Response of the North Pacific Storm Track Activity in the Cold Season to Multi-scale Oceanic Variations of Kuroshio Extension System: A Statistical Assessment

In this paper,a statistical method called Generalized Equilibrium Feedback Analysis(GEFA)is used to investigate the responses of the North Pacific Storm Track(NPST)in the cold season to the multi-scale oceanic variations of the Kuroshio Extension(KE)system,including its large-scale variation,oceanic front meridional shift,and mesoscale eddy activity.Results show that in the cold season from the lower to the upper troposphere,the KE large-scale variation significantly weakens the storm track activity over the central North Pacific south of 30°N.The northward shift of the KE front significantly strengthens the storm track activity over the western and central North Pacific south of 40°N,resulting in a southward shift of the NPST.In contrast,the NPST response to KE mesoscale eddy activity is not so significant and relatively shallow,which only shows some significant positive signals near the dateline in the lower and middle troposphere.Furthermore,it is found that baroclinicity and baroclinic energy conversion play an important role in the formation of the NPST response to the KE multi-scale oceanic variations.

A semi-analytical model for coupled flow in stress-sensitive multi-scale shale reservoirs with fractal characteristics

A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.

Multi-scale physics-informed neural networks for solving high Reynolds number boundary layer flows based on matched asymptotic expansions

Multi-scale system remains a classical scientific problem in fluid dynamics,biology,etc.In the present study,a scheme of multi-scale Physics-informed neural networks is proposed to solve the boundary layer flow at high Reynolds numbers without any data.The flow is divided into several regions with different scales based on Prandtl's boundary theory.Different regions are solved with governing equations in different scales.The method of matched asymptotic expansions is used to make the flow field continuously.A flow on a semi infinite flat plate at a high Reynolds number is considered a multi-scale problem because the boundary layer scale is much smaller than the outer flow scale.The results are compared with the reference numerical solutions,which show that the msPINNs can solve the multi-scale problem of the boundary layer in high Reynolds number flows.This scheme can be developed for more multi-scale problems in the future.

A multi-scale second-order autoregressive recursive filter approach for the sea ice concentration analysis

To effectively extract multi-scale information from observation data and improve computational efficiency,a multi-scale second-order autoregressive recursive filter(MSRF)method is designed.The second-order autoregressive filter used in this study has been attempted to replace the traditional first-order recursive filter used in spatial multi-scale recursive filter(SMRF)method.The experimental results indicate that the MSRF scheme successfully extracts various scale information resolved by observations.Moreover,compared with the SMRF scheme,the MSRF scheme improves computational accuracy and efficiency to some extent.The MSRF scheme can not only propagate to a longer distance without the attenuation of innovation,but also reduce the mean absolute deviation between the reconstructed sea ice concentration results and observations reduced by about 3.2%compared to the SMRF scheme.On the other hand,compared with traditional first-order recursive filters using in the SMRF scheme that multiple filters are executed,the MSRF scheme only needs to perform two filter processes in one iteration,greatly improving filtering efficiency.In the two-dimensional experiment of sea ice concentration,the calculation time of the MSRF scheme is only 1/7 of that of SMRF scheme.This means that the MSRF scheme can achieve better performance with less computational cost,which is of great significance for further application in real-time ocean or sea ice data assimilation systems in the future.

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

A new two-step variational model for multiplicative noise removal with applications to texture images

Multiplicative noise removal problems have attracted much attention in recent years.Unlike additive noise,multiplicative noise destroys almost all information of the original image,especially for texture images.Motivated by the TV-Stokes model,we propose a new two-step variational model to denoise the texture images corrupted by multiplicative noise with a good geometry explanation in this paper.In the first step,we convert the multiplicative denoising problem into an additive one by the logarithm transform and propagate the isophote directions in the tangential field smoothing.Once the isophote directions are constructed,an image is restored to fit the constructed directions in the second step.The existence and uniqueness of the solution to the variational problems are proved.In these two steps,we use the gradient descent method and construct finite difference schemes to solve the problems.Especially,the augmented Lagrangian method and the fast Fourier transform are adopted to accelerate the calculation.Experimental results show that the proposed model can remove the multiplicative noise efficiently and protect the texture well.

Multi-scale context-aware network for continuous sign language recognition

The hands and face are the most important parts for expressing sign language morphemes in sign language videos.However,we find that existing Continuous Sign Language Recognition(CSLR)methods lack the mining of hand and face information in visual backbones or use expensive and time-consuming external extractors to explore this information.In addition,the signs have different lengths,whereas previous CSLR methods typically use a fixed-length window to segment the video to capture sequential features and then perform global temporal modeling,which disturbs the perception of complete signs.In this study,we propose a Multi-Scale Context-Aware network(MSCA-Net)to solve the aforementioned problems.Our MSCA-Net contains two main modules:(1)Multi-Scale Motion Attention(MSMA),which uses the differences among frames to perceive information of the hands and face in multiple spatial scales,replacing the heavy feature extractors;and(2)Multi-Scale Temporal Modeling(MSTM),which explores crucial temporal information in the sign language video from different temporal scales.We conduct extensive experiments using three widely used sign language datasets,i.e.,RWTH-PHOENIX-Weather-2014,RWTH-PHOENIX-Weather-2014T,and CSL-Daily.The proposed MSCA-Net achieve state-of-the-art performance,demonstrating the effectiveness of our approach.

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

Transfer learning framework for multi-scale crack type classification with sparse microseismic networks

Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.

MSC-YOLO:Improved YOLOv7 Based on Multi-Scale Spatial Context for Small Object Detection in UAV-View

Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.

A Study to Observe Pulse Pressure Variation after Induction with Propofol for General Anesthesia

Background and Aims: Pulse pressure variation (PPV) is a reliable and predictive dynamic parameter presently being utilized for fluid responsiveness. In the operating room, fluid administration based on PPV monitoring helps the physician in deciding whether to volume resuscitate or use interventions in patients undergoing surgery. Propofol is an intravenous induction agent which lowers blood pressure. There are multiple causes such as depression in cardiac output, and peripheral vasodilatation for hypotension. We undertook this study to observe the utility of PPV as a guide to fluid therapy after propofol induction. Primary outcome of our study was to monitor PPV as a marker of fluid responsiveness for the hypotension caused by propofol induction. Secondary outcome included the correlation of PPV with other hemodynamic parameters like heart rate (HR), systolic blood pressure (SBP), and diastolic blood pressure (DBP);after induction with propofol at regular interval of time. Methods: A total number of 90 patients were recruited. Either of the radial artery was then cannulated under local anaesthesia with 20G VygonLeadercath arterial cannula and invasive monitoring transduced. A baseline recording of heart rate (HR), systolic blood pressure (SBP), diastolic blood pressure (DBP) and PPV was then recorded. Patients were then induced with predetermined doses of propofol (2 mg/kg) and recordings of HR, SBP, DBP, and PPV were taken at 5, 10 and 15 minutes. Results: Intraoperatively, PPV was significantly higher at 5 minutes and significantly lower at 15 minutes after induction. It was observed that there were no statistically significant correlations between PPV and SBP or DBP. PPV was strongly and directly associated with HR. Conclusion: We were able to establish that PPV predicts fluid responsiveness in hypotension caused by propofol induction;and can be used to administer fluid therapy in managing such hypotension. However, PPV was not directly correlated with hypotension subsequent to propofol administration.

Small temporal variation in abundance of virioplankton compared to bacterioplankton and phytoplankton in two bays in the northern South China Sea

Variations of picoplankton groups were investigated over a one-month period in Daya Bay and Sanya Bay,in the northern South China Sea.The two coastal regions exhibited different variation patterns in physicochemical parameters.Moreover,the diel variations of picoplankton groups were different between the two bays.The abundance of the picoplankton in Sanya Bay displayed a pronounced diel variation,while it was not significant in Daya Bay.In addition,some similar patterns of picoplankton abundance were discovered.In the two bays,virioplankton exhibited the smallest fluctuation range,whereas picocyanobacteria fluctuated most markedly.The fluctuation range of picoplankton groups was larger in spring tide than in neap tide,especially in Sanya Bay.Random forest model analysis demonstrated that the variation of picoplankton groups was attributed to physical and chemical factors in Sanya Bay and Daya Bay,respectively.Therefore,our findings suggest that virioplankton abundance can persist more stably in response to changing environmental conditions compared to bacterioplankton and picophytoplankton.

Associations of genome-wide structural variations with phenotypic differences in cross-bred Eurasian pigs

Background During approximately 10,000 years of domestication and selection,a large number of structural variations(SVs)have emerged in the genome of pig breeds,profoundly influencing their phenotypes and the ability to adapt to the local environment.SVs(≥50 bp)are widely distributed in the genome,mainly in the form of insertion(INS),mobile element insertion(MEI),deletion(DEL),duplication(DUP),inversion(INV),and translocation(TRA).While studies have investigated the SVs in pig genomes,genome-wide association studies(GWAS)-based on SVs have been rarely conducted.Results Here,we obtained a high-quality SV map containing 123,151 SVs from 15 Large White and 15 Min pigs through integrating the power of several SV tools,with 53.95%of the SVs being reported for the first time.These high-quality SVs were used to recover the population genetic structure,confirming the accuracy of genotyping.Potential functional SV loci were then identified based on positional effects and breed stratification.Finally,GWAS were performed for 36 traits by genotyping the screened potential causal loci in the F2 population according to their corresponding genomic positions.We identified a large number of loci involved in 8 carcass traits and 6 skeletal traits on chromosome 7,with FKBP5 containing the most significant SV locus for almost all traits.In addition,we found several significant loci in intramuscular fat,abdominal circumference,heart weight,and liver weight,etc.Conclusions We constructed a high-quality SV map using high-coverage sequencing data and then analyzed them by performing GWAS for 25 carcass traits,7 skeletal traits,and 4 meat quality traits to determine that SVs may affect body size between European and Chinese pig breeds.

Multi-scale Modeling and Finite Element Analyses of Thermal Conductivity of 3D C/SiC Composites Fabricating by Flexible-Oriented Woven Process

Thermal conductivity is one of the most significant criterion of three-dimensional carbon fiber-reinforced SiC matrix composites(3D C/SiC).Represent volume element(RVE)models of microscale,void/matrix and mesoscale proposed in this work are used to simulate the thermal conductivity behaviors of the 3D C/SiC composites.An entirely new process is introduced to weave the preform with three-dimensional orthogonal architecture.The 3D steady-state analysis step is created for assessing the thermal conductivity behaviors of the composites by applying periodic temperature boundary conditions.Three RVE models of cuboid,hexagonal and fiber random distribution are respectively developed to comparatively study the influence of fiber package pattern on the thermal conductivities at the microscale.Besides,the effect of void morphology on the thermal conductivity of the matrix is analyzed by the void/matrix models.The prediction results at the mesoscale correspond closely to the experimental values.The effect of the porosities and fiber volume fractions on the thermal conductivities is also taken into consideration.The multi-scale models mentioned in this paper can be used to predict the thermal conductivity behaviors of other composites with complex structures.

Temperature is a cryptic factor shaping the geographical pattern of genetic variation in Ceratophyllum demersum across a subtropical freshwater lake

Macrophyte habitats exhibit remarkable heterogeneity,encompassing the spatial variation of abiotic and biotic components such as changes in water conditions and weather as well as anthropogenic stressors.Environmental factors are thought to be important drivers shaping the genetic and epigenetic variation of aquatic plants.However,the links among genetic diversity,epigenetic variation,and environmental variables remain largely unclear,especially for clonal aquatic plants.Here,we performed population genetic and epigenetic analyses in conjunction with habitat discrimination to elucidate the environmental factors driving intraspecies genetic and epigenetic variation in hornwort(Ceratophyllum demersum)in a subtropical lake.Environmental factors were highly correlated with the genetic and epigenetic variation of C.demersum,with temperature being a key driver of the genetic variation.Lower temperature was detected to be correlated with greater genetic and epigenetic variation.Genetic and epigenetic variation were positively driven by water temperature,but were negatively affected by ambient air temperature.These findings indicate that the genetic and epigenetic variation of this clonal aquatic herb is not related to the geographic feature but is instead driven by environmental conditions,and demonstrate the effects of temperature on local genetic and epigenetic variation in aquatic systems.

The Variation of Plankton Community Structure in Artificial Reef Area and Adjacent Waters in Haizhou Bay

Plankton are an important component of marine protected areas(MPAs),and its communities would require much smaller interpatch distances to ensure connection among MPAs.According to the survey from MPAs dominated by artificial reefs and adjacent waters(estuary area(EA),aquaculture area(AA),artificial reef area(ARA),natural area(NA)and comprehensive effect area(CEA))in Haizhou Bay in spring and autumn,we analyzed phyto-zooplankton composition,abundance and biomass,and correlation with hydrologic variables to gain information about the forces that structure the plankton.The results showed that the dominant zooplankton were copepods(spring,98.9%;autumn,94.2%),while the phytoplankton were mainly composed of Bacillariophyta(spring,61.8%;autumn,95.6%).The RDA results showed that temperature,salinity and depth highly associated with the distribution and composition of plankton species among the habitats than other factors in spring;temperature,Chla and DO had the strongest influence in autumn.The zooplankton in the ARA and AA ecosystems basically contained the same species as those in other habitats,and each habitat also exhibited a relatively unique combination of plankton species.The structures of the EA zooplankton in spring and the EA phytoplankton in both seasons were much different than other habitats,which may have been caused by factors such as currents and tides.We concluded that there exists similarity of the plankton community between artificial reef area and adjacent waters,whereas the EAs may be relatively independent systems.Therefore,these interaction between plankton community should be considered when designing MPA networks,and ocean circulations should be considered more than the environmental factors.

Seasonal Variation of Hearing Sensitivity in the Red-eared Slider(Trachemys scripta elegans)

Seasonal variation of hearing sensitivity has been observed in many vertebrate groups with obvious vocal behaviors.Circulating hormones,conspecific calling signals,and temperature are potential factors that drive these plasticity patterns.Turtles have a hearing range that appears to be limited to under 1.5 kHz and are often thought to be non-vocal;thus,they are commonly neglected in vocal communication research.In this study,we aimed to determine whether the auditory phenotype exhibits seasonal variation in sensitivity and to analyze the potential factors driving such variation patterns in turtles.We measured hearing sensitivity and sex hormone levels in female(estradiol)and male(testosterone and dihydrotestosterone)Red-eared sliders(Trachemys scripta elegans)during spring and winter.The results showed that auditory brainstem response(ABR)thresholds were significantly lower in spring than in winter at a frequency range of 0.5-0.9 kHz.The hearing-sensitivity bandwidth was wider,and the ABR latency was significantly shorter in spring than in winter.No significant differences were found in estradiol,testosterone,and dihydrotestosterone levels in T.scripta elegans between spring and winter.This study is the first to reveal the seasonal variation of peripheral hearing sensitivity in turtles,a special animal group with limited hearing range and less vocalization.Temperature variations may be used to explain these seasonal effects,but further research is required to confirm our findings.

Improved multi-scale inverse bottleneck residual network based on triplet parallel attention for apple leaf disease identification

Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small computational costs while the dimensional dependencies are improved. To verify the validity of the model in this paper, we uniformly enhance apple leaf disease images screened from the public data sets of Plant Village, Baidu Flying Paddle, and the Internet. The final processed image count is 14,000. The ablation study, pre-processing comparison, and method comparison are conducted on the processed datasets. The experimental results demonstrate that the proposed method reaches 98.73% accuracy on the adopted datasets, which is 1.82% higher than the classical ResNet-50 model, and 0.29% better than the apple leaf disease datasets before preprocessing. It also achieves competitive results in apple leaf disease identification compared to some state-ofthe-art methods.

Few-shot image recognition based on multi-scale features prototypical network

In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.

Multi-Scale Mixed Attention Tea Shoot Instance Segmentation Model

Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often handpicked and need more delicate operations in intelligent picking machines.Compared with traditional image processing techniques,deep learning models have stronger feature extraction capabilities,and better generalization and are more suitable for practical tea shoot harvesting.However,current research mostly focuses on shoot detection and cannot directly accomplish end-to-end shoot segmentation tasks.We propose a tea shoot instance segmentation model based on multi-scale mixed attention(Mask2FusionNet)using a dataset from the tea garden in Hangzhou.We further analyzed the characteristics of the tea shoot dataset,where the proportion of small to medium-sized targets is 89.9%.Our algorithm is compared with several mainstream object segmentation algorithms,and the results demonstrate that our model achieves an accuracy of 82%in recognizing the tea shoots,showing a better performance compared to other models.Through ablation experiments,we found that ResNet50,PointRend strategy,and the Feature Pyramid Network(FPN)architecture can improve performance by 1.6%,1.4%,and 2.4%,respectively.These experiments demonstrated that our proposed multi-scale and point selection strategy optimizes the feature extraction capability for overlapping small targets.The results indicate that the proposed Mask2FusionNet model can perform the shoot segmentation in unstructured environments,realizing the individual distinction of tea shoots,and complete extraction of the shoot edge contours with a segmentation accuracy of 82.0%.The research results can provide algorithmic support for the segmentation and intelligent harvesting of premium tea shoots at different scales.