ORIGINAL ARTICLE Artificial neural network (ANN), M5P-tree, and regression analyses to predict the early age compression strength of concrete modified with DBC-21 and VK-98 polymers Ahmed Mohammed 1 • Lajan Burhan 1 • Kawan Ghafor 1 • Warzer Sarwar 1 • Wael Mahmood 1 Received: 10 June 2020 / Accepted: 10 November 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020 Abstract In this study, the effect of two water-reducer polymers with smooth and rough surfaces on the workability, and the compression strength of concrete from an early age (1 day) up to 28 days of curing was investigated. The polymer contents used in this study varied from 0 to 0.25% (wt%). The initial ratio between water and cement ( w c ) was 60%, and it slowly reduced to 0.46 by increasing the polymer contents. The compression strength of concrete was increased significantly with increasing the polymer contents by 24–95% depending on the polymer type, polymer content, w c , and curing age. Because of a fiber net (netting) in the concrete when the polymers were added which leads to a decrease void between the particles, binding the cement particles, therefore, increased rapidly the viscosity for the fresh concrete and the compression strength of the hardened concrete. This study also aims to establish systematic multiscale models to predict the compression strength of concrete containing polymers and to be used by the construction projects with no theoretical restrictions. For that purpose, 88 concrete samples modified with two types of polymer (44 samples for each modification) has been tested, analyzed, and modeled. Linear, nonlinear regression, M5P-tree, and artificial neural network (ANN) approaches were used for the qualifications. In the modeling process, the most relevant parameters affect the strength of concrete, i.e., polymer incorporation ratio (0–0.25% of cement’s mass), water-to-cement ratio (0.46–0.6), and curing ages (1–28 days). Among the used approaches and based on the training data set, the model made based on the nonlinear regression, ANN, and M5P- tree models seem to be the most reliable models. The sensitivity investigation concludes that the curing time is the most dominating parameter for the prediction of the maximum stress (compression strength) of concrete with this dataset. Keywords Concrete Á Polymer contents Á Workability Á Compression strength Á Statistical assessment Á Modeling 1 Introduction Cement plays an adhesive role in binding materials used in construction projects. Cement is widely used in construc- tion and oil well cementing fields. Cement alone (neat) can be used as grouting, mortar and concrete processing, pipe joints, and foundation preparation [1]. Calcium (sand or clay), aluminum, and iron are the main raw materials for cement production. The chemical properties of the cement and its time change provide insight into the strength of the cement system and the chemical properties of cement [2–4]. A variety of byproduct products used in many comprehensive research trials to alter the properties of cement-based concrete such as slag, silica fume, fuel ash, husk ash, soil granulated furnace slag, and metakaolin [5–10]. Concrete is a construction material composed of cement, fine aggregates (sand), and coarse aggregates mixed with water, which with time hardens. Portland cement is the commonly used type of cement for concrete production. Concrete technology deals with the study of concrete properties and its practical applications. Concrete is used in building construction to create floors, columns, beams, slabs, and other load-bearing components [11–15]. The polymer is one of the chemical admixtures used to improve the properties of fresh and hardened concrete & Ahmed Mohammed ahmed.mohammed@univsul.edu.iq 1 College of Engineering, Civil Engineering Department, University of Sulaimani, Sulaymaniyah, Iraq 123 Neural Computing and Applications https://doi.org/10.1007/s00521-020-05525-y