The extraction yield of Juglans nigra L. leaves was assessed at different ethanol concentrations (0-96% (v/v)) and solvent-to-solid ratios (5-20 kg kg(-1)). The response surface methodology (RSM) and artificial neural network with genetic algorithms (ANN-GA) were developed to optimize the extraction variables. The RSM and ANN-GA models determined 50% (v/v) ethanol concentration and 20 kg kg(-1) solvent-to-solid ratio as optimal conditions, ensuring an extraction yield of 27.69 and 27.19 g 100 g(-1) of dry leaves. The phenolic compounds in optimal extract were quantified: 3-O-caffeoylquinic acid (2.27 mg g(-1)of dry leaves), quercetin-3-O-galactoside (10.99 mg g(-1) of dry leaves) and quercetin 3 0 rhamnoside (15.07 mg g(-1)of dry leaves) using high-performance liquid chromatography (HPLC). The minerals in optimal extract were quantified: macro-elements (the relative order by content was: K > Mg > Ca) using inductively coupled plasma optical emission spectrometry (ICP-OES) and micro-elements (the relative order by content was: Zn > Rb > Mn > I>Sr > Ni > Cu > Co > V > Ag > Se) using inductively coupled plasma mass spectrometry (ICP-MS). The extraction coefficients for minerals were determined and were highest for K (64.3%) and I (53.5%). Optimization of extraction process resulted in high extraction yield from J. nigra leaves and optimal extract containing different phytochemical compounds. (C) 2020 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.