We apply four statistical learning methods to a sample of 7941 galaxies ( z < 0.06 ) from the Galaxy and Mass Assembly ( GAMA ) survey to test the feasibility of using automated algorithms to classify galaxies .
Using 10 features measured for each galaxy ( sizes , colours , shape parameters & stellar mass ) we apply the techniques of Support Vector Machines ( SVM ) , Classification Trees ( CT ) , Classification Trees with Random Forest ( CTRF ) and Neural Networks ( NN ) , returning True Prediction Ratios ( TPRs ) of 75.8 \% , 69.0 \% , 76.2 \% and 76.0 \% respectively .
Those occasions whereby all four algorithms agree with each other yet disagree with the visual classification ( ‘ unanimous disagreement ’ ) serves as a potential indicator of human error in classification , occurring in \sim 9 \% of ellipticals , \sim 9 \% of Little Blue Spheroids , \sim 14 \% of early-type spirals , \sim 21 \% of intermediate-type spirals and \sim 4 \% of late-type spirals & irregulars .
We observe that the choice of parameters rather than that of algorithms is more crucial in determining classification accuracy .
Due to its simplicity in formulation and implementation , we recommend the CTRF algorithm for classifying future galaxy datasets .
Adopting the CTRF algorithm , the TPRs of the 5 galaxy types are : E , 70.1 \% ; LBS , 75.6 \% ; S0-Sa , 63.6 \% ; Sab-Scd , 56.4 \% and Sd-Irr , 88.9 \% .
Further , we train a binary classifier using this CTRF algorithm that divides galaxies into spheroid-dominated ( E , LBS & S0-Sa ) and disk-dominated ( Sab-Scd & Sd-Irr ) , achieving an overall accuracy of 89.8 \% .
This translates into an accuracy of 84.9 \% for spheroid-dominated systems and 92.5 \% for disk-dominated systems .