Multimodal data integration to model, predict, and understand changes in plant biodiversity: a systematic review

The integration of multimodal data to analyze, model, and predict changes in plant biodiversity is critical for addressing global conservation challenges. This systematic review examines the current landscape of plant biodiversity data, focusing on the identification, classification, and evaluation of key open-access data sources and integration methodologies. We highlight the strengths and limitations of major biodiversity platforms, emphasizing their contributions to species occurrence, trait data, taxonomic checklists, and environmental variables. The review also explores computational approaches for multimodal data integration, including metadata standardization frameworks (e.g., Darwin Core) and advanced modeling techniques like Species Distribution Models (SDMs) and deep learning methods. Additionally, we assess environmental drivers of biodiversity change—such as climate variables, land-use patterns, and elevation gradients—and the tools available for their analysis. Despite significant advancements in biodiversity informatics, challenges persist in achieving interoperability across datasets, addressing spatial and temporal biases, and integrating remote sensing with in situ observations. By identifying gaps in current methodologies and proposing pathways for improvement, this review contributes to advancing biodiversity monitoring strategies. These efforts align with global conservation goals outlined by the Convention on Biological Diversity and the United Nations Sustainable Development Goal 15. Ultimately, the findings underscore the importance of harmonized data integration frameworks to enhance predictive modeling capabilities and inform effective conservation policies.