Acoustic indices have been increasingly explored as possible proxies for biodiversity, yet in complex environments non-avian sounds often mask bird vocalizations, compromising assessment accuracy and ecological representativeness. To address this, we developed an integrated framework that combines deep learning-based soundscape classification with a threshold-optimized strategy for removing non-avian recordings. A multi-label model was trained to identify 12 representative soundscape categories. Non-avian recordings were then removed using threshold criteria optimized through systematic evaluation of threshold combinations, maximizing correlations between six acoustic indices [acoustic complexity index (ACI), acoustic diversity index (ADI), acoustic evenness index (AEI), bioacoustic index (BIO), normalized difference soundscape index (NDSI), acoustic entropy index (H)] and bird vocal activity while retaining as much useable recording data as possible to avoid excessive reduction of sample size. To validate the effectiveness of our framework, generalized additive models and random forest regressions were used to compare diel patterns and predict bird vocal activity before and after removal. Using data from 19 passive acoustic recorders in the Central Green Forest Park, Beijing, we found insect sounds exerted the strongest masking effect on relationships between indices and bird vocal activity. Applying optimized removal improved temporal alignment of indices with bird vocal activity and enhanced predictive performance. This study demonstrates that threshold-guided removal of non-avian recordings strengthen the ecological interpretability and predictive utility of acoustic indices in biodiversity monitoring.

Marine protected areas (MPAs) across various countries have contributed to safeguarding coastal and marine environments. Despite these efforts, marine non-native species (NNS) continue to threaten biodiversity and ecosystems, even within MPAs. Currently, there is a lack of comprehensive studies on the inventories, distribution patterns, and effect factors of NNS within MPAs. Here we show a database containing over 15,000 occurrence records of 2714 marine NNS across 16,401 national or regional MPAs worldwide. To identify the primary mechanisms driving the occurrence of NNS, we utilize model selection with proxies representing colonization pressure, environmental variables, and MPA characteristics. Among the environmental predictors analyzed, sea surface temperature emerged as the sole factor strongly associated with NNS richness. Higher sea surface temperatures are linked to increased NNS richness, aligning with global marine biodiversity trends. Furthermore, human activities help species overcome geographical barriers and migration constraints. Consequently, this influences the distribution patterns of marine introduced species and associated environmental factors. As global climate change continues to alter sea temperatures, it is crucial to protect marine regions that are increasingly vulnerable to intense human activities and biological invasions.