Classification of rocks radionuclide data using machine learning techniques     

Abdul Razzaq Khan  Adil Aslam Mir  Sharjil Saeed  Muhammad Rafique  Khawaja M. Asim  Talat Iqbal  Abdul Jabbar  Saeed Ur Rahman 《Acta Geophysica》2018,66(5):1073-1079

The aim of this study is to assess the performance of linear discriminate analysis, support vector machines (SVMs) with linear and radial basis, classification and regression trees and random forest (RF) in the classification of radionuclide data obtained from three different types of rocks. Radionuclide data were obtained for metamorphic, sedimentary and igneous rocks using gamma spectroscopic method. A P-type high-purity germanium detector was used for the radiometric study. For analysis purpose, we have determined activity concentrations of ²³²Th, ²²⁶Ra and ⁴⁰K radionuclides, published elsewhere (Rafique et al. in Russ Geol Geophys 55:1073–1082, 2014), in different rock samples and built the classification model after pre-processing the data using three times tenfold cross-validation. Using this model, we have classified the new samples into known categories of sedimentary, igneous and metamorphic. The statistics depicts that RF and SVM with radial kernel outperform as compared to other classification methods in terms of error rate, area under the curve and with respect to other performance measures.  相似文献   

Seismic activity prediction using computational intelligence techniques in northern Pakistan     

Khawaja M. Asim  Muhammad Awais  F. Martínez–Álvarez  Talat Iqbal 《Acta Geophysica》2017,65(5):919-930

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar’s statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.  相似文献   

Periodic orbits generated by Lagrangian solutions of the restricted three body problem when one of the primaries is an oblate body     

Amit Mittal  Iqbal Ahmad  K. B. Bhatnagar 《Astrophysics and Space Science》2009,319(1):63-73

We have studied periodic orbits generated by Lagrangian solutions of the restricted three body problem when one of the primaries is an oblate body. We have determined the periodic orbits for different values of μ, h and A (h is energy constant, μ is mass ratio of the two primaries and A is an oblateness factor). These orbits have been determined by giving displacements along the tangent and normal to the mobile coordinates as defined by Karimov and Sokolsky (Celest. Mech. 46:335, 1989). These orbits have been drawn by using the predictor-corrector method. We have also studied the effect of oblateness by taking some fixed values of μ, A and h. As starters for our method, we use some known periodic orbits in the classical restricted three body problem.  相似文献   

Enhanced MEMS-IMU/odometer/GPS integration using mixture particle filter   总被引：2，自引：2，他引：0  

Jacques Georgy  Tashfeen Karamat  Umar Iqbal  Aboelmagd Noureldin 《GPS Solutions》2011,15(3):239-252

Dead reckoning techniques such as inertial navigation and odometry are integrated with GPS to avoid interruption of navigation solutions due to lack of visible satellites. A common method to achieve a low-cost navigation solution for land vehicles is to use a MEMS-based inertial measurement unit (IMU) for integration with GPS. This integration is traditionally accomplished by means of a Kalman filter (KF). Due to the significant inherent errors of MEMS inertial sensors and their time-varying changes, which are difficult to model, severe position error growth happens during GPS outages. The positional accuracy provided by the KF is limited by its linearized models. A Particle filter (PF), being a nonlinear technique, can accommodate for arbitrary inertial sensor characteristics and motion dynamics. An enhanced version of the PF, called Mixture PF, is employed in this paper. It samples from both the prior importance density and the observation likelihood, leading to an improved performance. Furthermore, in order to enhance the performance of MEMS-based IMU/GPS integration during GPS outages, the use of pitch and roll calculated from the longitudinal and transversal accelerometers together with the odometer data as a measurement update is proposed in this paper. These updates aid the IMU and limit the positional error growth caused by two horizontal gyroscopes, which are a major source of error during GPS outages. The performance of the proposed method is examined on road trajectories, and results are compared to the three different KF-based solutions. The proposed Mixture PF with velocity, pitch, and roll updates outperformed all the other solutions and exhibited an average improvement of approximately 64% over KF with the same updates, about 85% over KF with velocity updates only, and around 95% over KF without any updates during GPS outages.  相似文献   

Flood risk assessment of River Indus of Pakistan   总被引：1，自引：1，他引：0  

Bushra Khan  Muhammad Jawed Iqbal  M. Ayub Khan Yosufzai 《Arabian Journal of Geosciences》2011,4(1-2):115-122

Annual flood peak discharges is widely used in risk assessment. Major sources of flooding in Pakistan are River Jhelum, River Chenab, River Kabul, and upper and lower parts of River Indus. These rivers are major tributaries of the River Indus System which is one of the most important systems of the world and the greatest system of Pakistan. River Indus is the longest river of Pakistan containing seven gauge stations and several barrages, and it plays a vital role in the irrigation system and power generation for the country. This paper estimates the risk of flood in River Indus using historical data of maximum peak discharges. On the basis of our analysis, we find out which dam/barrage reservoir need to be updated in capacity, and whether there are more dams/barrages needed.  相似文献   

Spectral analysis of local climatic fluctuations   总被引：1，自引：1，他引：0  

Muhammad J. Iqbal  J. Quamar  M. A. K. Yousufzai 《Arabian Journal of Geosciences》2011,4(1-2):291-298

This paper employs spectral analysis to detect regular cyclical patterns or periodicities of local climate parameters of five major cities of Pakistan. Our calculations show that the temperature of all major climate stations may be affected by ENSO or QBO or Sunspot Cycles. As for the rainfall, what we find is that Pakistan summer monsoon exhibits a fairly similar bienniality with that of the Indian monsoon.  相似文献   

Comparison of rockfall susceptibility assessment at local and regional scale: a case study in the north of Beijing (China)     

Xueliang Wang  Luqing Zhang  Jixin Ding  Qingfeng Meng  Javed Iqbal  Lihui Li  Zhifa Yang 《Environmental Earth Sciences》2014,72(11):4639-4652

This study shows a rockfall susceptibility assessment at local scale in north Beijing of China, including the identification of rockfall sources onsite by terrain and rock discontinuities analysis and run-out distance prediction by Rocfall^? simulation. Two types of rockfall were defined including one type on the cliffs with long inclined slopes and another type on the road slopes with low height. Two historical rockfall events were used to back-calibrating the parameters used for run-out distance simulation. Based on the work, rockfall susceptibility map at local scale was created in GIS, which was compared with the map obtained at regional scale (entire Huairou district scale). Due to the difference of approaches applied, procedure of assessment and types of source data acquired, the two resulting rockfall susceptibility maps are proved to be different. Still, both of them are useful and could be used at different level’s decision for rockfall prevention and mitigation. Different types of uncertainties exist in the study of rockfall susceptibility assessment. To reduce the uncertainties, studies on both approaches and techniques are suggested.  相似文献   

Erratum to: The inner ramp facies of the Thanetian Lockhart Formation,western Salt Range,Indus Basin,Pakistan     

Muhammad Hanif  Muhammad Imraz  Fahad Ali  Muhammad Haneef  Abdus Saboor  Shahid Iqbal  Sajjad Ahmad Jr 《Arabian Journal of Geosciences》2014,7(11):4927-4932

  相似文献   

Adaptive state estimation of groundwater contaminant boundary input flux in a 2-dimensional aquifer     

Muhammad Nauman Malik  Mehdi Murtuza  Iqbal Asif  Bakar Muhammad Saifullah Abu  Brahim Aissa  Dk Nur Afiqah Jalwati Puteri  Amer Farhan Rafique 《地下水科学与工程》2014,7(4):373-382

In many circumstances involving heat and mass transfer issues, it is considered impractical to measure the input flux and the resulting state distribution in the domain. Therefore, the need to develop techniques to provide solutions for such problems and estimate the inverse mass flux becomes imperative. Adaptive state estimator (ASE) is increasingly becoming a popular inverse estimation technique which resolves inverse problems by incorporating the semi-Markovian concept into a Bayesian estimation technique, thereby developing an inverse input and state estimator consisting of a bank of parallel adaptively weighted Kalman filters. The ASE is particularly designed for a system that encompasses independent unknowns and /or random switching of input and measurement biases. The present study describes the scheme to estimate the groundwater input contaminant flux and its transient distribution in a conjectural two-dimensional aquifer by means of ASE, which in particular is because of its unique ability to efficiently handle the process noise giving an estimation of keeping the relative error range within 10% in 2-dimensional problems. Numerical simulation results show that the proposed estimator presents decent estimation performance for both smoothly and abruptly varying input flux scenarios. Results also show that ASE enjoys a better estimation performance than its competitor, Recursive Least Square Estimator (RLSE) due to its larger error tolerance in greater process noise regimes. ASE’s inherent deficiency of being slower than the RLSE, resulting from the complexity of algorithm, was also noticed. The chosen input scenarios are tested to calculate the effect of input area and both estimators show improved results with an increase in input flux area especially as sensors are moved closer to the assumed input location.  相似文献   

Short‐term variability in isotopic composition of precipitation: A case study from the Midwestern United States     

M. Z. Iqbal 《水文研究》2008,22(23):4609-4619

Oxygen and deuterium isotopes in precipitation were analysed to define local isotopic trends in Iowa, US. The area is far inland from an oceanic source and the observed averages of δ¹⁸O and δ D are ? 6·43‰ and ? 41·35‰ for Ames, ? 7·53‰ and ? 51·33‰ for Cedar Falls, and ? 6·01‰ and ? 38·19‰ for Iowa City, respectively. Although these data generally follow global trends, they are different when compared to a semi‐arid mid‐continental location in North Platt, Nebraska. The local meteoric water lines of Iowa are δ D = 7·68 δ¹⁸O + 8·0 for Ames, δ D = 7·62 δ¹⁸O + 6·07 for Cedar Falls, and δ D = 7·78 δ¹⁸O + 8·61 for Iowa City. The current Iowa study compares well with a study conducted in Ames, Iowa, 10 years earlier. The differences between Iowa and Nebraska studies are attributed to a variable climate across the northern Great Plains ranging from sub‐humid in the east to semi‐arid in the west. Iowa being further east in the region is more strongly influenced by a moist sub‐humid to humid climate fed by the tropical air stream from the Gulf of Mexico. The average d‐excess values are 10·06‰ for Ames, 8·92‰ for Cedar Falls and 9·92‰ for Iowa City. Eighty seven percent of the samples are within the global d‐excess range of 0‰ and 20‰. The results are similar to previous studies, including those by National Atmospheric Deposition Programs and International Atomic Energy Agency. It appears that the impact of recycled water or secondary evaporation on δ¹⁸O values of area precipitation is minimal. Copyright © 2008 John Wiley & Sons, Ltd.  相似文献