian Chen
LNLongfeng Nie
Longfeng Nie
SLSiyu Lou
Siyu Lou
DZDongxiao Zhang
Dongxiao Zhang
Unveiling the underlying governing equations of nonlinear dynamic systems remains a significant challenge. Insufficient prior knowledge hinders the determination of an accurate candidate library, while noisy observations lead to imprecise evaluations, which in turn result in redundant function terms or erroneous equations. This study proposes a framework to robustly uncover open-form partial differential equations (PDEs) from limited and noisy data. The framework operates through two alternating update processes: discovering and embedding. The discovering phase employs symbolic representation and a novel reinforcement learning (RL)-guided hybrid PDE generator to efficiently produce diverse open-form PDEs with tree structures. A neural network-based predictive model fits the system response and serves as the reward evaluator for the generated PDEs. PDEs with higher rewards are utilized to iteratively optimize the generator via the RL strategy and the best-performing PDE is selected by a parameter-free stability metric. The embedding phase integrates the initially identified PDE from the discovering process as a physical constraint into the predictive model for robust training. The traversal of PDE trees automates the construction of the computational graph and the embedding process without human intervention. Numerical experiments demonstrate our framework's capability to uncover governing equations from nonlinear dynamic systems with limited and highly noisy data and outperform other physics-informed neural network-based discovery methods. This work opens new potential for exploring real-world systems with limited understanding.

5 January 2024 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
LNLongfeng Nie
Longfeng Nie
YCYuntian Chen
Yuntian Chen
DZDongxiao Zhang
Dongxiao Zhang
XLXinyue Liu
Xinyue Liu
WYWentian Yuan
Wentian Yuan

19 December 2024 in Applied Energy
Verified
Journal Article
Closed access
LXLei Xu
Lei Xu
YCYulong Chen
Yulong Chen
YCYuntian Chen
Yuntian Chen
LNLongfeng Nie
Longfeng Nie
XWXuetao Wei
Xuetao Wei
DZDongxiao Zhang
Dongxiao Zhang

16 February 2024 in Remote Sensing of Environment
Verified
Journal Article
Closed access
LNLongfeng Nie
Longfeng Nie
YCYuntian Chen
Yuntian Chen
MDMengge Du
Mengge Du
CSChangqi Sun
Changqi Sun
DZDongxiao Zhang
Dongxiao Zhang

5 March 2025 in Scientific Data
Verified
Journal Article
Open access
PDF file
LNLongfeng Nie
Longfeng Nie
YCYuntian Chen
Yuntian Chen
DZDongxiao Zhang
Dongxiao Zhang
The cloud property database and different type cloud occurrence probability datasets are helpful for meteorological research and application, as well as climate comprehension. Building on the foundation of CldNet with all-day cloud type recognition capability, CldNet Version 2.0 (CldNetV2) is proposed. This enhanced version leverages transfer learning and model parameter sharing techniques to not only classify cloud types but also predict additional cloud properties. Datasets with multiple cloud properties obtained by CldNetV2 make up for the lack of current Himawari cloud product at nighttime. Meanwhile, the dataset of different cloud type occurrence probabilities is statistically obtained on three time scales including annual, seasonal, and monthly, and more importantly, the dataset distinguishes between all day, daytime, and nighttime. In addition, the reliability of our cloud product is independently validated by the cloud properties from CALIPSO trajectories, ERA5 cloud cover fraction and the visualization of cloud property distribution and typhoon eye track during typhoons. Further more, the all-day cloud property and occurrence probability dataset for meteorological environment assessment has been publicly released.