A Case Study on MJO Energy Transport Path in a Local Multi-scale Interaction Framework

A new local kinetic energy(KE)budget for the Madden−Julian Oscillation(MJO)is constructed in a multi-scale framework.This energy budget framework allows us to analyze the local energy conversion processes of the MJO with the high-frequency disturbances and the low-frequency background state.The KE budget analysis is applied to a pronounced MJO event during the DYNAMO field campaign to investigate the KE transport path of the MJO.The work done by the pressure gradient force and the conversion of available potential energy at the MJO scale are the two dominant processes that affect the MJO KE tendency.The MJO winds transport MJO KE into the MJO convection region in the lower troposphere while it is transported away from the MJO convection region in the upper troposphere.The energy cascade process is relatively weak,but the interaction between high-frequency disturbances and the MJO plays an important role in maintaining the high-frequency disturbances within the MJO convection.The MJO KE mainly converts to interaction KE between MJO and high-frequency disturbances over the area where the MJO zonal wind is strong.This interaction KE over the MJO convection region is enhanced through its flux convergence and further transport KE to the high-frequency disturbances.This process is conducive to maintaining the MJO convection.This study highlights the importance of KE interaction between the MJO and the high-frequency disturbances in maintaining the MJO convection.

Multi-scale interaction between tearing modes and micro-turbulence in the HL-2A plasmas

The influence of m/n=2/1(m and n are poloidal and toroidal mode numbers)tearing modes on plasma perpendicular flows and micro-fluctuations has been investigated in HL-2A neutral beam injection heated L-mode plasmas.It is found that the local perpendicular rotation velocity and turbulence energy are modulated by the alternation between the island X-point and O-point of the naturally rotating tearing modes.Cross-correlation analysis indicates that the modulation of density fluctuations by the tearing mode is not only limited to the island region,but also occurs in the edge region near the last closed flux surface.The turbulence exhibits distinct spectral characteristics inside and outside the island region.In addition,it is observed that the particle flux near the strike point is also significantly impacted by the tearing modes.The experimental evidence reveals that there are strong core-edge interactions between the core tearing modes and the edge transport.

Tailoring Light–Matter Interactions in Overcoupled Resonator for Biomolecule Recognition and Detection

Plasmonic nanoantennas provide unique opportunities for precise control of light–matter coupling in surface-enhanced infrared absorption(SEIRA)spectroscopy,but most of the resonant systems realized so far suffer from the obstacles of low sensitivity,narrow bandwidth,and asymmetric Fano resonance perturbations.Here,we demonstrated an overcoupled resonator with a high plasmon-molecule coupling coefficient(μ)(OC-Hμresonator)by precisely controlling the radiation loss channel,the resonator-oscillator coupling channel,and the frequency detuning channel.We observed a strong dependence of the sensing performance on the coupling state,and demonstrated that OC-Hμresonator has excellent sensing properties of ultra-sensitive(7.25%nm^(−1)),ultra-broadband(3–10μm),and immune asymmetric Fano lineshapes.These characteristics represent a breakthrough in SEIRA technology and lay the foundation for specific recognition of biomolecules,trace detection,and protein secondary structure analysis using a single array(array size is 100×100μm^(2)).In addition,with the assistance of machine learning,mixture classification,concentration prediction and spectral reconstruction were achieved with the highest accuracy of 100%.Finally,we demonstrated the potential of OC-Hμresonator for SARS-CoV-2 detection.These findings will promote the wider application of SEIRA technology,while providing new ideas for other enhanced spectroscopy technologies,quantum photonics and studying light–matter interactions.

Catalyst–Support Interaction in Polyaniline‑Supported Ni_(3)Fe Oxide to Boost Oxygen Evolution Activities for Rechargeable Zn‑Air Batteries

Catalyst–support interaction plays a crucial role in improving the catalytic activity of oxygen evolution reaction(OER).Here we modulate the catalyst–support interaction in polyaniline-supported Ni_(3)Fe oxide(Ni_(3)Fe oxide/PANI)with a robust hetero-interface,which significantly improves oxygen evolution activities with an overpotential of 270 mV at 10 mA cm^(-2)and specific activity of 2.08 mA cm_(ECSA)^(-2)at overpotential of 300 mV,3.84-fold that of Ni_(3)Fe oxide.It is revealed that the catalyst–support interaction between Ni_(3)Fe oxide and PANI support enhances the Ni–O covalency via the interfacial Ni–N bond,thus promoting the charge and mass transfer on Ni_(3)Fe oxide.Considering the excellent activity and stability,rechargeable Zn-air batteries with optimum Ni_(3)Fe oxide/PANI are assembled,delivering a low charge voltage of 1.95 V to cycle for 400 h at 10 mA cm^(-2).The regulation of the effect of catalyst–support interaction on catalytic activity provides new possibilities for the future design of highly efficient OER catalysts.

T cell interactions with microglia in immune-inflammatory processes of ischemic stroke

The primary mechanism of secondary injury after cerebral ischemia may be the brain inflammation that emerges after an ischemic stroke,which promotes neuronal death and inhibits nerve tissue regeneration.As the first immune cells to be activated after an ischemic stroke,microglia play an important immunomodulatory role in the progression of the condition.After an ischemic stroke,peripheral blood immune cells(mainly T cells)are recruited to the central nervous system by chemokines secreted by immune cells in the brain,where they interact with central nervous system cells(mainly microglia)to trigger a secondary neuroimmune response.This review summarizes the interactions between T cells and microglia in the immune-inflammatory processes of ischemic stroke.We found that,during ischemic stroke,T cells and microglia demonstrate a more pronounced synergistic effect.Th1,Th17,and M1 microglia can co-secrete proinflammatory factors,such as interferon-γ,tumor necrosis factor-α,and interleukin-1β,to promote neuroinflammation and exacerbate brain injury.Th2,Treg,and M2 microglia jointly secrete anti-inflammatory factors,such as interleukin-4,interleukin-10,and transforming growth factor-β,to inhibit the progression of neuroinflammation,as well as growth factors such as brain-derived neurotrophic factor to promote nerve regeneration and repair brain injury.Immune interactions between microglia and T cells influence the direction of the subsequent neuroinflammation,which in turn determines the prognosis of ischemic stroke patients.Clinical trials have been conducted on the ways to modulate the interactions between T cells and microglia toward anti-inflammatory communication using the immunosuppressant fingolimod or overdosing with Treg cells to promote neural tissue repair and reduce the damage caused by ischemic stroke.However,such studies have been relatively infrequent,and clinical experience is still insufficient.In summary,in ischemic stroke,T cell subsets and activated microglia act synergistically to regulate inflammatory progression,mainly by secreting inflammatory factors.In the future,a key research direction for ischemic stroke treatment could be rooted in the enhancement of anti-inflammatory factor secretion by promoting the generation of Th2 and Treg cells,along with the activation of M2-type microglia.These approaches may alleviate neuroinflammation and facilitate the repair of neural tissues.

Dynamic Interaction Analysis of Coupled Axial-Torsional-Lateral Mechanical Vibrations in Rotary Drilling Systems

Maintaining the integrity and longevity of structures is essential in many industries,such as aerospace,nuclear,and petroleum.To achieve the cost-effectiveness of large-scale systems in petroleum drilling,a strong emphasis on structural durability and monitoring is required.This study focuses on the mechanical vibrations that occur in rotary drilling systems,which have a substantial impact on the structural integrity of drilling equipment.The study specifically investigates axial,torsional,and lateral vibrations,which might lead to negative consequences such as bit-bounce,chaotic whirling,and high-frequency stick-slip.These events not only hinder the efficiency of drilling but also lead to exhaustion and harm to the system’s components since they are difficult to be detected and controlled in real time.The study investigates the dynamic interactions of these vibrations,specifically in their high-frequency modes,usingfield data obtained from measurement while drilling.Thefindings have demonstrated the effect of strong coupling between the high-frequency modes of these vibrations on drilling sys-tem performance.The obtained results highlight the importance of considering the interconnected impacts of these vibrations when designing and implementing robust control systems.Therefore,integrating these compo-nents can increase the durability of drill bits and drill strings,as well as improve the ability to monitor and detect damage.Moreover,by exploiting thesefindings,the assessment of structural resilience in rotary drilling systems can be enhanced.Furthermore,the study demonstrates the capacity of structural health monitoring to improve the quality,dependability,and efficiency of rotary drilling systems in the petroleum industry.

Psycho-gastroenterological profile of an Italian population of children with disorders of gut-brain interaction:A case-control study

BACKGROUND Disorders of gut-brain interaction(DGBI)are common,but knowledge about their physiopathology is still poor,nor valid tools have been used to evaluate them in childhood.AIM To develop a psycho-gastroenterological questionnaire(PGQ)to assess the psycho-gastroenterological profile and social characteristics of a pediatric population with and without DGBI.METHODS One hundred and nineteen Italian children(age 11-18)were included:28 outpatient patients with DGBI(Rome IV criteria)and 91 healthy controls.They filled the PGQ,faces pain scale revised(FPS-R),Bristol stool chart,ga-strointestinal symptoms rating scale,state-trait anxiety inventory,Toronto alexithymia scale 20,perceived self-efficacy in the management of negative emotions and expression of positive emotions(APEN-G,APEP-G),irritable bowel syndrome-quality of life questionnaire,school performances,tobacco use,early life events,degree of digital-ization.RESULTS Compared to controls,patients had more medical examinations(35%of them went to the doctor more than five times),a higher school performance(23%vs 13%,P<0.05),didn’t use tobacco(never vs 16%,P<0.05),had early life events(28%vs 1%P<0.05)and a higher percentage of pain classified as 4 in the FPS-R during the examination(14%vs 7%,P<0.05).CONCLUSION Pediatric outpatients with DGBI had a higher prevalence of early life events,a lower quality of life,more medical examinations rising health care costs,lower anxiety levels.

The Effect of the Interaction among Multi-Scale Systems and the Asymmetric an

ＴＨＥＥＦＦＥＣＴＯＦＴＨＥＩＮＴＥＲＡＣＴＩＯＮＡＭＯＮＧＭＵＬＴＩ－ＳＣＡＬＥＳＹＳＴＥＭＳＡＮＤＴＨＥＡＳＹＭＭＥＴＲＩＣＤＹＮＡＭＩＣＡＮＤＴＨＥＲＭＯＤＹＮＡＭＩＣＳＴＲＵＣＴＵＲＥＯＦＴＲＯＰＩＣＡＬＣＹＣＬＯＮＥＯＮＩＴＳＴＲＡＣＫＸｕ...

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.

Biological Interaction and Imaging of Ultrasmall Gold Nanoparticles

Ultrasmall gold nanoparticles(AuNPs)typically includes atomically precise gold nanoclusters(AuNCs)and AuNPs with a core size below 3 nm.Serving as a bridge between small molecules and traditional inorganic nanoparticles,the ultrasmall AuNPs show the unique advantages of both small molecules(e.g.,rapid distribution,renal clearance,low non-specific organ accumulation)and nanoparticles(e.g.,long blood circulation and enhanced permeability and retention effect).The emergence of ultrasmall AuNPs creates significant opportunities to address many challenges in the health field including disease diagnosis,monitoring and treatment.Since the nano–bio interaction dictates the overall biological applications of the ultrasmall AuNPs,this review elucidates the recent advances in the biological interactions and imaging of ultrasmall AuNPs.We begin with the introduction of the factors that influence the cellular interactions of ultrasmall AuNPs.We then discuss the organ interactions,especially focus on the interactions of the liver and kidneys.We further present the recent advances in the tumor interactions of ultrasmall AuNPs.In addition,the imaging performance of the ultrasmall AuNPs is summarized and discussed.Finally,we summarize this review and provide some perspective on the future research direction of the ultrasmall AuNPs,aiming to accelerate their clinical translation.

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.

Machine learning with active pharmaceutical ingredient/polymer interaction mechanism:Prediction for complex phase behaviors of pharmaceuticals and formulations

The high throughput prediction of the thermodynamic phase behavior of active pharmaceutical ingredients(APIs)with pharmaceutically relevant excipients remains a major scientific challenge in the screening of pharmaceutical formulations.In this work,a developed machine-learning model efficiently predicts the solubility of APIs in polymers by learning the phase equilibrium principle and using a few molecular descriptors.Under the few-shot learning framework,thermodynamic theory(perturbed-chain statistical associating fluid theory)was used for data augmentation,and computational chemistry was applied for molecular descriptors'screening.The results showed that the developed machine-learning model can predict the API-polymer phase diagram accurately,broaden the solubility data of APIs in polymers,and reproduce the relationship between API solubility and the interaction mechanisms between API and polymer successfully,which provided efficient guidance for the development of pharmaceutical formulations.

Strong metal–support interaction boosts the electrocatalytic hydrogen evolution capability of Ru nanoparticles supported on titanium nitride

Ruthenium(Ru)has been regarded as one of the most promising alternatives to substitute Pt for catalyzing alkaline hydrogen evolution reaction(HER),owing to its inherent high activity and being the cheapest platinum-group metal.Herein,based on the idea of strong metal–support interaction(SMSI)regulation,Ru/TiN catalysts with different degrees of TiN overlayer over Ru nanoparticles were fabricated,which were applied to the alkaline electrolytic water.Characterizations reveal that the TiN overlayer would gradually encapsulate the Ru nanoparticles and induce more electron transfer from Ru nanoparticles to TiN support by the Ru–N–Ti bond as the SMSI degree increased.Further study shows that the exposed Ru–TiN interfaces greatly promote the H_(2) desorption capacity.Thus,the Ru/TiN-300 with a moderate SMSI degree exhibits excellent HER performance,with an overpotential of 38 mV at 10 mA cm^(−2).Also,due to the encapsulation role of TiN overlayer on Ru nanoparticles,it displays super long-term stability with a very slight potential change after 24 h.This study provides a deep insight into the influence of the SMSI effect between Ru and TiN on HER and offers a novel approach for preparing efficient and stable HER electrocatalysts through SMSI engineering.

Enhanced Ion-Selective Diffusion Achieved by Supramolecular Interaction for High Thermovoltage and Thermal Stability

Thermoelectric(TE)generators capable of converting thermal energy into applicable electricity have gained great popularity among emerging energy conversion technologies.Biopolymer-based ionic thermoelectric(i-TE)materials are promising candidates for energy conversion systems because of their wide sources,innocuity,and low manufacturing cost.However,common physically crosslinked biopolymer gels induced by single hydrogen bonding or hydrophobic interaction suffer from low differential thermal voltage and poor thermodynamic stability.Here,we develop a novel i-TE gel with supramolecular structures through multiple noncovalent interactions between ionic liquids(ILs)and gelatin molecular chains.The thermopower and thermoelectric power factor of the ionic gels are as high as 2.83 mV K-1 and 18.33μW m^(-1)K^(-2),respectively.The quasi-solid-state gelatin-[EMIM]DCA i-TE cells achieve ultrahigh 2 h output energy density(E_(2h)=9.9 mJ m^(-2))under an optimal temperature range.Meanwhile,the remarkable stability of the supramolecular structure provides the i-TE hydrogels with a thermal stability of up to 80℃.It breaks the limitation that biopolymer-based i-TE gels can only be applied in the low temperature range and enables biopolymer-based i-TE materials to pursue better performance in a higher temperature range.

Electrostatic Interaction-directed Construction of Hierarchical Nanostructured Carbon Composite with Dual Electrical Conductive Networks for Zinc-ion Hybrid Capacitors with Ultrastability

Metal-organic framework(MOF)-derived carbon composites have been considered as the promising materials for energy storage.However,the construction of MOF-based composites with highly controllable mode via the liquid-liquid synthesis method has a great challenge because of the simultaneous heterogeneous nucleation on substrates and the self-nucleation of individual MOF nanocrystals in the liquid phase.Herein,we report a bidirectional electrostatic generated self-assembly strategy to achieve the precisely controlled coatings of single-layer nanoscale MOFs on a range of substrates,including carbon nanotubes(CNTs),graphene oxide(GO),MXene,layered double hydroxides(LDHs),MOFs,and SiO_(2).The obtained MOF-based nanostructured carbon composite exhibits the hierarchical porosity(V_(meso)/V_(micro)∶2.4),ultrahigh N content of 12.4 at.%and"dual electrical conductive networks."The assembled aqueous zinc-ion hybrid capacitor(ZIC)with the prepared nanocarbon composite as a cathode shows a high specific capacitance of 236 F g^(-1)at 0.5 A g^(-1),great rate performance of 98 F g^(-1)at 100 A g^(-1),and especially,an ultralong cycling stability up to 230000 cycles with the capacitance retention of 90.1%.This work develops a repeatable and general method for the controlled construction of MOF coatings on various functional substrates and further fabricates carbon composites for ZICs with ultrastability.

Plume-lithosphere interaction in the Comei Large Igneous Province: Evidence from two types of mafic dykes in Gyangze, south Tibet, China

Two suites of mafic dykes,T1193-A and T1194-A,outcrop in Gyangze area,southeast Tibet.They are in the area of Comei LIP and have indistinguishable field occurrences with two other dykes in Gyangze,T0902 dyke with 137.7±1.3 Ma zircon age and T0907 dyke with 142±1.4 Ma zircon age reported by Wang YY et al.(2016),indicating coeval formation time.Taking all the four diabase dykes into consideration,two different types,OIB-type and weak enriched-type,can be summarized.The“OIB-type”samples,including T1193-A and T0907 dykes,show OIB-like geochemical features and have initial Sr-Nd isotopic values similar with most mafic products in Comei Large Igneous Provinces(LIP),suggesting that they represent melts directly generated from the Kerguelen mantle plume.The“weak enriched-type”samples,including T1194-A and T0902 dykes,have REEs and trace element patterns showing withinplate affinity but have obvious Nb-Ta-Ti negative anomalies.They show uniform lowerεNd(t)values(−6‒−2)and higher 87Sr/86Sr(t)values(0.706‒0.709)independent of their MgO variation,indicating one enriched mantle source.Considering their closely spatial and temporal relationship with the widespread Comei LIP magmatic products in Tethyan Himalaya,these“weak enriched-type”samples are consistent with mixing of melts from mantle plume and the above ancient Tethyan Himalaya subcontinental lithospheric mantle(SCLM)in different proportions.These weak enriched mafic rocks in Comei LIP form one special rock group and most likely suggest large scale hot mantle plume-continental lithosphere interaction.This process may lead to strong modification of the Tethyan Himalaya lithosphere in the Early Cretaceous.

Ecological network analysis reveals complex responses of tree species life stage interactions to stand variables

Tree interactions are essential for the structure,dynamics,and function of forest ecosystems,but variations in the architecture of life-stage interaction networks(LSINs)across forests is unclear.Here,we constructed 16 LSINs in the mountainous forests of northwest Hebei,China based on crown overlap from four mixed forests with two dominant tree species.Our results show that LSINs decrease the complexity of stand densities and basal areas due to the interaction cluster differentiation.In addition,we found that mature trees and saplings play different roles,the first acting as“hub”life stages with high connectivity and the second,as“bridges”controlling information flow with high centrality.Across the forests,life stages with higher importance showed better parameter stability within LSINs.These results reveal that the structure of tree interactions among life stages is highly related to stand variables.Our efforts contribute to the understanding of LSIN complexity and provide a basis for further research on tree interactions in complex forest communities.

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.

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.