Enhancing dimensional stability in cement pastes: a machine learning approach with metaheuristic-optimized categorical boosting

Abstract Low hydration activity and challenging management of delayed expansion restrict the application of fly ash $$\left(FA\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>F</mml:mi> <mml:mi>A</mml:mi> </mml:mfenced> </mml:math> and $$MgO$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>MgO</mml:mi> </mml:mrow> </mml:math> expansive additive $$\left(MEA\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>M</mml:mi> <mml:mi>E</mml:mi> <mml:mi>A</mml:mi> </mml:mfenced> </mml:math> in cement pastes. Very few research on machine learning techniques for volume expansion $$\left({V}_{e}\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:msub> <mml:mi>V</mml:mi> <mml:mi>e</mml:mi> </mml:msub> </mml:mfenced> </mml:math> in such systems have been conducted already. This study develops a machine learning framework to predict the volume expansion $$\left({V}_{e}\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:msub> <mml:mi>V</mml:mi> <mml:mi>e</mml:mi> </mml:msub> </mml:mfenced> </mml:math> of cement pastes incorporating fly ash $$\left(FA\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>F</mml:mi> <mml:mi>A</mml:mi> </mml:mfenced> </mml:math> and $$MgO$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>MgO</mml:mi> </mml:mrow> </mml:math> expansive additive $$\left(MEA\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>M</mml:mi> <mml:mi>E</mml:mi> <mml:mi>A</mml:mi> </mml:mfenced> </mml:math> , materials whose low hydration activity and delayed expansion complicate their practical use. A dataset of 170 samples compiled from published literature was utilized, comprising four input variables—Portland cement content ( $$PC$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>PC</mml:mi> </mml:mrow> </mml:math> , %), fly ash content ( $$FA$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>FA</mml:mi> </mml:mrow> </mml:math> , %), $$MgO$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>MgO</mml:mi> </mml:mrow> </mml:math> expansive additive ( $$MEA$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>MEA</mml:mi> </mml:mrow> </mml:math> , %), and curing age ( $$SA$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>SA</mml:mi> </mml:mrow> </mml:math> , days)—to predict the target variable, $${V}_{e}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mi>V</mml:mi> <mml:mi>e</mml:mi> </mml:msub> </mml:math> (%). A Categorical Boosting $$\left(CatBoost\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>C</mml:mi> <mml:mi>a</mml:mi> <mml:mi>t</mml:mi> <mml:mi>B</mml:mi> <mml:mi>o</mml:mi> <mml:mi>o</mml:mi> <mml:mi>s</mml:mi> <mml:mi>t</mml:mi> </mml:mfenced> </mml:math> model was optimized using two recent metaheuristic algorithms, the Starfish Optimization Algorithm $$\left(StOA\right)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mfenced> <mml:mi>S</mml:mi> <mml:mi>t</mml:mi> <mml:mi>O</mml:mi> <mml:mi>A</mml:mi> </mml:mfenced> </mml:math> </jats