International Journal of Engineering and Technology Innovation, vol. 13, no. 3, 2023, pp. 175-188 English language proofreader: Chih-Wen Teng Determination of the California Bearing Ratio of the Subgrade and Granular Base Using Artificial Neural Networks Jose Manuel Palomino Ojeda 1 , Billy Alexis Cayatopa Calderon 2 , Lenin Quiñones Huatangari 1,* , Wilmer Rojas Pintado 2 1 Instituto de Ciencia de Datos, Universidad Nacional de Jaen, Jaen, Peru 2 Instituto de Investigación en Sismológica y Construcción, Universidad Nacional de Jaen, Jaen, Peru Received 26 October 2022; received in revised form 27 February 2023; accepted 04 March 2023 DOI: https://doi.org/10.46604/ijeti.2023.11053 Abstract The objective of the research is to estimate the value of the California bearing ratio (CBR) through the application of ANN. The methodology consists of creating a database with soil index and CBR variables of the subgrades and granular base of pavements in Jaen, Peru, carried out in the soil mechanics laboratories of the city and the National University of Jaen. In addition, the Python library Seaborn is for variable selection and relevance, and the scikit-learn and Keras libraries were used for the learning, training, and validation stage. Five ANN are proposed to estimate the CBR value, obtaining an error of 4.47% in the validation stage. It can be concluded that this method is effective and valid to determine the CBR value in subgrades and granular bases of any pavement for its evaluation or design. Keywords: CBR, subgrade, soil, prediction, model 1. Introduction Peru has paved 17% of the 168,953.9 km of roads in the country, because in 2021 only Huanuco, Ancash, Junin, Piura, and San Martin experienced an increase of 10 km in their paving compared to Apurimac, Cajamarca, Pasco, and Moquegua that had a slight increase of 5.4 km. The government is investing in road works in the highlands, coast, and jungle, allowing connectivity between rural and urban areas, which boosts trade and the extraction of products to different parts of the country. By 2022, investments in pavements will exceed US$325 million [1]. In pavement construction, quality control is essential, and the bearing capacity of the subgrade, subbase, base, CBR values, and compaction characteristics should be properly evaluated [2]. The pavement is composed of layers of different thicknesses, and quality, which are supported on the subgrade. The layers that form the pavement structure are the subbase, base, and asphalt binder for flexible pavements, and the subbase and hydraulic concrete slab for rigid pavements [1]. However, in any type of pavement, the properties of the subgrade are determinant in the design and behavior of the structure. The subgrade can be constituted by the soil in its natural state or improved by mechanical, and chemical processes or using geosynthetics [3], being the important part of the pavement structure, which must be adequately compacted to maximize its strength while supporting loads of the previous pavement layers, as well as loads of moving traffic [4]. Pavement quality is tested by the California bearing ratio (CBR) test, which is a field/laboratory test used to determine the bearing strength of soil layers [5], is plotted using empirical curves, to establish the thickness of pavement and its component layers [6]. In the construction of pavements, earth dams, retaining wall backfills, and bridge abutments [7], civil * Corresponding author. E-mail address: lenin.quinones@unj.edu.pe