Development of ensemble learning models to evaluate the strength of coal-grout materials

In the loose and fractured coal seam with particularly low uniaxial compressive strength(UCS),driving a roadway is extremely difficult as roof falling and wall spalling occur frequently.To address this issue,the jet grouting(JG)technique(high-pressure grout mixed with coal particles)was first introduced in this study to improve the self-supporting ability of coal mass.To evaluate the strength of the jet-grouted coal-grout composite(JG composite),the UCS evolution patterns were analyzed by preparing 405 specimens combining the influential variables of grout types,curing time,and coal to grout(C/G)ratio.Furthermore,the relationships between UCS and these influencing variables were modeled using ensemble learning methods i.e.gradient boosted regression tree(GBRT)and random forest(RF)with their hyperparameters tuned by the particle swarm optimization(PSO).The results showed that the chemical grout composite has higher short-term strength,while the cement grout composite can achieve more stable strength in the long term.The PSO-GBRT and PSO-RF models can both achieve high prediction accuracy.Also,the variable importance analysis demonstrated that the grout type and curing time should be considered carefully.This study provides a robust intelligent model for predicting UCS of JG composites,which boosts JG design in the field.

Data-driven methods for predicting the representative temperature of bridge cable based on limited measured data

Cable-stayed bridges have been widely used in high-speed railway infrastructure.The accurate determination of cable’s representative temperatures is vital during the intricate processes of design,construction,and maintenance of cable-stayed bridges.However,the representative temperatures of stayed cables are not specified in the existing design codes.To address this issue,this study investigates the distribution of the cable temperature and determinates its representative temperature.First,an experimental investigation,spanning over a period of one year,was carried out near the bridge site to obtain the temperature data.According to the statistical analysis of the measured data,it reveals that the temperature distribution is generally uniform along the cable cross-section without significant temperature gradient.Then,based on the limited data,the Monte Carlo,the gradient boosted regression trees(GBRT),and univariate linear regression(ULR)methods are employed to predict the cable’s representative temperature throughout the service life.These methods effectively overcome the limitations of insufficient monitoring data and accurately predict the representative temperature of the cables.However,each method has its own advantages and limitations in terms of applicability and accuracy.A comprehensive evaluation of the performance of these methods is conducted,and practical recommendations are provided for their application.The proposed methods and representative temperatures provide a good basis for the operation and maintenance of in-service long-span cable-stayed bridges.

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling,people are accustomed to taking and uploading photos on social media websites,which has led to the accumulation of huge numbers of geotagged photos.Combined with multisource information(e.g.weather,transportation,or textual information),these geotagged photos could help us in constructing user preference profiles at a high level of detail.Therefore,using these geotagged photos,we built a personalised recommendation system to provide attraction recommendations that match a user’s preferences.Specifically,we retrieved a geotagged photo collection from the public API for Flickr(Flickr.com)and fetched a large amount of other contextual information to rebuild a user’s travel history.We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation(the matching process)and candidate ranking.In the matching process,we used a support vector machine model that was modified for multiclass classification to generate the candidate list.In addition,we used a gradient boosting regression tree to score each candidate and rerank the list.Finally,we evaluated our recommendation results with respect to accuracy and ranking ability.Compared with widely used memory-based methods,our proposed method performs significantly better in the cold-start situation and when mining‘long-tail’data.

Machine learning-based prediction of soil compression modulus with application of ID settlement

The compression modulus(Es)is one of the most significant soil parameters that affects the compressive deformation of geotechnical systems,such as foundations.However,it is difficult and sometime costly to obtain this parameter in engineering practice.In this study,we aimed to develop a non-parametric ensemble artificial intelligence(AI)approach to calculate the Es of soft clay in contrast to the traditional regression models proposed in previous studies.A gradient boosted regression tree(GBRT)algorithm was used to discern the non-linear pattern between input variables and the target response,while a genetic algorithm(GA)was adopted for tuning the GBRT model's hyper-parameters.The model was tested through 10-fold cross validation.A dataset of 221 samples from 65 engineering survey reports from Shanghai infrastructure projects was constructed to evaluate the accuracy of the new model5 s predictions.The mean squared error and correlation coefficient of the optimum GBRT model applied to the testing set were 0.13 and 0.91,respectively,indicating that the proposed machine learning(ML)model has great potential to improve the prediction of Es for soft clay.A comparison of the performance of empirical formulas and the proposed ML method for predicting foundation settlement indicated the rationality of the proposed ML model and its applicability to the compressive deformation of geotechnical systems.This model,however,cannot be directly applied to the prediction of Es in other sites due to its site specificity.This problem can be solved by retraining the model using local data.This study provides a useful reference for future multi-parameter prediction of soil behavior.

Development of machine learning multi-city model for municipal solid waste generation prediction

Integrated management of municipal solid waste(MSW)is a major environmental challenge encountered by many countries.To support waste treatment/management and national macroeconomic policy development,it is essential to develop a prediction model.With this motivation,a database of MSW generation and feature variables covering 130 cities across China is constructed.Based on the database,advanced machine learning(gradient boost regression tree)algorithm is adopted to build the waste generation prediction model,i.e.,WGMod.In the model development process,the main influencing factors on MSW generation are identified by weight analysis.The selected key influencing factors are annual precipitation,population density and annual mean temperature with the weights of 13%,11%and 10%,respectively.The WGMod shows good performance with R^(2)=0.939.Model prediction on MSW generation in Beijing and Shenzhen indicates that waste generation in Beijing would increase gradually in the next 3–5 years,while that in Shenzhen would grow rapidly in the next 3 years.The difference between the two is predominately driven by the different trends of population growth.

Comparison and correction of IDW based wind speed interpolation methods in urbanized Shenzhen

Based on the 2-min average wind speed observations at 100 automatic weather stations in Shenzhen from January 2008 to December 2018,this study tries to explore the ways to improve wind interpolation quality over the Shenzhen region.Three IDW based methods,i.e.,traditional inverse distance weight(IDW),modified inverse distance weight(MIDW),and gradient inverse distance weight(GIDW)are used to interpolate the near surface wind field in Shenzhen.In addition,the gradient boosted regression trees(GBRT)model is used to correct the wind interpolation results based on the three IDW based methods.The results show that among the three methods,GIDW has better interpolation effects than the other two in the case of stratified sampling.The MSE and R2 for the GIDW’s in different months are in the range of 1.096-1.605 m/s and 0.340-0.419,respectively.However,in the case of leave-one-group-out crossvalidation,GIDW has no advantage over the other two methods.For the stratified sampling,GBRT effectively corrects the interpolated results by the three IDW based methods.MSE decreases to the range of 0.778-0.923 m/s,and R2 increases to the range of 0.530-0.671.In the nonstation area,the correction effect of GBRT is still robust,even though the elevation frequency distribution of the non-station area is different from that of the stations’area.The correction performance of GBRT mainly comes from its consideration of the nonlinear relationship between wind speed and the elevation,and the combination of historical and current observation data.