Biodiversity loss is one of the main challenges of our time,1,2 and attempts to address it require a clear un derstanding of how ecological communities respond to environmental change across time and space.3,4 While the increasing availability of global databases on ecological communities has advanced our knowledge of biodiversity sensitivity to environmental changes,5–7 vast areas of the tropics remain understudied.8–11 In the American tropics, Amazonia stands out as the world’s most diverse rainforest and the primary source of Neotropical biodiversity,12 but it remains among the least known forests in America and is often underrepre sented in biodiversity databases.13–15 To worsen this situation, human-induced modifications16,17 may elim inate pieces of the Amazon’s biodiversity puzzle before we can use them to understand how ecological com munities are responding. To increase generalization and applicability of biodiversity knowledge,18,19 it is thus crucial to reduce biases in ecological research, particularly in regions projected to face the most pronounced environmental changes. We integrate ecological community metadata of 7,694 sampling sites for multiple or ganism groups in a machine learning model framework to map the research probability across the Brazilian Amazonia, while identifying the region’s vulnerability to environmental change. 15%–18% of the most ne glected areas in ecological research are expected to experience severe climate or land use changes by 2050. This means that unless we take immediate action, we will not be able to establish their current status, much less monitor how it is changing and what is being lost

Abstract The Global Strategy for Plant Conservation (GSPC) was established by the Conference of Parties in 2002 to decrease the loss of plant diversity, reduce poverty and contribute to sustainable development. To achieve this overarching goal, the GSPC has established a series of targets, one of which is to ensure that plant diversity is well understood, so that it can be effectively conserved and used in a sustainable manner. Brazil hosts more than 46,000 species of plants, algae and fungi, representing one of the most biodiverse countries on Earth, and playing a key role in the GSPC. To meet the GSPC goals of Target 1 and facilitate access to plant diversity, Brazil committed to preparing the List of Species of the Brazilian Flora (2008-2015) and the Brazilian Flora 2020 (2016-present). Managing all the information associated with such great biodiversity has proven to be an extremely challenging task. Here, we synthesize the history of these projects, focusing on the multidisciplinary and collaborative approach adopted to develop and manage the inclusion of all the knowledge generated though digital information systems. We further describe the methods used, challenges faced, and strategies adopted, as well as summarize advances to date and prospects for completing the Brazilian flora in 2020.