A Shinyrapp to solve the problem of when to stop managing or surveying species under imperfect detection

摘要

In the last decade, artificial intelligence (AI) has increasingly been applied to help solve applied ecology problems. Partially observable Markov decision processes (POMDPs) are one such example. POMDPs have been applied in conservation, applied ecology and natural resource management to solve problems such as deciding when to stop managing or surveying threatened species that are difficult to detect. POMDP solvers are useful to find optimal sequential decisions under imperfect detection. However, POMDPs remain inaccessible to most applied ecologists. Here, we present the shinyrpackagesmsPOMDPthat solves the problem of 'When to stop managing or surveying cryptic threatened species?' (Chades et al., 2008). We developed this package to address a common and challenging problem faced by conservation managers. It has broad applications for decision-makers and ecologists by supporting them to focus efforts and resources where they are most likely to provide benefits to threatened species. OurrpackagesmsPOMDPincludes a set of functions that call a POMDP solver, allowing users to solve any stop, manage or survey problems that share the same structure as the original problem. Our Shinyrapp also allows users to run simulations of optimal management and graphically represent the optimal solution. ThesmsPOMDPpackage and documentation are hosted at . In artificial intelligence, POMDPs are acknowledged as the Swiss army knife of decision models. However, POMDP's application in applied ecology remains seldom despite repeated evidence of their flexibility. Our packagesmsPOMDPis fast and provides an entry point to further develop POMDP apps, contributing to further uptake of AI research to solve ecological problems.