Partial observability and management of ecological systems

Neural Causal Information Extractor for Unobserved Causes

Causal inference aims to faithfully depict the causal relationships between given variables. However, in many practical systems, variables are often partially observed, and some unobserved variables could carry significant information and induce causal effects on a target. Identifying these unobserved causes remains a challenge, and existing works have not considered extracting the unobserved causes while retaining the causes that have already been observed and included. In this work, we aim to construct the implicit variables with a generator-discriminator framework named the Neural Causal Information Extractor (NCIE), which can complement the information of unobserved causes and thus provide a complete set of causes with both observed causes and the representations of unobserved causes. By maximizing the mutual information between the targets and the union of observed causes and implicit variables, the implicit variables we generate could complement the information that the unobserved causes should have provided. The synthetic experiments show that the implicit variables preserve the information and dynamics of the unobserved causes. In addition, extensive real-world time series prediction tasks show improved precision after introducing implicit variables, thus indicating their causality to the targets.

Four conservation challenges and a synthesis

Conservation and management of biological systems involves decision-making over time, with a generic goal of sustaining systems and their capacity to function in the future. We address four persistent and difficult conservation challenges: (1) prediction of future consequences of management, (2) uncertainty about the system's structure, (3) inability to observe ecological systems fully, and (4) nonstationary system dynamics. We describe these challenges in terms of dynamic systems subject to different sources of uncertainty, and we present a basic Markovian framework that can encompass approaches to all four challenges. Finding optimal conservation strategies for each challenge requires issue-specific structural features, including adaptations of state transition models, uncertainty metrics, valuation of accumulated returns, and solution methods. Strategy valuation exhibits not only some remarkable similarities among approaches but also some important operational differences. Technical linkages among the models highlight synergies in solution approaches, as well as possibilities for combining them in particular conservation problems. As methodology and computing software advance, such an integrated conservation framework offers the potential to improve conservation outcomes with strategies to allocate management resources efficiently and avoid negative consequences.