# Modeling p′p and recent LHC pp total cross-sections

Research output: Contribution to journalArticle

New technique is presented for modeling total cross-section of both pp and $\bar{p}p$ collisions from low to ultra high energy regions using an efficient artificial neural network (ANN). We have used the input (center-of-mass energy, √s, and type of particle P) and output (total cross-section σtot) data to build a prediction model by ANN. The neural network has been trained to produce a function that studies the dependence of σtot on √s and P. The trained ANN model shows a good performance in matching the trained distributions, predicts cross-sections that are not presented in the training set. The general trend of the predicted values shows a good agreement with the recent Large Hadron Collider (LHC) measurements, where the total cross-section at √s = 7∼{\rm TeV}$and 8 TeV are measured to be 98.6 mb and 101.7 mb, respectively. The predicted values of the total cross-section at √s = 10∼{\rm TeV} and 14 TeV are found to be 105.8 mb and 111.7 mb, respectively. Those predictions are in good agreement with Block, Cudell and Nakamura. Original language English 1450044 Modern Physics Letters A 29 8 https://doi.org/10.1142/S0217732314500448 Published - Mar 14 2014 ### Fingerprint cross sections predictions center of mass education trends collisions energy output ### Keywords • artificial neural networks. • Hadronic collisions • pp collisions • p′p collisions • total cross-section ### ASJC Scopus subject areas • Nuclear and High Energy Physics • Astronomy and Astrophysics ### Cite this Modeling p′p and recent LHC pp total cross-sections. / Radi, Amr; El-Khateeb, Esraa. In: Modern Physics Letters A, Vol. 29, No. 8, 1450044, 14.03.2014. Research output: Contribution to journalArticle @article{0095d87d4412456f9330bbd2bba263b0, title = "Modeling p′p and recent LHC pp total cross-sections", abstract = "New technique is presented for modeling total cross-section of both pp and$\bar{p}p$collisions from low to ultra high energy regions using an efficient artificial neural network (ANN). We have used the input (center-of-mass energy, √s, and type of particle P) and output (total cross-section σtot) data to build a prediction model by ANN. The neural network has been trained to produce a function that studies the dependence of σtot on √s and P. The trained ANN model shows a good performance in matching the trained distributions, predicts cross-sections that are not presented in the training set. The general trend of the predicted values shows a good agreement with the recent Large Hadron Collider (LHC) measurements, where the total cross-section at √s = 7∼{\rm TeV}$ and 8 TeV are measured to be 98.6 mb and 101.7 mb, respectively. The predicted values of the total cross-section at √s = 10∼{\rm TeV} and 14 TeV are found to be 105.8 mb and 111.7 mb, respectively. Those predictions are in good agreement with Block, Cudell and Nakamura.",
keywords = "artificial neural networks., Hadronic collisions, pp collisions, p′p collisions, total cross-section",
author = "Amr Radi and Esraa El-Khateeb",
year = "2014",
month = "3",
day = "14",
doi = "10.1142/S0217732314500448",
language = "English",
volume = "29",
journal = "Modern Physics Letters A",
issn = "0217-7323",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "8",

}

TY - JOUR

T1 - Modeling p′p and recent LHC pp total cross-sections

AU - El-Khateeb, Esraa

PY - 2014/3/14

Y1 - 2014/3/14

N2 - New technique is presented for modeling total cross-section of both pp and $\bar{p}p$ collisions from low to ultra high energy regions using an efficient artificial neural network (ANN). We have used the input (center-of-mass energy, √s, and type of particle P) and output (total cross-section σtot) data to build a prediction model by ANN. The neural network has been trained to produce a function that studies the dependence of σtot on √s and P. The trained ANN model shows a good performance in matching the trained distributions, predicts cross-sections that are not presented in the training set. The general trend of the predicted values shows a good agreement with the recent Large Hadron Collider (LHC) measurements, where the total cross-section at √s = 7∼{\rm TeV}$and 8 TeV are measured to be 98.6 mb and 101.7 mb, respectively. The predicted values of the total cross-section at √s = 10∼{\rm TeV} and 14 TeV are found to be 105.8 mb and 111.7 mb, respectively. Those predictions are in good agreement with Block, Cudell and Nakamura. AB - New technique is presented for modeling total cross-section of both pp and$\bar{p}p$collisions from low to ultra high energy regions using an efficient artificial neural network (ANN). We have used the input (center-of-mass energy, √s, and type of particle P) and output (total cross-section σtot) data to build a prediction model by ANN. The neural network has been trained to produce a function that studies the dependence of σtot on √s and P. The trained ANN model shows a good performance in matching the trained distributions, predicts cross-sections that are not presented in the training set. The general trend of the predicted values shows a good agreement with the recent Large Hadron Collider (LHC) measurements, where the total cross-section at √s = 7∼{\rm TeV}$ and 8 TeV are measured to be 98.6 mb and 101.7 mb, respectively. The predicted values of the total cross-section at √s = 10∼{\rm TeV} and 14 TeV are found to be 105.8 mb and 111.7 mb, respectively. Those predictions are in good agreement with Block, Cudell and Nakamura.

KW - artificial neural networks.

KW - pp collisions

KW - p′p collisions

KW - total cross-section

UR - http://www.scopus.com/inward/record.url?scp=84897115551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897115551&partnerID=8YFLogxK

U2 - 10.1142/S0217732314500448

DO - 10.1142/S0217732314500448

M3 - Article

AN - SCOPUS:84897115551

VL - 29

JO - Modern Physics Letters A

JF - Modern Physics Letters A

SN - 0217-7323

IS - 8

M1 - 1450044

ER -