Classification and detection of dental images using meta-learning

Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input.Instead of just memorizing a task,this is accomplished through teaching a model how to learn.Algorithms for meta-learning are typically trained on a collection of training problems,each of which has a limited number of labelled instances.Multiple Xray classification tasks,including the detection of pneumonia,coronavirus disease 2019,and other disorders,have demonstrated the effectiveness of meta-learning.Meta-learning has the benefit of allowing models to be trained on dental X-ray datasets that are too few for more conventional machine learning methods.Due to the high cost and lengthy collection process associated with dental imaging datasets,this is significant for dental X-ray classification jobs.The ability to train models that are more resistant to fresh input is another benefit of meta-learning.

Meta-Auto-Decoder:a Meta-Learning-Based Reduced Order Model for Solving Parametric Partial Differential Equations

Many important problems in science and engineering require solving the so-called parametric partial differential equations(PDEs),i.e.,PDEs with different physical parameters,boundary conditions,shapes of computational domains,etc.Typical reduced order modeling techniques accelerate the solution of the parametric PDEs by projecting them onto a linear trial manifold constructed in the ofline stage.These methods often need a predefined mesh as well as a series of precomputed solution snapshots,and may struggle to balance between the efficiency and accuracy due to the limitation of the linear ansatz.Utilizing the nonlinear representation of neural networks(NNs),we propose the Meta-Auto-Decoder(MAD)to construct a nonlinear trial manifold,whose best possible performance is measured theoretically by the decoder width.Based on the meta-learning concept,the trial manifold can be learned in a mesh-free and unsupervised way during the pre-training stage.Fast adaptation to new(possibly heterogeneous)PDE parameters is enabled by searching on this trial manifold,and optionally fine-tuning the trial manifold at the same time.Extensive numerical experiments show that the MAD method exhibits a faster convergence speed without losing the accuracy than other deep learning-based methods.

Application of meta-learning in cyberspace security:a survey

In recent years,machine learning has made great progress in intrusion detection,network protection,anomaly detection,and other issues in cyberspace.However,these traditional machine learning algorithms usually require a lot of data to learn and have a low recognition rate for unknown attacks.Among them,“one-shot learning”,“few-shot learning”,and“zero-shot learning”are challenges that cannot be ignored for traditional machine learning.The more intractable problem in cyberspace security is the changeable attack mode.When a new attack mode appears,there are few or even zero samples that can be learned.Meta-learning comes from imitating human problem-solving methods as humans can quickly learn unknown things based on their existing knowledge when learning.Its purpose is to quickly obtain a model with high accuracy and strong generalization through less data training.This article first divides the meta-learning model into five research directions based on different principles of use.They are model-based,metric-based,optimization-based,online-learning-based,or stacked ensemble-based.Then,the current problems in the field of cyberspace security are categorized into three branches:cyber security,information security,and artificial intelligence security according to different perspectives.Then,the application research results of various meta-learning models on these three branches are reviewed.At the same time,based on the characteristics of strong generalization,evolution,and scalability of meta-learning,we contrast and summarize its advantages in solving problems.Finally,the prospect of future deep application of meta-learning in the field of cyberspace security is summarized.

Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

Crop Disease Recognition Based on Improved Model-Agnostic Meta-Learning

Currently,one of the most severe problems in the agricultural industry is the effect of diseases and pests on global crop production and economic development.Therefore,further research in the field of crop disease and pest detection is necessary to address the mentioned problem.Aiming to identify the diseased crops and insect pests timely and accurately and perform appropriate prevention measures to reduce the associated losses,this article proposes a Model-Agnostic Meta-Learning(MAML)attention model based on the meta-learning paradigm.The proposed model combines meta-learning with basic learning and adopts an Efficient Channel Attention(ECA)mod-ule.The module follows the local cross-channel interactive strategy of non-dimensional reduction to strengthen the weight parameters corresponding to certain disease characteristics.The proposed meta-learning-based algorithm has the advantage of strong generalization capability and,by integrating the ECA module in the original model,can achieve more efficient detection in new tasks.The proposed model is verified by experiments,and the experimental results show that compared with the original MAML model,the proposed improved MAML-Attention model has a better performance by 1.8–9.31 percentage points in different classification tasks;the maximum accuracy is increased by 1.15–8.2 percentage points.The experimental results verify the strong generalization ability and good robustness of the proposed MAML-Attention model.Compared to the other few-shot methods,the proposed MAML-Attention performs better.

Spatial analysis of the osteoarthritis microenvironment: techniques, insights, and applications

Osteoarthritis(OA)is a debilitating degenerative disease affecting multiple joint tissues,including cartilage,bone,synovium,and adipose tissues.OA presents diverse clinical phenotypes and distinct molecular endotypes,including inflammatory,metabolic,mechanical,genetic,and synovial variants.Consequently,innovative technologies are needed to support the development of effective diagnostic and precision therapeutic approaches.Traditional analysis of bulk OA tissue extracts has limitations due to technical constraints,causing challenges in the differentiation between various physiological and pathological phenotypes in joint tissues.This issue has led to standardization difficulties and hindered the success of clinical trials.Gaining insights into the spatial variations of the cellular and molecular structures in OA tissues,encompassing DNA,RNA,metabolites,and proteins,as well as their chemical properties,elemental composition,and mechanical attributes,can contribute to a more comprehensive understanding of the disease subtypes.Spatially resolved biology enables biologists to investigate cells within the context of their tissue microenvironment,providing a more holistic view of cellular function.Recent advances in innovative spatial biology techniques now allow intact tissue sections to be examined using various-omics lenses,such as genomics,transcriptomics,proteomics,and metabolomics,with spatial data.This fusion of approaches provides researchers with critical insights into the molecular composition and functions of the cells and tissues at precise spatial coordinates.Furthermore,advanced imaging techniques,including high-resolution microscopy,hyperspectral imaging,and mass spectrometry imaging,enable the visualization and analysis of the spatial distribution of biomolecules,cells,and tissues.Linking these molecular imaging outputs to conventional tissue histology can facilitate a more comprehensive characterization of disease phenotypes.This review summarizes the recent advancements in the molecular imaging modalities and methodologies for in-depth spatial analysis.It explores their applications,challenges,and potential opportunities in the field of OA.Additionally,this review provides a perspective on the potential research directions for these contemporary approaches that can meet the requirements of clinical diagnoses and the establishment of therapeutic targets for OA.

FPGA-based position reconstruction method for neutron beam flux spatial distribution measurement in BNCT

A new measurement method for the spatial distribution of neutron beam flux in boron neutron capture therapy(BNCT)is being developed based on the two-dimensional Micromegas detector.To address the issue of long processing times in traditional offline position reconstruction methods,this paper proposes a field programmable gate array based online position reconstruction method utilizing the micro-time projection chamber principle.This method encapsulates key technical aspects:a self-adaptive serial link technique built upon the dynamical adjustment of the delay chain length,fast sorting,a coordinate-matching technique based on the mapping between signal timestamps and random access memory(RAM)addresses,and a precise start point-merging technique utilizing a circular combined RAM.The performance test of the selfadaptive serial link shows that the bit error rate of the link is better than 10-12 at a confidence level of 99%,ensuring reliable data transmission.The experiment utilizing the readout electronics and Micromegas detector shows a spatial resolution of approximately 1.4 mm,surpassing the current method’s resolution level of 5 mm.The beam experiment confirms that the readout electronics system can obtain the flux spatial distribution of neutron beams online,thus validating the feasibility of the position reconstruction method.The online position reconstruction method avoids traditional methods,such as bubble sorting and traversal searching,simplifies the design of the logic firmware,and reduces the time complexity from O(n2)to O(n).This study contributes to the advancement in measuring neutron beam flux for BNCT.

Estimation-free spatial-domain image reconstruction of structured illumination microscopy

Structured illumination microscopy(SIM)achieves super-resolution(SR)by modulating the high-frequency information of the sample into the passband of the optical system and subsequent image reconstruction.The traditional Wiener-filtering-based reconstruction algorithm operates in the Fourier domain,it requires prior knowledge of the sinusoidal illumination patterns which makes the time-consuming procedure of parameter estimation to raw datasets necessary,besides,the parameter estimation is sensitive to noise or aberration-induced pattern distortion which leads to reconstruction artifacts.Here,we propose a spatial-domain image reconstruction method that does not require parameter estimation but calculates patterns from raw datasets,and a reconstructed image can be obtained just by calculating the spatial covariance of differential calculated patterns and differential filtered datasets(the notch filtering operation is performed to the raw datasets for attenuating and compensating the optical transfer function(OTF)).Experiments on reconstructing raw datasets including nonbiological,biological,and simulated samples demonstrate that our method has SR capability,high reconstruction speed,and high robustness to aberration and noise.

Design of Protograph LDPC-Coded MIMO-VLC Systems with Generalized Spatial Modulation

This paper investigates the bit-interleaved coded generalized spatial modulation(BICGSM) with iterative decoding(BICGSM-ID) for multiple-input multiple-output(MIMO) visible light communications(VLC). In the BICGSM-ID scheme, the information bits conveyed by the signal-domain(SiD) symbols and the spatial-domain(SpD) light emitting diode(LED)-index patterns are coded by a protograph low-density parity-check(P-LDPC) code. Specifically, we propose a signal-domain symbol expanding and re-allocating(SSER) method for constructing a type of novel generalized spatial modulation(GSM) constellations, referred to as SSERGSM constellations, so as to boost the performance of the BICGSM-ID MIMO-VLC systems.Moreover, by applying a modified PEXIT(MPEXIT) algorithm, we further design a family of rate-compatible P-LDPC codes, referred to as enhanced accumulate-repeat-accumulate(EARA) codes,which possess both excellent decoding thresholds and linear-minimum-distance-growth property. Both analysis and simulation results illustrate that the proposed SSERGSM constellations and P-LDPC codes can remarkably improve the convergence and decoding performance of MIMO-VLC systems. Therefore, the proposed P-LDPC-coded SSERGSM-mapped BICGSMID configuration is envisioned as a promising transmission solution to satisfy the high-throughput requirement of MIMO-VLC applications.

A Meta-Learning Approach for Aircraft Trajectory Prediction

The aviation industry has seen significant advancements in safety procedures over the past few decades, resulting in a steady decline in aviation deaths worldwide. However, the safety standards in General Aviation (GA) are still lower compared to those in commercial aviation. With the anticipated growth in air travel, there is an imminent need to improve operational safety in GA. One way to improve aircraft and operational safety is through trajectory prediction. Trajectory prediction plays a key role in optimizing air traffic control and improving overall flight safety. This paper proposes a meta-learning approach to predict short- to mid-term trajectories of aircraft using historical real flight data collected from multiple GA aircraft. The proposed solution brings together multiple models to improve prediction accuracy. In this paper, we are combining two models, Random Forest Regression (RFR) and Long Short-term Memory (LSTM), using k-Nearest Neighbors (k-NN), to output the final prediction based on the combined output of the individual models. This approach gives our model an edge over single-model predictions. We present the results of our meta-learner and evaluate its performance against individual models using the Mean Absolute Error (MAE), Absolute Altitude Error (AAE), and Root Mean Squared Error (RMSE) evaluation metrics. The proposed methodology for aircraft trajectory forecasting is discussed in detail, accompanied by a literature review and an overview of the data preprocessing techniques used. The results demonstrate that the proposed meta-learner outperforms individual models in terms of accuracy, providing a more robust and proactive approach to improve operational safety in GA.

Evaluation of COVID-19 Cases and Vaccinations in the State of Georgia, United States: A Spatial Perspective

This study evaluates the distribution of COVID-19 cases and mass vaccination campaigns from January 2020 to April 2023. There are over 235,000 COVID-19 cases and over 733,000 vaccinations across the 159 counties in the state of Georgia. Data on COVID-19 was acquired from usafact.org while the vaccination records were obtained from COVID-19 vaccination tracker. The spatial patterns across the counties were analyzed using spatial statistical techniques which include both global and local spatial autocorrelation. The study further evaluates the effect of vaccination and selected socio-economic predictors on COVID-19 cases across the study area. The result of hotspot analysis reveals that the epicenters of COVID-19 are distributed across Cobb, Fulton, Gwinnett, and DeKalb counties. It was also affirmed that the vaccination records followed the same pattern as COVID-19 cases’ epicenters. The result of the spatial error model performed well and accounted for a considerable percentage of the regression with an adjusted R squared of 0.68, Akaike Information Criterion (AIC) 387.682 and Breusch-Pagan of 9.8091. ESDA was employed to select the main explanatory variables. The selected variables include vaccination, population density, percentage of people that do not have health insurance, black race, Hispanic and these variables accounted for 68% of the number of COVID-19 cases in the state of Georgia during the study period. The study concludes that both COVID-19 cases and vaccinated individuals have spatial peculiarities across counties in Georgia state. Lastly, socio-economic variables and vaccination are very important to reduce the vulnerability of individuals to COVID-19 disease.

Spatial evolution and spatial production of traditional villages from "backward poverty villages" to "ecologically well-off villages": Experiences from the hinterland of national nature reserves in China

With the rapid urbanization process,the space of traditional villages in China is undergoing significant changes.Studying the spatial evolution of traditional villages is significant in promoting rural spatial transformation and realizing rural revitalization and sustainable rural development.Based on the traceability analysis of spatial production theory,this paper constructed an analytical framework for the spatial production evolution of traditional villages,analyzed the spatial evolution process and characteristics of traditional villages by using buffer analysis,spatial syntax,and other research methods,and revealed the characteristics of the spatial production evolution of traditional villages and the driving mechanism.The results show that:(1)The village spatial formation and development follow the village life cycle theory and usually develop from embryonic villages to diversified and integrated villages;(2)The evolution of village spatial production is characterized by the diversity of material space,the sublimation of daily life space,and the integration of social system space and generalization of emotional space;(3)The evolution of village spatial production from backward and poor village to ecologically well-off village is influenced by a combination of factors;(4)The village has formed a spatial structure of"people-land-scape-culture-industry",realized comprehensive reconstruction and spatial reproduction.The study results reflect the spatial evolution characteristics of traditional villages in mountainous areas in a more comprehensive way,which helps to promote the protection and development of traditional villages in mountainous areas and,to a certain extent,provides a reference for the development of rural revitalization.

Spatial transcriptomics:recent developments and insights in respiratory research

The respiratory system's complex cellular heterogeneity presents unique challenges to researchers in this field.Although bulk RNA sequencing and single-cell RNA sequencing(scRNA-seq)have provided insights into cell types and heterogeneity in the respiratory system,the relevant specific spatial localization and cellular interactions have not been clearly elucidated.Spatial transcriptomics(ST)has filled this gap and has been widely used in respiratory studies.This review focuses on the latest iterative technology of ST in recent years,summarizing how ST can be applied to the physiological and pathological processes of the respiratory system,with emphasis on the lungs.Finally,the current challenges and potential development directions are proposed,including high-throughput full-length transcriptome,integration of multi-omics,temporal and spatial omics,bioinformatics analysis,etc.These viewpoints are expected to advance the study of systematic mechanisms,including respiratory studies.

A Novel Deep Model with Meta-Learning for Rolling Bearing Few-Shot Fault Diagnosis

Machine learning,especially deep learning,has been highly successful in data-intensive applications;however,the performance of these models will drop significantly when the amount of the training data amount does not meet the requirement.This leads to the so-called few-shot learning(FSL)problem,which requires the model rapidly generalize to new tasks that containing only a few labeled samples.In this paper,we proposed a new deep model,called deep convolutional meta-learning networks,to address the low performance of generalization under limited data for bearing fault diagnosis.The essential of our approach is to learn a base model from the multiple learning tasks using a support dataset and finetune the learnt parameters using few-shot tasks before it can adapt to the new learning task based on limited training data.The proposed method was compared to several FSL methods,including methods with and without pre-training the embedding mapping,and methods with finetuning the classifier or the whole model by utilizing the few-shot data from the target domain.The comparisons are carried out on 1-shot and 10-shot tasks using the Case Western Reserve University bearing dataset and a cylindrical roller bearing dataset.The experimental result illustrates that our method has good performance on the bearing fault diagnosis across various few-shot conditions.In addition,we found that the pretraining process does not always improve the prediction accuracy.

Assessing the Spatial Equality of COVID Testing Sites Maintaining Zero COVID Policy

Rapid and timely testing is essential to minimize the COVID-19 spread. Decision makers and policy planners need to determine the equal distribution and accessibility of testing sites. This study mainly examines the spatial equality of COVID-19 testing sites that maintain a zero COVID policy in Guangzhou City. The study has identified the spatial disparities of COVID testing sites, characteristics of testing locations, and accessibility. The study has obtained information on COVID testing sites in Guangzhou City and population data. Point pattern analyses, Euclidian distance and allocation, and network analyses are the main methods used to achieve the research objectives, and 1183 total COVID testing sites can be recognized in Guangzhou City. Results revealed that spatial disparities could be noticed over the study area. Testing locations of Guangzhou City are highly clustered. The most significant testing sites are located in Haizhu District, which has the third largest population. The highest population density can be identified in Yuexiu District. However, only 94 testing sites are located there. According to all the results, higher disparities can be identified, and a lack of testing sites is located in the north part of the study area. Some people in the northern part have to travel more than 10 km to reach a testing site. Finally, this paper suggests increasing the number of testing sites in the north and south parts of the study area and keeping the same distribution, considering the area, total population, and population density. This kind of research will be helpful to decision-makers in making proper decisions to maintain a zero COVID policy.

MetaPINNs:Predicting soliton and rogue wave of nonlinear PDEs via the improved physics-informed neural networks based on meta-learned optimization

Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep learning-based methods to the forefront of research on numerical methods for partial differential equations.Among them,physics-informed neural networks(PINNs)are a new class of deep learning methods that show great potential in solving PDEs and predicting complex physical phenomena.In the field of nonlinear science,solitary waves and rogue waves have been important research topics.In this paper,we propose an improved PINN that enhances the physical constraints of the neural network model by adding gradient information constraints.In addition,we employ meta-learning optimization to speed up the training process.We apply the improved PINNs to the numerical simulation and prediction of solitary and rogue waves.We evaluate the accuracy of the prediction results by error analysis.The experimental results show that the improved PINNs can make more accurate predictions in less time than that of the original PINNs.

Dynamics of Advantageous Mutant Spread in Spatial Death-Birth and Birth-Death Moran Models

The spread of an advantageous mutation through a population is of fundamental interest in population genetics. While the classical Moran model is formulated for a well-mixed population, it has long been recognized that in real-world applications, the population usually has an explicit spatial structure which can significantly influence the dynamics. In the context of cancer initiation in epithelial tissue, several recent works have analyzed the dynamics of advantageous mutant spread on integer lattices, using the biased voter model from particle systems theory. In this spatial version of the Moran model, individuals first reproduce according to their fitness and then replace a neighboring individual. From a biological standpoint, the opposite dynamics, where individuals first die and are then replaced by a neighboring individual according to its fitness, are equally relevant. Here, we investigate this death-birth analogue of the biased voter model. We construct the process mathematically, derive the associated dual process, establish bounds on the survival probability of a single mutant, and prove that the process has an asymptotic shape. We also briefly discuss alternative birth-death and death-birth dynamics, depending on how the mutant fitness advantage affects the dynamics. We show that birth-death and death-birth formulations of the biased voter model are equivalent when fitness affects the former event of each update of the model, whereas the birth-death model is fundamentally different from the death-birth model when fitness affects the latter event.

Analysis of spatial distribution characteristics and driving factors of ethnicminority villages in China using geospatial technology and statistical models

This study aims to reveal the spatial structural characteristics of 1,652 Ethnic-Minority Villages(EMV)in China and to analyze the mechanisms driving their spatial heterogeneity.EMV are a special type of settlement space that preserve a large number of historical traces of the ethnic culture of ancient China.They are important carriers of China’s excellent traditional culture and are key to the implementation of rural revitalization strategies.In this study,1652 EMV in China were selected as the research subjects.The Nearest Neighbor Index,kernel density,and spatial autocorrelation index were employed to reveal the spatial structural characteristics of minority villages.Neural network models,spatial lag models,and geographical detectors were used to analyze the formation mechanism of spatial heterogeneity in EMV.The results indicate that:(1)EMV exhibit significant spatial differentiation characterized by“single-core with multiple surrounding sub-centers,”“polarization between east and west,”“decreasing quantity from southwest to east coast to northeast to northwest,”and“large dispersion with small agglomeration.”(2)EMV are mainly distributed in areas rich in intangible cultural heritage,with high vegetation coverage and low altitude,far from central cities,and having limited arable land and an underdeveloped economy and transportation,particularly in shaded or riverbank areas.(3)Distance from the nearest river(X3),distance from central cities(X8),national intangible cultural heritage(X9),and NDVI(X10)were the main driving factors affecting the spatial distribution of EMV,whereas elevation(X1)and GDP(X5)had the weakest influence.As EMV are a relatively unique territorial spatial unit,the identification of their spatial heterogeneity characteristics not only deepens the research content of settlement geography,but also involves the assessment,protection,and development of Minority Villages,which is of great significance for the inheritance and utilization of excellent ethnic cultures in the era.

Enhancing transboundary natural tourism resources governance:unveiling the spatial pattern and its influencing factors

Tourism resources that span provincial boundaries in China play a pivotal role in regional development,yet effective governance poses persistent challenges.This study addresses this issue by constructing a comprehensive database of transboundary natural tourism resources(TNTR)through amalgamation of diverse data sources.Utilizing the Getis-Ord Gi^(*),kernel density estimation,and geographical detectors,we scrutinize the spatial patterns of TNTR,focusing on both named and unnamed entities,while exploring the influencing factors.Our findings reveal 7883 identified TNTR in China,with mountain tourism resources emerging as the predominant type.Among provinces,Hunan boasts the highest count,while Shanghai exhibits the lowest.Southern China demonstrates a pronounced clustering trend in TNTR distribution,with the spatial arrangement of biological landscapes appearing more random compared to geological and water landscapes.Western China,characterized by intricate terrain,exhibits fewer TNTR,concurrently unveiling a significant presence of unnamed natural tourism resources.Crucially,administrative segmentation influences TNTR development,generating disparities in regional goals,developmental stages and intensities,and management approaches.In response to these variations,we advocate for strengthening the naming of the unnamed transboundary tourism resources,constructing a geographic database of TNTR for government and establishing a collaborative management mechanism based on TNTR database.Our research contributes to elucidating the intricate landscape of TNTR,offering insights for tailored governance strategies in the realm of cross-provincial tourism resource management.

Ultrafast dynamics of femtosecond laser-induced high spatial frequency periodic structures on silicon surfaces

Femtosecond laser-induced periodic surface structures(LIPSS)have been extensively studied over the past few decades.In particular,the period and groove width of high-spatial-frequency LIPSS(HSFL)is much smaller than the diffraction limit,making it a useful method for efficient nanomanufacturing.However,compared with the low-spatial-frequency LIPSS(LSFL),the structure size of the HSFL is smaller,and it is more easily submerged.Therefore,the formation mechanism of HSFL is complex and has always been a research hotspot in this field.In this study,regular LSFL with a period of 760 nm was fabricated in advance on a silicon surface with two-beam interference using an 800 nm,50 fs femtosecond laser.The ultrafast dynamics of HSFL formation on the silicon surface of prefabricated LSFL under single femtosecond laser pulse irradiation were observed and analyzed for the first time using collinear pump-probe imaging method.In general,the evolution of the surface structure undergoes five sequential stages:the LSFL begins to split,becomes uniform HSFL,degenerates into an irregular LSFL,undergoes secondary splitting into a weakly uniform HSFL,and evolves into an irregular LSFL or is submerged.The results indicate that the local enhancement of the submerged nanocavity,or the nanoplasma,in the prefabricated LSFL ridge led to the splitting of the LSFL,and the thermodynamic effect drove the homogenization of the splitting LSFL,which evolved into HSFL.