NCEAS Product 25586

Cheng, Samantha; Augustin, Caitlin; Bethel, Alison; Gill, David; Anzaroot, Sam; Brun, Julien; Garside, Ruth; Masuda, Yuta; Miller, Daniel C.; Wilkie, David; Wongbusarakum, Supin; McKinnon (Bottrill), Madeleine; DeWilde, Burton; Minnich, Bob. 2018. Using machine learning to advance synthesis and use of conservation and environmental evidence. Conservation Biology. (Abstract)


Rapid growth in environmental research (Li & Zhao 2015) presents a potential wealth of information for conservation decision‐making. Evidence synthesis methods (e.g. systematic maps, reviews, meta‐analyses) (Pullin & Knight 2009) are critical for garnering actionable insight from published research, yet come with high resource demands (time and funding) that are prohibitive for meeting short policy windows (Elliott et al. 2014) and balancing trade‐offs between conservation planning and implementation.