Predicting grain size-dependent superplastic properties in friction stir processed ZK30 magnesium alloy with machine learning methods

The aim of this work is to predict,for the first time,the high temperature flow stress dependency with the grain size and the underlaid deformation mechanism using two machine learning models,random forest(RF)and artificial neural network(ANN).With that purpose,a ZK30 magnesium alloy was friction stir processed(FSP)using three different severe conditions to obtain fine grain microstructures(with average grain sizes between 2 and 3μm)prone to extensive superplastic response.The three friction stir processed samples clearly deformed by grain boundary sliding(GBS)deformation mechanism at high temperatures.The maximum elongations to failure,well over 400% at high strain rate of 10^(-2)s^(-1),were reached at 400℃ in the material with coarsest grain size of 2.8μm,and at 300℃ for the finest grain size of 2μm.Nevertheless,the superplastic response decreased at 350℃ and 400℃ due to thermal instabilities and grain coarsening,which makes it difficult to assess the operative deformation mechanism at such temperatures.This work highlights that the machine learning models considered,especially the ANN model with higher accuracy in predicting flow stress values,allow determining adequately the superplastic creep behavior including other possible grain size scenarios.

Green‑Solvent Processed Blade‑Coating Organic Solar Cells with an Efficiency Approaching 19%Enabled by Alkyl‑Tailored Acceptors

Power-conversion-efficiencies(PCEs)of organic solar cells(OSCs)in laboratory,normally processed by spin-coating technology with toxic halogenated solvents,have reached over 19%.However,there is usually a marked PCE drop when the bladecoating and/or green-solvents toward large-scale printing are used instead,which hampers the practical development of OSCs.Here,a new series of N-alkyl-tailored small molecule acceptors named YR-SeNF with a same molecular main backbone are developed by combining selenium-fused central-core and naphthalene-fused endgroup.Thanks to the N-alkyl engineering,NIR-absorbing YR-SeNF series show different crystallinity,packing patterns,and miscibility with polymeric donor.The studies exhibit that the molecular packing,crystallinity,and vertical distribution of active layer morphologies are well optimized by introducing newly designed guest acceptor associated with tailored N-alkyl chains,providing the improved charge transfer dynamics and stability for the PM6:L8-BO:YRSeNF-based OSCs.As a result,a record-high PCE approaching 19%is achieved in the blade-coating OSCs fabricated from a greensolvent o-xylene with high-boiling point.Notably,ternary OSCs offer robust operating stability under maximum-power-point tracking and well-keep>80%of the initial PCEs for even over 400 h.Our alkyl-tailored guest acceptor strategy provides a unique approach to develop green-solvent and blade-coating processed high-efficiency and operating stable OSCs,which paves a way for industrial development.

In situ digital testing method for quality assessment of soft soil improvement with polyurethane

This study purposes an in situ testing method on quality assessment of soil improvement.Factual drilling data includes the spatial distribution and in situ strength of untreated and treated soil along three different drillholes measured by on-site drilling monitoring method.These factual drilling data can characterize the degree of soil improvement by penetration injection with permeable polyurethane.Result from on-site drilling monitoring shows that the linear zones represent constant drilling speeds shown in the plot of drill bit advancement vs.net drilling time,which indicates the spatial distributions of soil profile.The soil profile at the study site is composed of four layers,which includes fill,untreated silty clay,treated silty clay,and mucky soil.The results of soil profile are verified by the parallel site loggings.The constant drilling speeds profile the coring-resistant strength of drilled soils.By comparing with the untreated silty clay,the constant drilling speeds of the treated silty clay have been decreased by 13.0-62.8%.Two drilling-speed-based indices of 61.2%and 65.6%are proposed to assess the decreased average drilling speed and the increased in situ strength of treated silty clay.Laboratory tests,i.e.uniaxial compressive strength(UCS)test,have been performed with core sample to investigate and characterize in situ strength by comparing that with drilling speeds.Results show that the average predicted strengths of treated silty clay are 2.4-6.9 times higher than the average measured strength of untreated silty clay.The UCS-based indices of 374.5%and 344.2%verified the quality assessment(QA)results by this new in situ method.This method provides a cost-effective tool for quality assessment of soil improvement by utilizing the digital drilling data.

A deep learning framework for suppressing prestack seismic random noise without noise-free labels

Random noise attenuation is significant in seismic data processing.Supervised deep learning-based denoising methods have been widely developed and applied in recent years.In practice,it is often time-consuming and laborious to obtain noise-free data for supervised learning.Therefore,we propose a novel deep learning framework to denoise prestack seismic data without clean labels,which trains a high-resolution residual neural network(SRResnet)with noisy data for input and the same valid data with different noise for output.Since valid signals in noisy sample pairs are spatially correlated and random noise is spatially independent and unpredictable,the model can learn the features of valid data while suppressing random noise.Noisy data targets are generated by a simple conventional method without fine-tuning parameters.The initial estimates allow signal or noise leakage as the network does not require clean labels.The Monte Carlo strategy is applied to select training patches for increasing valid patches and expanding training datasets.Transfer learning is used to improve the generalization of real data processing.The synthetic and real data tests perform better than the commonly used state-of-the-art denoising methods.

Improved Responses with Multitaper Spectral Analysis for Magnetotelluric Time Series Data Processing:Examples from Field Data

In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without a multitaper approach for spectral estimation.There are several common ways to increase the reliability of the Fourier spectral estimation from experimental(noisy)data;for example to subdivide the experimental time series into segments,taper these segments(using single taper),perform the Fourier transform of the individual segments,and average the resulting spectra.

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.

Comparative analysis shows high level of lineage sorting in genomic regions with low recombination in the extended Picea likiangensis species complex

Genome-scale data,while promising for illuminating phylogenetic relationships,frequently pose a conundrum by yielding conflicting topologies and highly variable gene tree distributions(Pease et al.,2016).This complexity likely arises from the reticulate evolution observed in many taxa,where genetic information exchange occurs through diverse biological processes.

Comparing Fine-Tuning, Zero and Few-Shot Strategies with Large Language Models in Hate Speech Detection in English

Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.

Combining reinforcement learning with mathematical programming:An approach for optimal design of heat exchanger networks

Heat integration is important for energy-saving in the process industry.It is linked to the persistently challenging task of optimal design of heat exchanger networks(HEN).Due to the inherent highly nonconvex nonlinear and combinatorial nature of the HEN problem,it is not easy to find solutions of high quality for large-scale problems.The reinforcement learning(RL)method,which learns strategies through ongoing exploration and exploitation,reveals advantages in such area.However,due to the complexity of the HEN design problem,the RL method for HEN should be dedicated and designed.A hybrid strategy combining RL with mathematical programming is proposed to take better advantage of both methods.An insightful state representation of the HEN structure as well as a customized reward function is introduced.A Q-learning algorithm is applied to update the HEN structure using theε-greedy strategy.Better results are obtained from three literature cases of different scales.

Combined Insights from Leachate Structure and Microstructure Characteristics for Eating Quality of Convenience Rice Processed by Super-Heated and Pressurized Steam Technologies

Convenience rice has become widely popular due to its easy availability for cooking. This study investigated the starch structure and composition of leachate and the microstructure of reheated convenience rice using novel processing technologies: super-heated steaming(SHS), auto-electric cooking(AEC), and pressurized-steam cooking(PSC). Additionally, the effect of two different target water contents(58% and 63%) was also evaluated. The PSC_63% sample had the highest total solids and amylopectin amount in the leachate. The amylopectin amount in the leachate differed significantly based on the targeted water content. Morphological characterization revealed that the swelling of starch and the coated layer on the surface of rice grains were most pronounced in the PSC_63% sample due to the pressure processing. The textural hardness of the AEC_58% sample was much higher than that of the other samples. The PSC_63% sample had the highest textural adhesiveness value, which can be attributed to the highest amylopectin amount in the leachate. Sensory characterization showed that the PSC_63% sample had the highest glossiness, whiteness, moistness, and overall acceptability. The principal component analysis score plots presented substantial differences in the leachate and textural and sensory characteristics of reheated convenience rice among the different processing technologies.

Local Torrential Rainfall Event within a Mei-Yu Season Mesoscale Convective System:Importance of Back-Building Processes

An extreme rainfall event occurred over Hangzhou,China,during the afternoon hours on 24 June 2013.This event occurred under suitable synoptic conditions and the maximum 4-h cumulative rainfall amount was over 150 mm.This rainfall event had two major rainbands.One was caused by a quasi-stationary convective line,and the other by a backbuilding convective line related to the interaction of the outflow boundary from the first rainband and an existing low-level mesoscale convergence line associated with a mei-yu frontal system.The rainfall event lasted 4 h,while the back-building process occurred in 2 h when the extreme rainfall center formed.So far,few studies have examined the back-building processes in the mei-yu season that are caused by the interaction of a mesoscale convergence line and a convective cold pool.The two rainbands are successfully reproduced by the Weather Research and Forecasting(WRF)model with fourlevel,two-way interactive nesting.In the model,new cells repeatedly occur at the west side of older cells,and the backbuilding process occurs in an environment with large CAPE,a low LFC,and plenty of water vapor.Outflows from older cells enhance the low-level convergence that forces new cells.High precipitation efficiency of the back-building training cells leads to accumulated precipitation of over 150 mm.Sensitivity experiments without evaporation of rainwater show that the convective cold pool plays an important role in the organization of the back-building process in the current extreme precipitation case.

MicroMagnetic.jl:A Julia package for micromagnetic and atomistic simulations with GPU support

MicroMagnetic.jl is an open-source Julia package for micromagnetic and atomistic simulations.Using the features of the Julia programming language,MicroMagnetic.jl supports CPU and various GPU platforms,including NVIDIA,AMD,Intel,and Apple GPUs.Moreover,MicroMagnetic.jl supports Monte Carlo simulations for atomistic models and implements the nudged-elastic-band method for energy barrier computations.With built-in support for double and single precision modes and a design allowing easy extensibility to add new features,MicroMagnetic.jl provides a versatile toolset for researchers in micromagnetics and atomistic simulations.

Image enhancement with intensity transformation on embedding space

In recent times,an image enhancement approach,which learns the global transformation function using deep neural networks,has gained attention.However,many existing methods based on this approach have a limitation:their transformation functions are too simple to imitate complex colour transformations between low-quality images and manually retouched high-quality images.In order to address this limitation,a simple yet effective approach for image enhancement is proposed.The proposed algorithm based on the channel-wise intensity transformation is designed.However,this transformation is applied to the learnt embedding space instead of specific colour spaces and then return enhanced features to colours.To this end,the authors define the continuous intensity transformation(CIT)to describe the mapping between input and output intensities on the embedding space.Then,the enhancement network is developed,which produces multi-scale feature maps from input images,derives the set of transformation functions,and performs the CIT to obtain enhanced images.Extensive experiments on the MIT-Adobe 5K dataset demonstrate that the authors’approach improves the performance of conventional intensity transforms on colour space metrics.Specifically,the authors achieved a 3.8%improvement in peak signal-to-noise ratio,a 1.8%improvement in structual similarity index measure,and a 27.5%improvement in learned perceptual image patch similarity.Also,the authors’algorithm outperforms state-of-the-art alternatives on three image enhancement datasets:MIT-Adobe 5K,Low-Light,and Google HDRþ.

Colorectal cancer’s burden attributable to a diet high in processed meat in the Belt and Road Initiative countries

BACKGROUND Colorectal cancer(CRC)plays a significant role in morbidity,mortality,and economic cost in the Belt and Road Initiative(“B and R”)countries.In addition,these countries have a substantial consumption of processed meat.However,the burden and trend of CRC in relation to the consumption of a diet high in processed meat(DHPM-CRC)in these“B and R”countries remain unknown.AIM To analyze the burden and trend of DHPM-CRC in the“B and R”countries from 1990 to 2019.METHODS We used the 2019 Global Burden of Disease Study to collate information regarding the burden of DHPM-CRC.Numbers and age-standardized rates(ASRs)of deaths along with the disability-adjusted life years(DALYs)were determined among the“B and R”countries in 1990 and 2019.Using joinpoint regression analysis,the average annual percent change(AAPC)was used to analyze the temporal trends of age-standardized DALYs rate(ASDALR)from 1990 to 2019 and in the final decade(2010–2019).RESULTS We found geographical differences in the burden of DHPM-CRC among“B and R”countries,with the three highest-ranking countries being the Russian Federation,China,and Ukraine in 1990,and China,the Russian Federation,and Poland in 2019.The burden of DHPM-CRC generally increased in most member countries from 1990 to 2019(all P<0.05).The absolute number of deaths and DALYs in DHPM-CRC were 3151.15[95%uncertainty interval(UI)665.74-5696.64]and 83249.31(95%UI 15628.64-151956.31)in China in 2019.However,the number of deaths(2627.57-2528.51)and DALYs(65867.39-55378.65)for DHPM-CRC in the Russian Federation has declined.The fastest increase in ASDALR for DHPM-CRC was observed in Vietnam,Southeast Asia,with an AAPC value of 3.90%[95%confidence interval(CI):3.63%-4.16%],whereas the fastest decline was observed in Kyrgyzstan,Central Asia,with an AAPC value of-2.05%(95%CI:-2.37%to-1.73%).A substantial upward trend in ASR of mortality,years lived with disability,years of life lost,and DALYs from DHPM-CRC changes in 1990-2019 and the final decade(2010-2019)for most Maritime Silk Route members in East Asia,South Asia,Southeast Asia,North Africa,and the Middle East,as well as Central Europe,while those of the most Land Silk Route members in Central Asia and Eastern Europe have decreased markedly(all P<0.05).The ASDALR for DHPM-CRC increased more in males than in females(all P<0.05).For those aged 50-74 years,the ASDALR for DHPM-CRC in 40 members exhibited an increasing trend,except for 20 members,including 7 members in Central Asia,Maldives,and 12 high or high-middle social development index(SDI)members in other regions(all P<0.05).CONCLUSION The burden of DHPM-CRC varies substantially across“B and R”countries and threatens public health.Relevant evidence-based policies and interventions tailored to the different trends of countries in SDIs or Silk Routes should be adopted to reduce the future burden of CRC in“B and R”countries via extensive collaboration.

Modeling and Performance Analysis of UAV-Aided Millimeter Wave Cellular Networks with Stochastic Geometry

UAV-aided cellular networks,millimeter wave(mm-wave) communications and multi-antenna techniques are viewed as promising components of the solution for beyond-5G(B5G) and even 6G communications.By leveraging the power of stochastic geometry,this paper aims at providing an effective framework for modeling and analyzing a UAV-aided heterogeneous cellular network,where the terrestrial base stations(TBSs) and the UAV base stations(UBSs) coexist,and the UBSs are provided with mm-wave and multi-antenna techniques.By modeling the TBSs as a PPP and the UBSs as a Matern hard-core point process of type Ⅱ(MPH-Ⅱ),approximated but accurate analytical results for the average rate of the typical user of both tiers are derived through an approximation method based on the mean interference-to-signal ratio(MISR) gain.The influence of some relevant parameters is discussed in detail,and some insights into the network deployment and optimization are revealed.Numerical results show that some trade-offs are worthy of being considered,such as the antenna array size,the altitude of the UAVs and the power control factor of the UBSs.

An object detection approach with residual feature fusion and second-order term attention mechanism

Automatically detecting and locating remote occlusion small objects from the images of complex traffic environments is a valuable and challenging research.Since the boundary box location is not sufficiently accurate and it is difficult to distinguish overlapping and occluded objects,the authors propose a network model with a second-order term attention mechanism and occlusion loss.First,the backbone network is built on CSPDarkNet53.Then a method is designed for the feature extraction network based on an item-wise attention mechanism,which uses the filtered weighted feature vector to replace the original residual fusion and adds a second-order term to reduce the information loss in the process of fusion and accelerate the convergence of the model.Finally,an objected occlusion regression loss function is studied to reduce the problems of missed detections caused by dense objects.Sufficient experimental results demonstrate that the authors’method achieved state-of-the-art performance without reducing the detection speed.The mAP@.5 of the method is 85.8%on the Foggy_cityscapes dataset and the mAP@.5 of the method is 97.8%on the KITTI dataset.

Electrochemically Deposited CZTSSe Thin Films for Monolithic Perovskite Tandem Solar Cells with Efficiencies Over 17%

In spite of the high potential economic feasibility of the tandem solar cells consisting of the halide perovskite and the kesterite Cu2ZnSn(S,Se)4(CZTSSe),they have rarely been demonstrated due to the difficulty in implementing solution-processed perovskite top cell on the rough surface of the bottom cells.Here,we firstly demonstrate an efficient monolithic two-terminal perovskite/CZTSSe tandem solar cell by significantly reducing the surface roughness of the electrochemically deposited CZTSSe bottom cell.The surface roughness(R_(rms))of the CZTSSe thin film could be reduced from 424 to 86 nm by using the potentiostatic mode rather than using the conventional galvanostatic mode,which can be further reduced to 22 nm after the subsequent ion-milling process.The perovskite top cell with a bandgap of 1.65 eV could be prepared using a solution process on the flattened CZTSSe bottom cell,resulting in the efficient perovskite/CZTSSe tandem solar cells.After the current matching between two subcells involving the thickness control of the perovskite layer,the best performing tandem device exhibited a high conversion efficiency of 17.5%without the hysteresis effect.

RGB-guided hyperspectral image super-resolution with deep progressive learning

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

Learning to represent 2D human face with mathematical model

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of pixels.The authors attempt to learn a continuous surface representation for face image with explicit function.First,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function element.Further,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of EmFace.The authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C datasets.Visualisation results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other factors.Furthermore,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

Health effects of fruit juices and beverages with varying degrees of processing

The degree of processing is rarely considered an independent factor in the health effects of fruit juices and beverages(FJBs)consumption.In fact,the consumption of ultra-processed foods has been shown to pose health risks.In this study,we first integrated 4 systems used to classify the degree of food processing and then classified FJBs into three major categories,low(minimal),moderate and high.Second,we compared the differences in attitudes towards FJBs in dietary guidelines.Third,we integrated the results of existing epidemiological surveys,randomized controlled trials,and animal experiments to explore the health risks associated with consuming FJBs.Deepening the processing of FJBs has been found to lead to an increased risk of diseases.Dietary pattern,nutrients,addition agents and consumer preferences may be influential factors.Finally,we investigated whether there were any changes in the health benefits of 100%fruit juices produced by different processing methods.In conclusion,minimally/moderately processed 100%fruit juices provide more health benefits than highly processed fruit beverages.The results support the need to consider the extent of FJBs processing in future studies to adjust official nutritional recommendations for beverage consumption.