TY - GEN

T1 - Evaluation of the Models of Copper Spatial Distribution in the Surface Layer of the Soil Based on Artificial Neural Networks by the Permutation Method

AU - Sergeev, Aleksandr

AU - Butorova, Anastasia

AU - Shichkin, Andrey

AU - Buevich, Alexander

AU - Baglaeva, Elena

AU - Subbotina, Irina

AU - Sergeeva, Marina

N1 - The research funding from the Ministry of Science and Higher Education of the Russian Federation (Ural Federal University Program of Development within the Priority-2030 Program) is gratefully acknowledged.

PY - 2024

Y1 - 2024

N2 - The paper introduces an original permutation approach to assessment of the predictive ability of models based on artificial neural networks. Three models based on artificial neural networks (a multilayer perceptron, a network with the radial basis function, and a neural network with the generalized regression) were implemented to illustrate the permutation approach. Data on the spatial distribution of copper in the upper soil layer of Novy Urengoy (Yamalo-Nenets Autonomous Okrug, Russia) were used for modeling. To evaluate the performance of the models, three different methods were used: error indices estimation, a graphical approach (the Taylor diagram), and a randomization estimation of the probability of obtaining the divergence between the observed and predicted series under assumption that both these datasets are taken from the same population. In the permutation approach, two statistics were used: the difference in means and the correlation coefficient. The permutation approach proved to be productive, as it allowed assessing the significance of the divergence between the observed and predicted datasets.

AB - The paper introduces an original permutation approach to assessment of the predictive ability of models based on artificial neural networks. Three models based on artificial neural networks (a multilayer perceptron, a network with the radial basis function, and a neural network with the generalized regression) were implemented to illustrate the permutation approach. Data on the spatial distribution of copper in the upper soil layer of Novy Urengoy (Yamalo-Nenets Autonomous Okrug, Russia) were used for modeling. To evaluate the performance of the models, three different methods were used: error indices estimation, a graphical approach (the Taylor diagram), and a randomization estimation of the probability of obtaining the divergence between the observed and predicted series under assumption that both these datasets are taken from the same population. In the permutation approach, two statistics were used: the difference in means and the correlation coefficient. The permutation approach proved to be productive, as it allowed assessing the significance of the divergence between the observed and predicted datasets.

UR - http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85196489093

U2 - 10.1063/5.0210522

DO - 10.1063/5.0210522

M3 - Conference contribution

SN - 978-073544954-1

VL - 3094

T3 - AIP Conference Proceedings

BT - AIP Conference Proceedings

PB - American Institute of Physics Inc.

T2 - International Conference of Numerical Analysis and Applied Mathematics 2022, ICNAAM 2022

Y2 - 19 September 2022 through 25 September 2022

ER -