The design of geopolymer concrete must meet more stringent requirements for the landscape, so understanding and designing geopolymer concrete with a higher compressive strength challenging. In the performance prediction of geopolymer concrete compressive strength, machine learning models have the advantage of being more accurate and faster. However, only a single machine learning model is usually used at present, there are few applications of ensemble learning models, and model optimization processes is lacking. Therefore, this paper proposes to use the Firefly Algorithm (AF) as an optimization tool to perform hyperparameter tuning on Logistic Regression (LR), Multiple Logistic Regression (MLR), decision tree (DT), and Random Forest (RF) models. At the same time, the reliability and efficiency of four integrated learning models were analyzed. The model was used to analyze the influencing factors of geopolymer concrete and determine the strength of their influencing ability. According to the experimental data, the RF-AF model had the lowest RMSE value. The RMSE value of the training set and test set were 4.0364 and 8.7202, respectively. The R value of the training set and test set were 0.9774 and 0.8915, respectively. Therefore, compared with the other three models, RF-AF has a stronger generalization ability and higher prediction accuracy. In addition, the molar concentration of NaOH was the most important influencing factors, and its influence was far greater than the other possible factors including NaOH content. Therefore, it is necessary to pay more attention to NaOH molarity when designing geopolymer concrete.@en

As an environmentally responsible alternative to conventional concrete, geopolymer concrete recycles previously used resources to prepare the cementitious component of the product. The challenging issue with employing geopolymer concrete in the building business is the absence of a standard mix design. According to the chemical composition of its components, this work proposes a thorough system or framework for estimating the compressive strength of fly ash-based geopolymer concrete (FAGC). It could be possible to construct a system for predicting the compressive strength of FAGC using soft computing methods, thereby avoiding the requirement for time-consuming and expensive experimental tests. A complete database of 162 compressive strength datasets was gathered from the research papers that were published between the years 2000 and 2020 and prepared to develop proposed models. To address the relationships between inputs and output variables, long short-term memory networks were deployed. Notably, the proposed model was examined using several soft computing methods. The modeling process incorporated 17 variables that affect the CSFAG, such as percentage of SiO2 (SiO2), percentage of Na2O (Na2O), percentage of CaO (CaO), percentage of Al2O3 (Al2O3), percentage of Fe2O3 (Fe2O3), fly ash (FA), coarse aggregate (CAgg), fine aggregate (FAgg), Sodium Hydroxide solution (SH), Sodium Silicate solution (SS), extra water (EW), superplasticizer (SP), SH concentration, percentage of SiO2 in SS, percentage of Na2O in SS, curing time, curing temperature that the proposed model was examined to several soft computing methods such as multi-layer perception neural network (MLPNN), Bayesian regularized neural network (BRNN), generalized feed-forward neural networks (GFNN), support vector regression (SVR), decision tree (DT), random forest (RF), and LSTM. Three main innovations of this study are using the LSTM model for predicting FAGC, optimizing the LSTM model by a new evolutionary algorithm called the marine predators algorithm (MPA), and considering the six new inputs in the modeling process, such as aggregate to total mass ratio, fine aggregate to total aggregate mass ratio, FASiO2:Al2O3 molar ratio, FA SiO2:Fe2O3 molar ratio, AA Na2O:SiO2 molar ratio, and the sum of SiO2, Al2O3, and Fe2O3 percent in FA. The performance capacity of LSTM-MPA was evaluated with other artificial intelligence models. The results indicate that the R2 and RMSE values for the proposed LSTM-MPA model were as follows: MLPNN (R2 = 0.896, RMSE = 3.745), BRNN (R2 = 0.931, RMSE = 2.785), GFFNN (R2 = 0.926, RMSE = 2.926), SVR-L (R2 = 0.921, RMSE = 3.017), SVR-P (R2 = 0.920, RMSE = 3.291), SVR-S (R2 = 0.934, RMSE = 2.823), SVR-RBF (R2 = 0.916, RMSE = 3.114), DT (R2 = 0.934, RMSE = 2.711), RF (R2 = 0.938, RMSE = 2.892), LSTM (R2 = 0.9725, RMSE = 1.7816), LSTM-MPA (R2 = 0.9940, RMSE = 0.8332), and LSTM-PSO (R2 = 0.9804, RMSE = 1.5221). Therefore, the proposed LSTM-MPA model can be employed as a reliable and accurate model for predicting CSFAG. Noteworthy, the results demonstrated the significance and influence of fly ash and sodium silicate solution chemical compositions on the compressive strength of FAGC. These variables could adequately present variations in the best mix designs discovered in earlier investigations. The suggested approach may also save time and money by accurately estimating the compressive strength of FAGC with low calcium content. @en

Developed by Delft University of Technology, the tri-component polyurethane modified cold binder (PMCB) displays impressive durability and strength in asphalt mixtures, showing promise as a reliable binder for cold in-place recycling. However, when applying PMCB for rapid, in-situ recycling, the presence of moisture in reclaimed asphalt pavement (RAP) poses a significant challenge. To address this, an innovative approach involving treatment of the wet RAP with Calcium dioxide (CaO) prior to the integration of PMCB was tested. Evaluation methods used included the Indirect Tensile Test (ITT), followed by the calculation of the Indirect Tensile Strength Ratio (ITSR) to assess moisture susceptibility. Furthermore, Cantabro tests were performed to determine the material loss under abrasion and weathering conditions. These assessments underscored the feasibility of this approach. The treatment of wet RAP with CaO has proven a viable strategy for rapid in-situ recycling with PMCB, contributing to sustainable pavement construction. In addition, the research identified that a 5.5% concentration of the PMCB binder maximizes structural integrity and performance in the considered RAP.

@en

Bitumen fatigue resistance is critical to determine the overall fatigue performance and service life of asphalt pavements. However, the mechanisms responsible for fatigue damage of bitumen have previously not been well understood. Molecular dynamics (MD) simulation has recently emerged as a powerful computer-aided numerical technique to model the microscopic failure behaviours in materials. This study aims to use the MD method to investigate the molecular origin of bitumen fatigue damage. The molecular models of the virgin and aged PEN70/100 bitumen were firstly constructed based on their saturate, aromatic, resin and asphaltene (SARA) four fractions. An MD equilibrium was run on the developed bitumen models with the assigned interatomic potentials. Following an MD-based tensile simulation, a strain-controlled fatigue simulation was performed to study the nanostructure and damage behaviours of the virgin and aged bitumen under fatigue loading by calculating the stress-strain response, potential energy, molecular structure and nanovoid volumes. Furthermore, a rheometer measurement was also conducted to characterise the fatigue damage of the bitumen directly by a crack length at the macroscale. Results indicate that the bitumen molecules become unfolded and tend to align along the loading direction when fatigue loading was applied. The change in the molecular configuration helped the molecular chains move closer together and thus contributed to the reduction of the intermolecular interactions including the van der Waals and Coulombic energies. With the increasing load cycles, nanovoids were formed and grew in the bitumen through molecular rearrangement and movement, leading to microscopic fatigue damage of the bitumen. It was found that the aged bitumen produced more severe fatigue damage than the virgin bitumen, which was indicated by the MD-based nanovoid volume at the molecular scale and the DSR-based crack length at the macroscale. The findings from MD simulation provide a fundamental understanding of the molecular origin of fatigue damage, that cannot be experimentally detected for bitumen materials.@en

In this study, the environmentally friendly rejuvenators with waste thermal conductive oil, polymer, and the interfacial reinforcing agent were prepared. And the influence of the different rejuvenators on the rejuvenation mechanisms of aged SBS modified asphalt was characterized by different scales including the molecule structure, morphology, phase transition and interface adhesion characteristic, and macro performance. The results show that the thermal-oxidative aging process increases the molecular weight of asphalt, promotes the SBS phase to agglomerate, and decreases the high and low temperature performance, thermal stability, and adhesion. When the rejuvenator was added, the molecular weight distribution of asphalt binders can be improved, while adding the regenerant-II can supplement the SBS modifier and reform the cross-linking structure. Furthermore, the regenerant-II has a better recovery effect on the morphology structure and resumes the thermal behavior. And then softening point and ductility can be recovered by 89.7% and 94.8% of the original SBS modified asphalt. Under the action of the interfacial reinforcing agent, the regenerant-III could increase the adhesion work to 95.49% of the original SBS modified asphalt.

@en

This study aims to systematically investigate the influence of rejuvenator type/dosage and the aging degree of bitumen on the rutting resistance, flow behavior, and elastic/creep potential of rejuvenated bitumen at high temperatures. The rutting parameter (G*/sinδ), rutting failure temperature (RFT) from Linear viscoelastic test (LVE), zero-shear viscosity (ZSV) from flow test,
recovery percentage (R0.1, R3.2), creep compliance (Jnr0.1, Jnr3.2), and stress sensitivity parameters (Rdiff, Jnrslope) from multiple stress creep and recovery (MSCR) tests of rejuvenated bitumen are characterized. The results reveal that bio-oil rejuvenator weakens the high-temperature performance of aged bitumen maximally, followed by engine-oil and naphthenic-oil, while aromatic-oil
rejuvenated bitumen exhibits the best rutting, flow, and creep resistance. The RFT index can most effectively evaluate and differentiate the rejuvenation efficiency of various rejuvenators on the high-temperature performance, which correlates well with ZSV, R3.2, Jnr0.1, Jnr3.2, Rdiff, and Jnrslope indices. Therefore, the RFT index is recommended as the critical indicator for evaluating.
the high-temperature performance of rejuvenated binders. The flow and MSCR characteristics of rejuvenated bitumen can be predicted based on RFT values. The determination of critical indicators is beneficial to compare the rejuvenation effectiveness of variable rejuvenators on the high-temperature performance of aged bitumen. @en

This study investigates the impacts of rejuvenator type/dosage and the aging degree of bitumen on the chemical and rheological properties of rejuvenated bitumen, and propose critical chemo-rheological indicators for evaluating rejuvenation efficiency. Moreover, the potential connections between essential chemical and rheological indices of rejuvenator-aged bitumen blends are explored. Results indicate that chemical indices show linear relationships with rejuvenator dosage and vary depending on the rejuvenator type and aging level of bitumen. All rejuvenators can regenerate certain rheological parameters of aged bitumen to varying degrees, but cannot restore the crossover modulus (Gc). Various rheological indices exhibit different correlations with rejuvenator dosage and sensitivity degrees to the discrepancy in rejuvenator type and aging degree of bitumen. Critical chemical and rheological indicators are proposed based on their sensitivity levels to influence factors, with the aromaticity index (AI), carbonyl index (CI), and sulfoxide index (SI) as effective chemical indices and the complex modulus (G*), crossover frequency (fc), and high-temperature master curve area (AMH) as critical rheological indices for rejuvenation efficiency evaluation. The study finds that the magnitude of rejuvenation efficiency for four rejuvenators is Bio-oil > Engine-oil > Naphthenic-oil > Aromatic-oil, and the linear correlations between the critical chemical and rheological indices, together with their rejuvenation percentages, are significantly affected by the rejuvenator type and aging level of bitumen.@en

High-Content SBS Polymer Modified Asphalt Mixtures (HCPMA) combined with fibers have gained popularity in porous pavement construction due to their superior performance. Although the aging behavior of HCPMA has been extensively studied, the impact of fibers on performance and aging susceptibility remains unclear. This research investigates the influence of two representative fibers (lignin and polyester) on the raveling, cracking, fatigue, and rutting resistance of HCPMA before and after aging using Cantabro loss tests, SCB strength tests, SCB fatigue tests, and Hamburg Wheel-Tracking tests. The results indicate that in the original state, polyester fiber slightly enhances HCPMA performance, while lignin fiber shows limited or even adverse effects on cracking, raveling, fatigue, and rutting resistance. However, both fibers exhibit a more pronounced enhancement effect after short- and long-term aging. FTIR analysis reveals that fiber addition does not significantly impact bitumen oxidation and polymer degradation. The excellent properties of High-Content SBS Polymer Modified Bitumen (HCPMB) in the original state create a "masking" effect that conceals the enhancement effect of fibers, which becomes more evident after
long-term aging. Consequently, it is recommended that the performance evaluation and design of open-graded asphalt mixtures containing HCPMB be based on post-aging performance. @en

The film thickness of asphalt mixtures is critical for determining their performance and aging durability. However, understanding of the appropriate film thickness and its influence on performance and aging behavior for high-content polymer-modified asphalt (HCPMA) mixtures is still limited. This research aims to examine the relationship between film thickness, performance, and aging behavior of HCPMA mixtures in order to establish an optimal film thickness that ensures satisfactory performance and aging durability. HCPMA specimens with film thicknesses ranging from 6.9 μm to 17 μm were prepared using a 7.5% SBS-content-modified bitumen. Various tests, including Cantabro, SCB, SCB fatigue, and Hamburg wheel-tracking tests, were conducted to evaluate raveling, cracking, fatigue, and rutting resistance before and after aging. The key findings indicate that insufficient film thickness negatively affects aggregate bonding and performance, while excessive thickness reduces mixture stiffness and resistance to cracking and fatigue. A parabolic relationship between the aging index and film thickness was observed, suggesting that increasing film thickness improves aging durability up to a point, beyond which excessive thickness adversely impacts aging durability. The optimal film thickness for HCPMA mixtures, considering performance before and after aging and aging durability, falls within the 12.9 to 14.9 µm range. This range ensures the best balance between performance and aging durability, offering valuable insights for the pavement industry in designing and utilizing HCPMA mixtures.@en

This study aimed to explore the long-term aging influence on chemo rheological properties and develop novel consecutive models for the long-term aging reaction kinetics of bitumen. The results revealed that the aging index was significantly dependent on the types of selected parameters. The Zero-order model was suitable to describe the long-term aging reaction kinetics of bitumen based on the oxygen containing functional groups with the reaction rate constants in 0.7–3.3*10−4 (mol L−1·h−1). In the SARA-based consecutive reaction model, the most optimum kinetics model for aromatic fraction was the Third-order reaction model and the corresponding reaction kinetics constant (k1) was 0.02 (mol·L−1)−2(h)−1. The Zero-order model could well fit the generation kinetics of asphaltene molecules with the reaction rate constant k2 of 3.85*10−4 mol·(L·h)−1. Further, the transformation reaction from the resin to asphaltene molecules was the control step of the whole consecutive reaction model. In this study, when one-unit resin fraction was generated, the consumption amount of aromatic fraction was about 2.82 units. Meanwhile, when one-unit resin fraction was consumed, only 0.58-unit asphaltene could be generated. The developed reaction kinetics models could be beneficial to predict the functional groups distribution and SARA fractions in aged bitumen with different aging degrees.@en

The molecular dynamics (MD) simulation method is proved as an efficient tool to explore the intermolecular interaction between rejuvenators and aged bitumen, but the simple “singlemolecule” model of rejuvenator would bring the inaccuracy to simulation outputs due to a huge difference with its realistic multi-component chrematistic. This study aims to in-depth analyze the chemical components of four commonly-used rejuvenators with the Gas chromatographymass spectrometry (GC-MS) method, and propose their multi-component molecular models for the first time. Further, MD simulations are performed on the multi-component models of various rejuvenators to anticipate and compare their atomic-level properties. The GC-MS results reveal that the chemical components of petroleum-based rejuvenators are more complicated than the bio-oil (BO). The alkane, naphthenic, and aromatic molecules are the main constituents of engine-oil (EO), naphthenic-oil (NO), and aromatic-oil (AO) rejuvenators. The experimental density results validate the reliability of these multi-component molecular models of four rejuvenators. From the MD simulations outputs, there is a significant difference in the energetic indices, cohesive energy density (CED), solubility parameter δ, volumetric parameters, dynamic behaviors, structural indicators, expansion coefficient (α and β), and isobaric heat capacity (Cp) between the multi-component models of four rejuvenators. However,the multi-component molecular model of aromatic-oil based on the GC-MS method is not accurate because the polycyclic aromatic molecules with heavy-weight are not detected and considered. This study detects the difference in chemical components and thermodynamics properties between four rejuvenators and proposes their more realistic multi-component molecular models for further MD simulations on the rejuvenation of aged bitumen.@en

Compared with traditional asphalt, emulsified asphalt occurs to be a better low-temperature usability and environmental adaptability, which can reduce environmental pollution and energy consuming during road construction. The low-temperature ductility is a very important indicator to evaluate the environmental adaptability of emulsified asphalt. However, the relevance between microstructure and low-temperature ductility of modified asphalt is still rarely reported. Herein, we reported the first successful unfolding of the microscopic mechanism of ductility attenuation of the modified emulsified asphalt by combining experiments and characterization: Emulsifiers and additives had greater influence on the low-temperature ductility. Anionic and cationic emulsifiers had the similar ductility loss. Adding a non-ionic emulsifier OP-10 could be a solution to improve the ductility. The effect of the temperature change occurred less significant compared to the pH evolution of surfactant solution. The grey relation entropy (GRE) analysis revealed that the emulsifier structure (C/H ratio) would be the most important factor to affect the low-temperature ductility. The macro, micro and nano scales of modified emulsified asphalt were correlated, revealing in-depth that the aggregation and inter-chains interaction of styrene-butadiene-styrene (SBS) were the internal mechanism leading to the ductility loss. The change of glass transition temperature (Tg) was proposed to correlate the microstructural factor with the
ductility. Moreover, the combination of ductility test and bending beam rheometer (BBR) test could be an effective way to evaluate the low-temperature performance of asphalt.@en

Today, high-viscosity modified asphalt (HVMA) is widely used in drainage asphalt pavements. However, due to its high construction temperature, HVMA is prone to thermal oxidative aging, which reduces its life cycle and increases the maintenance costs of asphalt pavements. In this study, the effects of warm-mix additives on the physical, rheological and chemical properties of HVMA were studied to determine optimum warm-mix conditions. First, the effects of warm-mix technologies (foam warm mix, Sasobit, Evotherm, and GLWBR at 3%, 3%, 0.8%, and 0.8%, respectively) on the physical and rheological properties of HVMAwere studied. Then, two aging methods [thin film oven test (TFOT) and pressure aging vessel (PAV)] were applied to simulate the short-term and long-term thermal oxidation processes of HVMA and evaluate the influences of different warm-mix technologies on HVMA aging. The results showed that the four warm-mix technologies, especially foam warm mix and Sasobit, reduced the construction temperature of HVMA. In addition, warm-mix technologies also improved the high-temperature rheological properties of HVMA; however, they had adverse effects on the low-temperature cracking resistance of asphalt. Based on asphalt aging index fluctuations, it was evident that warm-mix technology was not conducive to the antiaging performance of HVMA, and foam warm mix had the weakest influence on the antiaging performance of high-viscosity asphalts. Furthermore, according to the results of an analysis of the carbonyl changes in aging asphalts, asphalt aging index can be applied to predicting the degree of aging of warm-mix HVMA.@en

High content rubber modified bitumen (HCRMB) prepared from the high content of waste tire rubber and bitumen has good performance while allowing greater use of the waste tires. However, HCRMB is subject to aging during use, which can affect its performance. The purpose of this paper was to investigate the effect of high content of waste tire rubber and sulfur on the aging behavior of bitumen. The properties of all bitumen were tested using rolling thin film oven aging (RTFOT) test, pressure aging vessel (PAV) test, frequency sweep tests, temperature sweep (TS) test, multiple stress creep recovery (MSCR) test, and attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) test. Test results show that the addition of sulfur to HCRMB leads to an improvement in the elasticity of HCRMB. The elasticity of HCRMB with different amounts of sulfur increases with aging. In addition, the increase in the amount of sulfur can improve the RTFOT aging resistance and the PAV aging resistance of HCRMB. Sulfur cannot reduce the degree of oxidation of HCRMB after aging, but can inhibit the degree of desulfurization of HCRMB. Furthermore, the aging process of HCRMB with different amounts of sulfur is dominated by the degradation of polybutadiene.

@en

Molecular dynamics (MD) simulation is an advanced tool to explore the interaction mechanism between aged bitumen and rejuvenators at the nanoscale. However, the general MD molecular structures of rejuvenators led to the lower quantify and inaccuracy of the simulation outputs. This study aims at developing more realistic molecular models to represent the generic rejuvenators for MD simulation of aged bitumen recycling. Four types of rejuvenators (bio-oil, engine-oil, naphthenic-oil, and aromatic-oil) are characterized in terms of element analysis, functional groups distribution observed from Attenuated total reflectance-Fourier-transform infrared (ATR-FTIR) spectroscopy, and average molecular weight. Afterward, the average molecular structures of rejuvenators are determined and validated. Further, the MD simulations are performed to predict the energetic, dynamic, volumetric,
and structural properties of various rejuvenators. Based on the chemical characteristics, the average chemical formula of bio-oil, engine-oil, naphthenic-oil, and aromatic-oil is derived as C19H36O2, C22H44, C26H48, C30H40. From MD simulations, the ranking of density and glass transition temperature for four different rejuvenators is AO > NO > BO > EO, which is same as the experimental results. It proves that the established average molecular structures of four rejuvenators are reasonable. Various rejuvenators display different thermodynamics and structural properties. The aromatic-oil exhibits the highest potential energy, cohesive energy density, and solubility parameter. Besides, the order of expansion coefficient and diffusion coefficient of the four rejuvenators is the same as BO > EO > NO > AO, while the viscosity presents the opposite sequence. Moreover, the fractional free volume values follow EO > BO > NO > AO. The occurrence probability between bio-oil and aromatic-oil molecules is higher than engine-oil and naphthenic-oil. This study develops the representative average molecular models for generic rejuvenators and helps understand the difference in chemo-physical and thermodynamics properties among various rejuvenators.@en

This study investigated the effects of swelling-degradation degree on the rheological properties and thermal pyrolysis behaviors of crumb rubber modified bitumen (CRMB). The equilibrium viscosity of CRMB in 160 ◦Cswelling process is 10.5 Pa·s at 8 h. During the 200℃-degradation procedure, the viscosity increased to a maximum value of 20.58 Pa·s at 7.5 h and gradually reduced to a stable value of 11.09 Pa·s after 35 h. The swelling and degradation processes exhibit the opposite influence on the rheological properties of CRMB. Moreover, the degradation process accelerated the pyrolysis rate of CRMB but hindered the release of toxic gas CO and hydrocarbons. @en

To further explore the long-term aging behaviors of bitumen from the multiscale perspectives, the experimental characterization and molecular dynamics (MD) simulation methods were performed. Series of chemical properties for the virgin and various aged bitumen were evaluated using the TCL-FID, ATR-FTIR, Elemental analysis and GPC tests. The molecular models of virgin and aged bitumen were established firstly, and the influence of long-term aging on the thermodynamics properties was predicted from the MD simulation results. The experimental results revealed that with the aging degree deepened, the resin and asphaltene fractions both increased dramatically, which resulted in the increment of average molecular weight and the more uneven molecular weight distribution in aged bitumen. Moreover, the aging of bitumen led to the increase of the oxidized functional groups (C=O and S=O) index, oxygen content, aromaticity and polarity, while the carbon, hydrogen element contents and the H/C ratio reduced. The density values from MD simulation agreed well with the experimental results, which significantly validated the reliability of molecular models for the virgin and different aged bitumen binders. The MD simulation results demonstrated that the long-term aging remarkably improved the cohesive energy density, solubility parameter and activation energy, however it deteriorated the surface free energy, work of cohesion and self-diffusion coefficient of the bitumen molecular system. This study develops the molecular models of virgin and aged bitumen with different long-term aging degrees, and provides a fundamental understanding regarding the influence of long-term aging influence on the chemo-physical and thermodynamic properties of bitumen.@en

Lignin, as a major waste from biofuel and paper industries, could be utilized as a modifier to enhance the relevant performance of bitumen. However, the effects of lignin on the thermodynamics properties and molecular structure of bitumen are rarely studied. Meanwhile, the potential modification mechanism of lignin modified bitumen is still unclear. Molecular dynamics (MD) simulation and laboratory experimental methods are combined to explore the influence of lignin on the thermodynamics characteristics, rheological properties as well as the molecular structure of bitumen. The lignin modified bitumen with different dosages of lignin (10, 20 and 30 wt%) were prepared. DSR results from a macroscale view reveal that lignin could significantly improve the modulus, elastic recovery and rutting resistance of bitumen, but it adversely affects the fatigue performance. Meanwhile, the MD simulation results from a microscale perspective show that lignin could increase the density, cohesive energy density, shear viscosity, modulus and adhesive strength of bitumen. However, the free volume, diffusion coefficient and self-healing ability of lignin modified bitumen are weakened with the increase of lignin dosage. The MD simulations results are consistent with the experimental data. Furthermore, the correlations between the microscale and macroscale properties of lignin modified bitumen indicate that the physical and rheological properties of bitumen both depend on the molecular structure dramatically. The findings of this research can provide insights for an in-depth understanding of the effect of lignin on bitumen.@en

It is well known that crumb rubber (CR) and styrene–butadienestyrene (SBS) composite modified asphalt has better rheological and engineering performance. However, it always presents very poor compatibility and storage stability. Meanwhile, Trans-polyoctenamer (TOR) can effectively improve the compatibility and thermal stability of rubber asphalt. Thus, this study aims to investigate the effectiveness of TOR on rheological properties, microstructure and thermal stability of CR/SBS modified asphalt. The results show that TOR has a significant influence on strengthening anti-rutting and temperature sensitivity of CR/SBS modified asphalt. However, TOR has a slightly negative influence on the anti-cracking ability for CR/SBS modified asphalt, which still maintains the critical low temperature requirement. Furthermore, TOR could be able to promote the conformation of cross-linked structure between polymer and asphalt, resulting in a significant enhancement in rheological properties and thermal stability of CR/SBS modified asphalt. Lastly, the effects of TOR on viscoelastic performance for modified asphalt markedly depend on the component of neat asphalt, and high asphaltene content is beneficial for improving the rheological behavior effects of TOR.@en