A hybrid machine learning optimization algorithm for multivariable pore pressure prediction

Pore pressure is essential data in drilling design,and its accurate prediction is necessary to ensure drilling safety and improve drilling efficiency.Traditional methods for predicting pore pressure are limited when forming particular structures and lithology.In this paper,a machine learning algorithm and effective stress theorem are used to establish the transformation model between rock physical parameters and pore pressure.This study collects data from three wells.Well 1 had 881 data sets for model training,and Wells 2 and 3 had 538 and 464 data sets for model testing.In this paper,support vector machine(SVM),random forest(RF),extreme gradient boosting(XGB),and multilayer perceptron(MLP)are selected as the machine learning algorithms for pore pressure modeling.In addition,this paper uses the grey wolf optimization(GWO)algorithm,particle swarm optimization(PSO)algorithm,sparrow search algorithm(SSA),and bat algorithm(BA)to establish a hybrid machine learning optimization algorithm,and proposes an improved grey wolf optimization(IGWO)algorithm.The IGWO-MLP model obtained the minimum root mean square error(RMSE)by using the 5-fold cross-validation method for the training data.For the pore pressure data in Well 2 and Well 3,the coefficients of determination(R^(2))of SVM,RF,XGB,and MLP are 0.9930 and 0.9446,0.9943 and 0.9472,0.9945 and 0.9488,0.9949 and 0.9574.MLP achieves optimal performance on both training and test data,and the MLP model shows a high degree of generalization.It indicates that the IGWO-MLP is an excellent predictor of pore pressure and can be used to predict pore pressure.

3D cluster members and near-infrared distance of open cluster NGC 6819

In order to obtain clean members of the open cluster NGC 6819, the proper motions and radial velocities of 1691 stars are used to construct a three-dimensional （3D） velocity space. Based on the DBSCAN clustering algorithm, 537 3D cluster members are obtained. From the 537 3D cluster members, the average radial velocity and absolute proper motion of the cluster are Vr = ＋2.30 ±0.04 km s-1 and （PMRA, PMDec） = （-2.5 ±0.5, -4.3 ± 0.5） mas yr-1, respectively. The proper motions, radial velocities, spatial positions and color-magnitude diagram of the 537 3D members indicate that our membership determination is effective. Among the 537 3D cluster members, 15 red clump giants can be easily identified by eye and are used as reliable standard candles for the distance estimate of the cluster. The distance modulus of the cluster is determined to be （m - M）0 -- 11.86 ± 0.05 mag （2355 ±54 pc）, which is quite consistent with published values. The uncertainty of our distance mod- ulus is dominated by the intrinsic dispersion in the luminosities of red clump giants （--0.04 mag）.

Discovery of high-velocity EHB stars in the globular cluster ωCentauri(NGC 5139)

Abstract We report the discovery of 45 high-velocity extreme horizontal branch （EHB） stars in the globular cluster Omega Centauri （NGC 5139）. The tangential ve- locities of these EHB stars are determined to be in the range 93-313 km s^-1, with an average uncertainty of -27 km s^-1. The central escape velocity of the cluster is determined to be in the range 60~105 km s^-1. These EHB stars are significantly more concentrated toward the cluster core compared with other cluster members. The formation mechanisms of these EHB stars are discussed. Our conclusions can be sum- marized as follows： （1） A comparison of the tangential velocities of these EHB stars to the central escape velocity of the cluster shows that most if not all of these EHB stars are unbound to the cluster; （2） These EHB stars obtained high velocities in the central cluster region no longer than - 1 Myr ago and may be subsequently ejected from the cluster in the next -1 Myr; （3） If the progenitors of these EHB stars were single stars, then they may have experienced a fast mass-loss process. If the progen- itors were in close binaries, then they may have formed through disruptions by the intermediate-mass black hole in the cluster center.