In this work, artificial intelligence is achieved using a genetic algorithm integrated with an artificial neuron network (GANN) to find the optimal combination of natural leaves on ZrO2 architecture anodes for water splitting devices and hydrogen evolution. Around 180 kinds of Aglaonema and 100 kinds of Codiaeum variegatum are evaluated from nine kinds of original Aglaonema and five kinds of Codiaeum variegatum over 10 generations of hybridization, respectively. The types and content of natural chlorophyll and anthocyanin are estimated and recorded by CMOS devices and an absorption spectrum for pixel recording and featured parameter mining for GANN. Optical extinction ZrO2 architecture anodes constructed on ITO substrates, which correspond with a leaf’s pigments, demonstrated ultrahigh water splitting performance for hydrogen evolution up to 9.42%. Furthermore, from promising experimental results, the natural pigments extracted from different color parts of Codiaeum variegatum and Aglaonema demonstrated over 85% incident photon to electron conversion efficiency while the pigments correspond with the lowest optical extinction ZrO2 architecture anodes. Ultrahigh current density (157.1 A/m2) and hydrogen evolution quality (around 18 mol after 6 h) are obtained when the lowest optical extinction ZrO2 architecture anodes correspond with green parts of Aglaonema under one sun irradiation.