Solving Combinatorial Optimization Problems with Deep Neural Network:A Survey

Combinatorial Optimization Problems(COPs)are a class of optimization problems that are commonly encountered in industrial production and everyday life.Over the last few decades,traditional algorithms,such as exact algorithms,approximate algorithms,and heuristic algorithms,have been proposed to solve COPs.However,as COPs in the real world become more complex,traditional algorithms struggle to generate optimal solutions in a limited amount of time.Since Deep Neural Networks(DNNs)are not heavily dependent on expert knowledge and are adequately flexible for generalization to various COPs,several DNN-based algorithms have been proposed in the last ten years for solving COPs.Herein,we categorize these algorithms into four classes and provide a brief overview of their applications in real-world problems.

基于绿色化学理念的自由基聚合制备聚丙烯酸实验新探索

自由基聚合制备聚丙烯酸实验是高分子化学实验课程中重要且经典的教学内容,其单体易得、反应条件温和,作为掌握自由基聚合反应和多孔吸附材料制备的代表性实验,多个高等院校均有开设。但现有教材中聚丙烯酸的制备实验存在反应体系易凝胶化、产生废液多,流程耗时30.5–33 h,无法在一个教学段内完成,表征过程较繁复等问题。为此,本改进实验采用天然且廉价易得的海藻酸钠作为增稠剂,稳定反应体系粘度,防止因局部粘度剧增引起的反应体系凝胶化;采用同样天然且廉价易得的多孔硅藻土作填充剂,与自由基聚合反应制得的聚丙烯酸溶液共沉淀制备多孔树脂,大幅减少有机溶剂的使用和消耗。此外,本改进实验紧跟学术前沿,引入智能手机识别-比色分析法表征产物的吸附性能,表征手段快速便捷。新的致孔方式和表征手段使实验时长缩减至5 h内,保证了教学的连贯性,同时保留原实验特色,使得该实验更具有教学意义,有利于激发学生对本实验课程的学习兴趣。

Spatially explicit reconstruction of cropland cover for China over the past millennium

Reconstructing historical land use and land cover change using explicit temporal,quantitative,and spatial information is not only the prerequisite for simulating long-term climate change and ecological effects but is also a scientific basis for comprehensively understanding the process and mechanism of anthropogenic land use alterations.Considering changes in historical borders and administrative divisions,a provincial cropland area dataset for China over the past millennium was created on the basis of existing estimations since the Song Dynasty.Land suitability for cultivation was then assessed by incorporating altitude,slope,soil texture,and the maximum potential productivity of climate.Subsequently,a gridding allocation model for cropland was constructed,and the provincial cropland area for 24 years over the past millennium was allocated into grids with a resolution of 10 km.The cropland area in China increased from 3.71×10^(7)ha in AD 1000 to 12.92×10^(7)ha in AD 1999,with a peak of 13.50×10^(7)ha in AD 1980.The total cropland area in China showed fluctuating increasing trends that can be divided into three phases:fluctuation without notable net change for AD 1000–1290,slow increase for AD 1290–1661,and rapid increase for AD 1661–1999.Spatially,cropland intensified in the middle-lower reaches of the Yellow and Yangtze Rivers and expanded to mountainous and frontier areas over the last millennium.Specifically,over the entire period,the fractional cropland areas(FCAs)in the middle-lower reaches of the Yellow and Yangtze Rivers increased by 1.4 and 0.8 times,respectively.Since the mid-Qing Dynasty,large-scale land reclamation expanded to areas of low reclamation in southwest and northeast China.The FCAs for southwest and northeast China increased from 2.13%and 0.55%in AD 1661 to 18.00%and 26.61%in AD 1999,respectively.For AD 1661–1999,the proportion of cropland increased by 55%in the hills and low mountains and 27%in the middle and high mountains.The comparison with remote sensing cropland data shows that the grid cells with absolute differences of 0–10%accounted for 70.35%of all grid cells,while grids with differences exceeding 60%accounted for only 0.83%.This finding indicates that the reconstruction method is feasible,and the reconstruction results objectively reveal the historical spatiotemporal changes in cropland.

Ang-(1-7)exerts anti-inflammatory and antioxidant activities on high glucose-induced injury by prohibiting NF-κB-IL-1βand activating HO-1 pathways in HUVECs

Previous reports have suggested that Ang-(1-7)may have a protective effect in endothelial cells against high glucose(HG)-induced cell injury thanks to a modulatory mechanism in the NF-κB signaling pathway.In this study,we have examined whether NF-κB-IL-1βand Heme oxygenase-1(HO-1)pathways contribute to the protection of Ang-(1-7)against hyperglycemia-induced inflammation and oxidative stress in human umbilical vein endothelial cells(HUVECs).Our results indicate that time-varying exposures of HUVECs,from 1 h to 24 h,to high glucose concentrations result in an increased expression of phosphorylated(p)-p65 and HO-1 in a time-dependent manner.As an inhibitor of NF-κB,pyrrolidinedithiocarbamic acid(PDTC)suppressed IL-1βproduction induced by HG.Of note,HUVECs previously treated with Ang-(1-7)(2μM)for 30 min before being exposed to HG concentrations significantly ameliorated the HG-increased in p-p65 and IL-1βexpression;whereas obviously up-regulated the level of HO-1,along with inhibition of oxidative stress,inflammation,and the HG-induced cytotoxicity.Importantly,when HUVECs were previously treated either with PDTC or IL-1Ra for 30 min before being exposed to HG,it significantly prevented damages caused by high glucose concentrations mentioned above,while the treatment of HO-1 inhibitor Sn-protoporphyrin(SnPP)before exposure to both HG and Ang-(1-7)significantly blocked the protective effect exerted by Ang-(1-7)on endothelial cells against injuries induced by HG mentioned above.To conclude,the data of this study showed that activation and inhibition of the NF-κB-IL-1βpathway and HO-1 pathway may constitute an important defense mechanism against endothelial cell damage caused by HG concentrations.We additionally gave new evidence showing that exogenous Ang-(1-7)exerts a protective effect on HUVECs against the HG-induced cell injury via the inhibition and the activation of the NF-κB-IL-1βpathway and the HO-1 pathway,respectively.

Lactobacillus johnsonii N5 from heat stress-resistant pigs improves gut mucosal immunity and barrier in dextran sodium sulfate-induced colitis

Developing effective strategies to prevent diarrhea and associated-gut disorders in mammals has gained great significance.Owing to the many health benefits provided by the commensal microbiota of the intestinal tract,such as against environmental perturbation,we explored the host phenotype-associated microbes and their probiotic potential.Based on the observations that the chronic heat stress-exposed weaned piglets present as heat stress-susceptible(HS-SUS)or heat stress-resistant(HS-RES)individuals,we confirmed the phenotypic difference between the two on growth performance(P<0.05),diarrhea index(P<0.001),intestinal heat shock protein 70(HSP70)regulation(P<0.01),and inflammatory responses(P<0.01).By comparing the gut microbiome using 16S rRNA gene sequencing and KEGG functional analysis,we found that Lactobacillus johnsonii exhibited significantly higher relative abundance in the HS-RES piglets than in the HS-SUS ones(P<0.05).Further experiments using a mouse model for chemical-induced inflammation and intestinal injury demonstrated that oral administration of a representative L.johnsonii N5(isolated from the HS-RES piglets)ameliorated the clinical and histological signs of colitis while suppressing intestinal pro-inflammatory cytokines TNF-a and IL-6 production(P<0.05).We found that N5 treatment enhanced tight junction proteins ZO-1 and occludin and cytoprotective HSP70 levels under physiological condition and restored their mucosal expressions in colitis(P<0.05).In support of the high production of the anti-inflammatory cytokine IL-10,N5 promoted the intestinal Peyer’s patches MHCⅡ+and CD103+dendritic cell populations(P<0.05),increased the regulatory T(Treg)cell numbers(P<0.05),and decreased the Th17 population and its IL-17a production under physiological condition and during colitis(P<0.01).Our results shed light on understanding the interaction between commensal Lactobacillus and the host health,and provide L.johnsonii N5 as an alternative to antibiotics for preventing diarrhea and intestinal diseases.

A simple fluorescent sensor for highly sensitive detection of UO_(2)2+

Extensive application of nuclear energy has caused widespread environmental uranium contamination.New detection approaches without complicated sample pretreatment and precision instruments are in demand for on-site and in-time determination of uranyl ions in environmental monitoring, especially in an emergency situation. In this work, a simple and effective fluorescent sensor(Z)-N’-hydroxy-4-(1,2,2-triphenylvinyl)benzimidamide(TPE-A) with aggregation-induced emission(AIE) character was established and studied. It could realize to detect UO_(2)2+via quenching the fluorescence of its aggregation-induced emission, with good selectivity and sensitivity. Such strategy shows a wide linear range from 5.0 × 10^(-8)mol/L to 4.5 × 10^(-7)mol/L(R^(2)= 0.9988) with exceptional sensitivity reaching 4.7 × 10^(-9)mol/L, which is far below the limit for uranium in drinking water(30 μg/L, ca. 1.1 × 10-7mol/L) stipulated by the WHO.A response time less than four minutes make it rapid for uranyl ion measurement. It was applied for detection of uranyl ion in spiked river water samples with recoveries in the range of 98.7%-104.0%, comparable to those obtained by ICP-MS. With the advantages of portable apparatus, rapid detection process and high sensitivity, TPE-A can serve as a promising fluorescent sensor for the detection of UO_(2)2+in environmental water samples.

Electronic properties of monolayer copper selenide with one-dimensional moirépatterns

Strain engineering is a vital way to manipulate the electronic properties of two-dimensional(2D)materials.As a typical representative of transition metal mono-chalcogenides(TMMs),a honeycomb CuSe monolayer features with one-dimensional(1D)moirépatterns owing to the uniaxial strain along one of three equivalent orientations of Cu(111)substrates.Here,by combining low-temperature scanning tunneling microscopy/spectroscopy(STM/S)experiments and density functional theory(DFT)calculations,we systematically investigate the electronic properties of the strained CuSe monolayer on the Cu(111)substrate.Our results show the semiconducting feature of CuSe monolayer with a band gap of 1.28 eV and the 1D periodical modulation of electronic properties by the 1D moirépatterns.Except for the uniaxially strained CuSe monolayer,we observed domain boundary and line defects in the CuSe monolayer,where the biaxial-strain and strain-free conditions can be investigated respectively.STS measurements for the three different strain regions show that the first peak in conduction band will move downward with the increasing strain.DFT calculations based on the three CuSe atomic models with different strain inside reproduced the peak movement.The present findings not only enrich the fundamental comprehension toward the influence of strain on electronic properties at 2D limit,but also offer the benchmark for the development of 2D semiconductor materials.

Evaluating the accuracy of Chinese pasture data in global historical land use datasets

Global historical land use datasets are widely used in global environmental change studies; however, uncertainties in the included pasture data have not been evaluated. In this study, using trend, relative difference ratio(RDR), and spatial comparisons, we evaluated the accuracy of China pasture data in the HYDE(versions 3.1 and 3.2), SAGE, and PJ datasets using historical document-based reconstructions, including the land use datasets for China covering 1935–1997(hereafter Ge-dataset)and Northeast China covering the 1700 s–2000(hereafter Ye-dataset), and the satellite-based China's Land-Use/cover Datasets(CLUDs) for 1980–2015. Four important results were obtained.(1) China pasture area in the HYDE, SAGE, and PJ datasets and grassland area in the Ge-dataset, Ye-dataset, and CLUDs show both disparate trends and large differences in absolute values.(2)Spatially, 50.9%, 52.8%, and 63.0% pasture/grassland grids in 2000 had RDRs greater than 60% between HYDE3.1, HYDE3.2,and SAGE datasets, and CLUDs, respectively. The percentage of grids with RDRs less than 20% were 24.9%, 26.7%, and 16.0%,respectively.(3) Based on HYDE3.2, the spatial distribution of pasture in Northeast China over the last 300 year has expanded,which is in contrast to the results from the Ye-dataset, which shows the spatial distribution of grassland shrinking because of human reclamation activities.(4) The large contrasts between the global datasets and Chinese native datasets are due to differences in pasture/grassland definitions, land use practices, and spatial reconstruction methods.

Lattice mismatch in Ni_(3)Al-based alloy for efficient oxygen evolution

The Ni_(3)Al-based alloy has been considered as a robust catalyst for oxygen evolution reaction(OER)due to its long-term durability and acceptable activity.However,related reports about understanding the catalytic mechanism are rare and desirable.Herein,the effect of γ/γ’phase lattice mismatch on the catalytic performance caused by various cooling rates after solution heat treatment was investigated.With decreasing cooling rate,the morphologies of γ' precipitates transformed from sphere to cube and the lattice mismatch increased from-0.172%to-0.409%.The increased lattice mismatch facilitated the formation of the active β-NiOOH phase and enhanced the intrinsic catalytic activity,resulting in the optimized OER overpotential of 240 mV at a current density of 10 mA cm^(−2) with a Tafel slope of 66.1 mV dec^(−1) and a stability of 200 h in 1 M KOH.This work reveals the lattice mismatch effect on OER and provides a potential candidate for OER.

Gridded reconstruction of the population in the traditional cultivated region of China from 1776 to 1953

Using modern census and environmental factor data,this study first identified the environmental factors that significantly affect the population distribution through Geodetector analysis and then constructed a population spatial distribution model based on the random forest regression algorithm.Finally,with this model and historical population data that were examined and corrected by historians,gridded population distributions with a spatial resolution of 10 km by 10 km in the traditional cultivated region of China(TCRC,hereafter)were reconstructed for six time slices from 1776 to 1953.Using the reconstruction dataset,the spatiotemporal characteristics of the population distribution were depicted.The results showed that(1)the environmental factors that significantly affected the population density differences among counties in the TCRC mainly consisted of elevation,slope,relief amplitude,distances to the nearest prefectural and provincial capitals,distance to the nearest river and the climatology moisture index.(2)Using the census data of 1934 counties in the TCRC in 2000 and the abovementioned environmental factor data,a random forest regression algorithm-based population spatial distribution model was constructed.Its determination coefficient(R^(2))is 0.81.In 88.4%of the counties(districts),the relative errors of the model predictions were less than 50%.(3)From 1776 to 1953,the total population in the study area showed an uptrend.Prior to 1851,the population increased mainly in the Yangtze River Delta.During this period,the number of grid cells in which the population densities were greater than 500 persons per km^(2) increased from 292 to 683.From 1851 to 1953,the population increased extensively across the study area.In the North China Plain and the Pearl River Delta,the number of grid cells in which the population densities were greater than 500 persons per km^(2) increased from 36 to 88 and from 4 to 35,respectively.The spatial clustering pattern of the population distribution varied temporally.The potential reasons included the shifts in economic development hot spots,traditional beliefs,wars,famine,and immigration policies.(4)Between our reconstructions and the HYDE dataset,there are large differences in the data sources,selected environmental factors and modeling methods.As a consequence,in comparison to our reconstructions,there were fewer populations in the eastern area and more populations in the western area from 1776 to 1851 and more populations in urban areas and fewer populations in rural areas after 1851 in the HYDE dataset.