HELIX: Data-driven characterization of Brazilian land snails

TL;DR

This paper presents a data-driven approach to characterize Brazilian land snails using morphometrical shell features, achieving high classification accuracy and revealing biological patterns useful for identification in cases where soft tissues are unavailable.

Contribution

Introduces a machine learning-based method for snail identification using shell morphometrical data, with insights into feature importance and biological variability.

Findings

Achieved up to 97.5% classification accuracy

Identified key morphometrical features for species differentiation

Revealed patterns related to climate and breeding traits

Abstract

Decision-support systems benefit from hidden patterns extracted from digital information. In the specific domain of gastropod characterization, morphometrical measurements support biologists in the identification of land snail specimens. Although snails can be easily identified by their excretory and reproductive systems, the after-death mollusk body is commonly inaccessible because of either soft material deterioration or fossilization. This study aims at characterizing Brazilian land snails by morphometrical data features manually taken from the shells. In particular, we examined a dataset of shells by using different learning models that labeled snail specimens with a precision up to 97.5% (F1-Score = .975, CKC = .967 and ROC Area = .998). The extracted patterns describe similarities and trends among land snail species and indicates possible outliers physiologies due to climate traits and breeding. Finally, we show some morphometrical characteristics dominate others according to different feature selection biases. Those data-based patterns can be applied to fast land snail identification whenever their bodies are unavailable, as in the recurrent cases of lost shells in nature or private and museum collections.