Spatial prediction of <i>Melanoplus differentialis</i> using an ensemble of multiple species distribution models

Abstract Melanoplus differentialis , a notorious invasive alien species with a high spread potential, causes negative socioecological impacts. Climate change‐induced alterations in its occurrence areas are a global concern, necessitating a precautionary evaluation of its distribution under varying climatic conditions to prevent damage caused by this pest. In this study, multiple species distribution modelling (SDM) algorithms (CLIMEX, MaxEnt and Random Forest) were employed and integrated to evaluate the potential distribution of M. differentialis under climate change scenarios. Model performance was evaluated using both the validation dataset used during model development and a spatiotemporally separated test dataset. Although the SDM algorithms showed differences in performance, all models consistently demonstrated a recall exceeding 0.9 on the test occurrence datasets. The potential occurrence areas for M. differentialis are expected to expand primarily around its native North America as climate changes. Additionally, Europe and Far East Asia, where the species has not yet been observed, have been identified as risk areas for its post‐invasion spread, highlighting the need for intensive monitoring. This study provides essential information for establishing proactive strategies to control M. differentialis , which occurs on a large scale and moves rapidly. It also proposes a methodological approach using a multi‐algorithm‐based ensemble SDM to develop an effective species distribution prediction model.