Corrosion resistance and anti-soiling performance of micro-arc oxidation/graphene oxide/stearic acid superhydrophobic composite coating on magnesium alloys

Magnesium(Mg)alloys,the lightest metal construction material used in industry,play a vital role in future development.However,the poor corrosion resistance of Mg alloys in corrosion environments largely limits their potential wide applications.Therefore,a micro-arc oxidation/graphene oxide/stearic acid(MAO/GO/SA)superhydrophobic composite coating with superior corrosion resistance was fabricated on a Mg alloy AZ91D through micro-arc oxidation(MAO)technology,electrodeposition technique,and self-assembly technology.The composition and microstructure of the coating were characterized by scanning electron microscopy,X-ray diffraction,energy dispersive spectroscopy,and Raman spectroscopy.The effective protection of the MAO/GO/SA composite coating applied to a substrate was evaluated using potentiodynamic polarization,electrochemical impedance spectroscopy tests,and salt spray tests.The results showed that the MAO/GO/SA composite coating with a petal spherical structure had the best superhydrophobicity,and it attained a contact angle of 159.53°±2°.The MAO/GO/SA composite coating exhibited high resistance to corrosion,according to electrochemical and salt spray tests.

Evaluation of Corrosion Degradation Law of Recycled Reinforced Concrete in Saline Soil Under Electrified Environment

In order to investigate the corrosion mechanism of recycled reinforced concrete (RRC) under harsh environments,four recycled coarse aggregate (RCA) contents were selected,and saline soil was used as an electrolyte to perform electrified accelerated corrosion experiments.The relative dynamic elastic modulus and relative corrosion current density were considered to describe the deterioration law of the RRC in saline soil.The results indicated that as the energization time increased,the corrosion current density,corrosion potential,and polarization resistance of the steel bar decreased gradually.Compared with ordinary reinforced concrete,when the RCA content was 30%,the ability of the RRC to resist corrosion was improved slightly;however,when the RCA content exceeded 30%,the corrosion resistance of the RRC deteriorated rapidly.Scanning electron microscopy revealed that for a dense RRC,less corrosion products were generated in the pores inside the concrete and on the surface of the steel bar.X-ray diffraction results indicated that SO_(4)^(2-) can generate ettringite and other corrosion products,along with volume expansion.The main corrosion products generated on the surface of the steel bars included Fe_(2)O_(3),Fe_(3)O_(4) and FeO(OH),which were the corrosion products generated by steel bars under natural environments.Therefore,using saline soil as an electrolyte is more consistent with the actual service environments of RRC.Both the relative dynamic mode and relative corrosion current density of the degradation parameters conform to the Weibull distribution;furthermore,the relative dynamic mode is more sensitive and the corresponding reliability curve can better describe the degradation law of RRC under saline soil environments.

Prediction model for corrosion rate of low-alloy steels under atmospheric conditions using machine learning algorithms

This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.

High corrosion and wear resistant electroless Ni–P gradient coatings on aviation aluminum alloy parts

A Ni–P alloy gradient coating consisting of multiple electroless Ni–P layers with various phosphorus contents was prepared on the aviation aluminum alloy. Several characterization and electrochemical techniques were used to characterize the different Ni–P coatings’ morphologies, phase structures, elemental compositions, and corrosion protection. The gradient coating showed good adhesion and high corrosion and wear resistance, enabling the application of aluminum alloy in harsh environments. The results showed that the double zinc immersion was vital in obtaining excellent adhesion (81.2 N). The optimal coating was not peeled and shredded even after bending tests with angles higher than 90°and was not corroded visually after 500 h of neutral salt spray test at 35℃. The high corrosion resistance was attributed to the misaligning of these micro defects in the three different nickel alloy layers and the amorphous structure of the high P content in the outer layer. These findings guide the exploration of functional gradient coatings that meet the high application requirement of aluminum alloy parts in complicated and harsh aviation environments.

A dynamic soil freezing characteristic curve model for frozen soil

The soil freezing characteristic curve(SFCC)plays a fundamental role in comprehending thermohydraulic behavior and numerical simulation of frozen soil.This study proposes a dynamic model to uniformly express SFCCs amidst varying total water contents throughout the freezing-thawing process.Firstly,a general model is proposed,wherein the unfrozen water content at arbitrary temperature is determined as the lesser of the current total water content and the reference value derived from saturated SFCC.The dynamic performance of this model is verified through test data.Subsequently,in accordance with electric double layer(EDL)theory,the theoretical residual and minimum temperatures in SFCC are calculated to be-14.5℃to-20℃for clay particles and-260℃,respectively.To ensure that the SFCC curve ends at minimum temperature,a correction function is introduced into the general model.Furthermore,a simplified dynamic model is proposed and investigated,necessitating only three parameters inherited from the general model.Additionally,both general and simplified models are evaluated based on a test database and proven to fit the test data exactly across the entire temperature range.Typical recommended parameter values for various types of soils are summarized.Overall,this study provides not only a theoretical basis for most empirical equations but also proposes a new and more general equation to describe the SFCC.

Prediction models of burst strength degradation for casing with considerations of both wear and corrosion

Casing wear and casing corrosion are serious problems affecting casing integrity failure in deep and ultra-deep wells.This paper aims to predict the casing burst strength with considerations of both wear and corrosion.Firstly,the crescent wear shape is simplified into three categories according to common mathematical models.Then,based on the mechano-electrochemical(M-E)interaction,the prediction model of corrosion depth is built with worn depth as the initial condition,and the prediction models of burst strength of the worn casing and corroded casing are obtained.Secondly,the accuracy of different prediction models is validated by numerical simulation,and the main influence factors on casing strength are obtained.At last,the theoretical models are applied to an ultra-deep well in Northwest China,and the dangerous well sections caused by wear and corrosion are predicted,and the corrosion rate threshold to ensure the safety of casing is obtained.The results show that the existence of wear defects results in a stress concentration and enhanced M-E interaction on corrosion depth growth.The accuracy of different mathematical models is different:the slot ring model is most accurate for predicting corrosion depth,and the eccentric model is most accurate for predicting the burst strength of corroded casing.The burst strength of the casing will be overestimated by more than one-third if the M-E interaction is neglected,so the coupling effect of wear and corrosion should be sufficiently considered in casing integrity evaluation.

New insights on the high-corrosion resistance of UHP Mg-Ge alloys tested in a simulated physiological environment

UHP Mg-Ge alloys was recently found to provide excellent corrosion resistance.This paper provides new insights on the mechanism of improved corrosion resistance of UHP Mg-Ge alloys in Hanks’solution.The studied UHP Mg-0.5Ge and UHP Mg-1Ge alloys showed superior corrosion resistance compared to UHP Mg and WE43,with the Mg-1Ge exhibiting the best corrosion performance.The exceptional corrosion resistance of the UHP alloy is attributed to(i)Mg_(2)Ge’s ability to suppress cathodic kinetics,(ii)Ge’s capability to accelerate the formation of a highly passive layer,and the(iii)low amounts of corrosion-accelerating impurities.

An ionic liquid-assisted strategy for enhanced anticorrosion of low-energy PEO coatings on magnesium–lithium alloy

A low-energy plasma electrolytic oxidation(LePEO)technique is developed to simultaneously improve energy efficiency and anti-corrosion.Ionic liquids(1-butyl-3-methylimidazole tetrafluoroborate(BmimBF_(4)))as sustainable corrosion inhibitors are chosen to investigate the corrosion inhibition behavior of ionic liquid(ILs)during the LePEO process for LA91 magnesium-lithium(Mg-Li)alloy.Results show that the ionic liquid BmimBF_(4)participates in the LePEO coating formation process,causing an increment in coating thickness and surface roughness.The low conductivity of the ionic liquid is responsible for the voltage and breakdown voltage increases during the LePEO with IL process(LePEO-IL).After adding BmimBF_(4),corrosion current density decreases from 1.159×10^(−4)A·cm^(−2)to 8.143×10^(−6)A·cm^(−2).The impedance modulus increases to 1.048×10^(4)Ω·cm^(−2)and neutral salt spray remains intact for 24 h.The superior corrosion resistance of the LePEO coating assisted by ionic liquid could be mainly attributed to its compact and thick barrier layer and physical absorption of ionic liquid.The ionic liquid-assisted LePEO technique provides a promising approach to reducing energy consumption and improving film performance.

Straw return increases crop production by improving soil organic carbon sequestration and soil aggregation in a long-term wheat-cotton cropping system

Straw return is a promising strategy for managing soil organic carbon(SOC)and improving yield stability.However,the optimal straw return strategy for sustainable crop production in the wheat(Triticum aestivum L.)-cotton(Gossypium hirsutum L.)cropping system remains uncertain.The objective of this study was to quantify the long-term(10 years)impact of carbon(C)input on SOC sequestration,soil aggregation and crop yields in a wheat-cotton cropping system in the Yangtze River Valley,China.Five treatments were arranged with a single-factor randomized design as follows:no straw return(Control),return of wheat straw only(Wt),return of cotton straw only(Ct),return of 50%wheat and 50%cotton straw(Wh-Ch)and return of 100%wheat and 100%cotton straw(Wt-Ct).In comparison to the Control,the SOC content increased by 8.4 to 20.2%under straw return.A significant linear positive correlation between SOC sequestration and C input(1.42-7.19 Mg ha^(−1)yr^(−1))(P<0.05)was detected.The percentages of aggregates of sizes>2 and 1-2 mm at the 0-20 cm soil depth were also significantly elevated under straw return,with the greatest increase of the aggregate stability in the Wt-Ct treatment(28.1%).The average wheat yields increased by 12.4-36.0%and cotton yields increased by 29.4-73.7%,and significantly linear positive correlations were also detected between C input and the yields of wheat and cotton.The average sustainable yield index(SYI)reached a maximum value of 0.69 when the C input was 7.08 Mg ha^(−1)yr^(−1),which was close to the maximum value(SYI of 0.69,C input of 7.19 Mg ha^(−1)yr^(-1))in the Wt-Ct treatment.Overall,the return of both wheat and cotton straw was the best strategy for improving SOC sequestration,soil aggregation,yields and their sustainability in the wheat-cotton rotation system.

Microstructures,corrosion behavior and mechanical properties of as-cast Mg-6Zn-2X(Fe/Cu/Ni)alloys for plugging tool applications

Mg-6Zn-2X(Fe/Cu/Ni)alloys were prepared through semi-continuous casting,with the aim of identifying a degradable magnesium(Mg)alloy suitable for use in fracturing balls.A comparative analysis was conducted to assess the impacts of adding Cu and Ni,which result in finer grains and the formation of galvanic corrosion sites.Scanner electronic microscopy examination revealed that precipitated phases concentrated at grain boundaries,forming a semi-continuous network structure that facilitated corrosion penetration in Mg-6Zn-2Cu and Mg-6Zn-2Ni alloys.Pitting corrosion was observed in Mg-6Zn-2Fe,while galvanic corrosion was identified as the primary mechanism in Mg-6Zn-2Cu and Mg-6Zn-2Ni alloys.Among the tests,the Mg-6Zn-2Ni alloy exhibited the highest corrosion rate(approximately 932.9 mm/a)due to its significant potential difference.Mechanical testing showed that Mg-6Zn-2Ni alloy possessed suitable ultimate compressive strength,making it a potential candidate material for degradable fracturing balls,effectively addressing the challenges of balancing strength and degradation rate in fracturing applications.

Corrosion and in vitro cytocompatibility investigation on the designed Mg-Zn-Ag metallic glasses for biomedical application

In the present work,seven Mg-Zn-Ag alloys with the nominal composition of Mg_(96-x)Zn_(x)Ag_(4)(x=17,20,23,26,29,32,35 in at.%)were prepared by induction melting and single-roller melt-spinning.The X-ray diffraction(XRD)analyses indicate the metallic glasses with three composition of Mg_(73)Zn_(23)Ag_(4),Mg_(70)Zn_(26)Ag_(4),and Mg_(67)Zn_(29)Ag_(4)were obtained successfully.The differential scanning calorimetry(DSC)measurement was used to obtain the characteristic temperature of Mg-Zn-Ag metallic glasses for the glass-forming ability analysis.The maximum glass transition temperature(Trg)was found to be 0.525 with a composition close to Mg_(67)Zn_(29)Ag_(4),which results in the best glass-forming ability.Moreover,the immersion test in simulated body fluid(SBF)demonstrate the relative homogeneous corrosion behavior of the Mg-Zn-Ag metallic glasses.The corrosion rate of Mg-Zn-Ag metallic glasses in SBF solution decreases with the increase of Zn content.The sample Mg_(67)Zn_(29)Ag_(4)has the lowest corrosion rate of 0.19mm/yr,which could meet the clinical application requirement well.The in vitro cell experiments show that the Madin-Darby canine kidney(MDCK)cells cultured in sample Mg_(67)Zn_(29)Ag_(4)and its extraction medium have higher activity.However,the Mg-Zn-Ag metallic glasses exhibit obvious inhibitory effect on human rhabdomyosarcoma(RD)tumor cells.The present investigations on the glass-forming ability,corrosion behavior,cytocompatibility and tumor inhibition function of the Mg-Zn-Ag based metallic glass could reveal their biomedical application possibility.

Assessment of soil erosion in the Irga watershed on the eastern edge of the Chota Nagpur Plateau,India

Human activities to improve the quality of life have accelerated the natural rate of soil erosion.In turn,these natural disasters have taken a great impact on humans.Human activities,particularly the conversion of vegetated land into agricultural land and built-up area,stand out as primary contributors to soil erosion.The present study investigated the risk of soil erosion in the Irga watershed located on the eastern fringe of the Chota Nagpur Plateau in Jharkhand,India,which is dominated by sandy loam and sandy clay loam soil with low soil organic carbon(SOC)content.The study used the Revised Universal Soil Loss Equation(RUSLE)and Geographical Information System(GIS)technique to determine the rate of soil erosion.The five parameters(rainfall-runoff erosivity(R)factor,soil erodibility(K)factor,slope length and steepness(LS)factor,cover-management(C)factor,and support practice(P)factor)of the RUSLE were applied to present a more accurate distribution characteristic of soil erosion in the Irga watershed.The result shows that the R factor is positively correlated with rainfall and follows the same distribution pattern as the rainfall.The K factor values in the northern part of the study area are relatively low,while they are relatively high in the southern part.The mean value of the LS factor is 2.74,which is low due to the flat terrain of the Irga watershed.There is a negative linear correlation between Normalized Difference Vegetation Index(NDVI)and the C factor,and the high values of the C factor are observed in places with low NDVI.The mean value of the P factor is 0.210,with a range from 0.000 to 1.000.After calculating all parameters,we obtained the average soil erosion rate of 1.43 t/(hm^(2)•a),with the highest rate reaching as high as 32.71 t/(hm^(2)•a).Therefore,the study area faces a low risk of soil erosion.However,preventative measures are essential to avoid future damage to productive and constructive activities caused by soil erosion.This study also identifies the spatial distribution of soil erosion rate,which will help policy-makers to implement targeted soil erosion control measures.

Effect of icosahedral phase formation on the stress corrosion cracking(SCC)behaviors of the as-cast Mg-8%Li(in wt.%)based alloys

Through exploring the stress corrosion cracking(SCC)behaviors of the as-cast Mg-8%Li and Mg-8%Li-6%Zn-1.2%Y alloys in a 0.1 M NaCl solution,it revealed that the SCC susceptibility index(I_(SCC))of the Mg-8%Li alloy was 47%,whilst the I_(SCC)of the Mg-8%Li-6%Zn-1.2%Y alloy was 68%.Surface,cross-sectional and fractography observations indicated that for the Mg-8%Li alloy,theα-Mg/β-Li interfaces acted as the preferential crack initiation sites and propagation paths during the SCC process.With regard to the Mg-8%Li-6%Zn-1.2%Y alloy,the crack initiation sites included the I-phase and the interfaces of I-phase/β-Li andα-Mg/β-Li,and the preferential propagation paths were the I-phase/β-Li andα-Mg/β-Li interfaces.Moreover,the SCC of the two alloys was concerned with hydrogen embrittlement(HE)mechanism.

High-throughput calculations combining machine learning to investigate the corrosion properties of binary Mg alloys

Magnesium(Mg)alloys have shown great prospects as both structural and biomedical materials,while poor corrosion resistance limits their further application.In this work,to avoid the time-consuming and laborious experiment trial,a high-throughput computational strategy based on first-principles calculations is designed for screening corrosion-resistant binary Mg alloy with intermetallics,from both the thermodynamic and kinetic perspectives.The stable binary Mg intermetallics with low equilibrium potential difference with respect to the Mg matrix are firstly identified.Then,the hydrogen adsorption energies on the surfaces of these Mg intermetallics are calculated,and the corrosion exchange current density is further calculated by a hydrogen evolution reaction(HER)kinetic model.Several intermetallics,e.g.Y_(3)Mg,Y_(2)Mg and La_(5)Mg,are identified to be promising intermetallics which might effectively hinder the cathodic HER.Furthermore,machine learning(ML)models are developed to predict Mg intermetallics with proper hydrogen adsorption energy employing work function(W_(f))and weighted first ionization energy(WFIE).The generalization of the ML models is tested on five new binary Mg intermetallics with the average root mean square error(RMSE)of 0.11 eV.This study not only predicts some promising binary Mg intermetallics which may suppress the galvanic corrosion,but also provides a high-throughput screening strategy and ML models for the design of corrosion-resistant alloy,which can be extended to ternary Mg alloys or other alloy systems.

Stress-assisted corrosion mechanism of 3Ni steel by using gradient boosting decision tree machining learning method

Traditional 3Ni weathering steel cannot completely meet the requirements for offshore engineering development,resulting in the design of novel 3Ni steel with the addition of microalloy elements such as Mn or Nb for strength enhancement becoming a trend.The stress-assisted corrosion behavior of a novel designed high-strength 3Ni steel was investigated in the current study using the corrosion big data method.The information on the corrosion process was recorded using the galvanic corrosion current monitoring method.The gradi-ent boosting decision tree(GBDT)machine learning method was used to mine the corrosion mechanism,and the importance of the struc-ture factor was investigated.Field exposure tests were conducted to verify the calculated results using the GBDT method.Results indic-ated that the GBDT method can be effectively used to study the influence of structural factors on the corrosion process of 3Ni steel.Dif-ferent mechanisms for the addition of Mn and Cu to the stress-assisted corrosion of 3Ni steel suggested that Mn and Cu have no obvious effect on the corrosion rate of non-stressed 3Ni steel during the early stage of corrosion.When the corrosion reached a stable state,the in-crease in Mn element content increased the corrosion rate of 3Ni steel,while Cu reduced this rate.In the presence of stress,the increase in Mn element content and Cu addition can inhibit the corrosion process.The corrosion law of outdoor-exposed 3Ni steel is consistent with the law based on corrosion big data technology,verifying the reliability of the big data evaluation method and data prediction model selection.

Corrosion behavior of pure metals(Ni and Ti)and alloys(316H SS and GH3535)in liquid GaInSn

In this study,the interactions between a Ga-based liquid metal,GaInSn,and several metal materials,including pure metals(Ni and Ti)and alloys(316H stainless steel(SS)and GH3535),at 650℃were investigated.The aim was to evaluate the corrosion performance and select a suitable candidate material for use as a molten salt manometer diaphragm in thermal energy storage systems.The results indicated that the alloys(316H SS and GH3535)exhibited less corrosion than pure metals(Ni and Ti)in liquid GaInSn.Ga-rich binary intermetallic compounds were found to form on the surfaces of all the tested metal materials exposed to liquid GaInSn,as a result of the decomposition of liquid GaInSn and its reaction with the constituent elements of the metal materials.The corrosion mechanism for all the tested materials exposed to liquid GaInSn was also investigated and proposed,which may aid in selecting the optimal candidate material when liquid GaInSn is used as the pressure-sensing medium.

Review on synergistic damage effect of irradiation and corrosion on reactor structural alloys

The synergistic damage effect of irradiation and corrosion of reactor structural materials has been a prominent research focus.This paper provides a comprehensive review of the synergistic effects on the third-and fourth-generation fission nuclear energy structural materials used in pressurized water reactors and molten salt reactors.The competitive mechanisms of multiple influencing factors,such as the irradiation dose,corrosion type,and environmental temperature,are summarized in this paper.Conceptual approaches are proposed to alleviate the synergistic damage caused by irradiation and corrosion,thereby promoting in-depth research in the future and solving this key challenge for the structural materials used in reactors.

Manure substitution improves maize yield by promoting soil fertility and mediating the microbial community in lime concretion black soil

Synthetic nitrogen(N)fertilizer has made a great contribution to the improvement of soil fertility and productivity,but excessive application of synthetic N fertilizer may cause agroecosystem risks,such as soil acidification,groundwater contamination and biodiversity reduction.Meanwhile,organic substitution has received increasing attention for its ecologically and environmentally friendly and productivity benefits.However,the linkages between manure substitution,crop yield and the underlying microbial mechanisms remain uncertain.To bridge this gap,a three-year field experiment was conducted with five fertilization regimes:i)Control,non-fertilization;CF,conventional synthetic fertilizer application;CF_(1/2)M_(1/2),1/2 N input via synthetic fertilizer and 1/2 N input via manure;CF_(1/4)M_(3/4),1/4 N input synthetic fertilizer and 3/4 N input via manure;M,manure application.All fertilization treatments were designed to have equal N input.Our results showed that all manure substituted treatments achieved high soil fertility indexes(SFI)and productivities by increasing the soil organic carbon(SOC),total N(TN)and available phosphorus(AP)concentrations,and by altering the bacterial community diversity and composition compared with CF.SOC,AP,and the soil C:N ratio were mainly responsible for microbial community variations.The co-occurrence network revealed that SOC and AP had strong positive associations with Rhodospirillales and Burkholderiales,while TN and C:N ratio had positive and negative associations with Micromonosporaceae,respectively.These specific taxa are implicated in soil macroelement turnover.Random Forest analysis predicted that both biotic(bacterial composition and Micromonosporaceae)and abiotic(AP,SOC,SFI,and TN)factors had significant effects on crop yield.The present work strengthens our understanding of the effects of manure substitution on crop yield and provides theoretical support for optimizing fertilization strategies.

Greatly enhanced corrosion/wear resistances of epoxy coating for Mg alloy through a synergistic effect between functionalized graphene and insulated blocking layer

The poor corrosion and wear resistances of Mg alloys seriously limit their potential applications in various industries.The conventional epoxy coating easily forms many intrinsic defects during the solidification process,which cannot provide sufficient protection.In the current study,we design a double-layer epoxy composite coating on Mg alloy with enhanced anti-corrosion/wear properties,via the spin-assisted assembly technique.The outer layer is functionalized graphene(FG)in waterborne epoxy resin(WEP)and the inner layer is Ce-based conversion(Ce)film.The FG sheets can be homogeneously dispersed within the epoxy matrix to fill the intrinsic defects and improve the barrier capability.The Ce film connects the outer layer with the substrate,showing the transition effect.The corrosion rate of Ce/WEP/FG composite coating is 2131 times lower than that of bare Mg alloy,and the wear rate is decreased by~90%.The improved corrosion resistance is attributed to the labyrinth effect(hindering the penetration of corrosive medium)and the obstruction of galvanic coupling behavior.The synergistic effect derived from the FG sheet and blocking layer exhibits great potential in realizing the improvement of multi-functional integration,which will open up a new avenue for the development of novel composite protection coatings of Mg alloys.

Enhancing Deep Learning Soil Moisture Forecasting Models by Integrating Physics-based Models

Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient representation of land-surface processes.In addition to PB models,deep learning(DL)models have been widely used in SM predictions recently.However,few pure DL models have notably high success rates due to lacking physical information.Thus,we developed hybrid models to effectively integrate the outputs of PB models into DL models to improve SM predictions.To this end,we first developed a hybrid model based on the attention mechanism to take advantage of PB models at each forecast time scale(attention model).We further built an ensemble model that combined the advantages of different hybrid schemes(ensemble model).We utilized SM forecasts from the Global Forecast System to enhance the convolutional long short-term memory(ConvLSTM)model for 1–16 days of SM predictions.The performances of the proposed hybrid models were investigated and compared with two existing hybrid models.The results showed that the attention model could leverage benefits of PB models and achieved the best predictability of drought events among the different hybrid models.Moreover,the ensemble model performed best among all hybrid models at all forecast time scales and different soil conditions.It is highlighted that the ensemble model outperformed the pure DL model over 79.5%of in situ stations for 16-day predictions.These findings suggest that our proposed hybrid models can adequately exploit the benefits of PB model outputs to aid DL models in making SM predictions.