Inference of ecological and environmental models

生态和环境模式不断发展。在渔业研究中，个体运动、环境驱动因素和种间相互作用是刺激新的和复杂的建模工作发展的关键领域。基于个体的模型（IBMs）是这种模型的一个例子，在这种模型中，个体动物相互作用，它们生活在其中，种群指标来自集体个体的行动。当在空间明确的景观中使用时，IBM可以显示人口预计如何随着时间的推移而变化以响应管理行动，因此已被证明是许多系统中有效的管理工具。例如，IBM正在被用于制定渔业保护和开发战略，以及评估重大建设项目和新型农业化学品对人口的影响。然而，在这些模型用于支持决策之前，需要对数据的拟合和相关的不确定性有很好的理解，因此，迫切需要改进复杂多参数模型的校准方法：现有方法太慢，并且不总是准确的。该项目旨在改进现有的最佳方法：近似贝叶斯计算，ABC。ABC目前被用于生态学、进化和更广泛领域的各种应用中的统计推断，包括例如：安博塞利大象模型;东北大西洋鲭鱼;当地蝴蝶种群;以及病原体的进化;社会网络分析;和统计物理学（参见Didelot et al. 2011; Prangle et al. 2016;货车der Vaart et al. 2016）。在大多数情况下，参数估计和模型比较的挑战都很重要，但实施可能会证明计算成本很高。该项目旨在改进ABC方法，并与环境研究人员合作应用这些方法，以帮助他们将模型与数据拟合。最初的重点将放在由英国政府海洋和淡水科学专家Cefas开发的渔业管理IBM上，https://www.cefas.co.uk/.ABC将模型输出与数据进行比较，对于模型仅作为IBM等计算机模拟器提供的统计推断特别有用。ABC是一个相对较新的研究领域，也是统计学和多个应用领域的热门话题（博蒙2010）。在这个领域有许多开放的问题，其中一些是这个项目的核心，包括：高维参数空间的ABC。IBM通常有超过10个参数，必须通过将模型拟合到数据来估计：比ABC的许多当前应用程序更多。有些IBM需要几分钟才能完成一次运行。这是一个问题，因为现有的ABC方法需要数千次运行才能获得可靠的结果。本项目将开发新的方法来解决这些问题，因为需要准确的渔业生态模型来指导渔业管理。

Ecological and environmental models are continually evolving. Within fisheries research , individual movement, environmental drivers, and interspecific interactions are key areas of interest stimulating the development of new and complex modelling efforts. Individual-based models (IBMs) are one example of such model in which individual animals interact with one another and the landscape in which they live, with population metrics emerging from the actions of collective individuals. When used in spatially-explicit landscapes IBMs can show how populations are expected to change over time in response to management actions, and have therefore been shown to be effective management tools in many systems. For instance, IBMs are being used to design strategies for the conservation and exploitation of fisheries, and for assessing the effects on populations of major construction projects and novel agricultural chemicals. However, good understanding of fits to data and associated uncertainty are needed before such models can be used to support decision making.Hence, there is urgent need to improve methods of calibrating complex multiparameter models: existing methods are too slow, and not always accurate. This project aims to improve the best existing method: Approximate Bayesian Computation, ABC. ABC is currently being used for statistical inference in a diverse range of applications in ecology, evolution and more widely, including for example: models of elephants in Amboseli; mackerel in the North East Atlantic; local butterfly populations; but also evolution of pathogens; social network analysis; and statistical physics (see Didelot et al. 2011; Prangle et al. 2016; van der Vaart et al. 2016). In most of these cases the challenges of parameter estimation and model comparison are both of importance, but implementation can prove computationally expensive. This project aims to improve ABC methods and apply them in collaboration with environmental researchers, to help them in fitting models to data. Initial focus will be on IBMs developed for fisheries management by Cefas, the UK governments marine and freshwater science experts, https://www.cefas.co.uk/.ABC compares model outputs with data and is particularly useful for statistical inference where the model is only available as a computer simulator such as an IBM. ABC is a relatively new field of research, and is a hot topic in statistics and several applied fields (Beaumont 2010). There are many open problems in this area, some of which lie at the heart of this project, including:ABC for high-dimensional parameter spaces. IBMs often have more than 10 parameters that have to be estimated by fitting the model to data: more than in many current applications of ABC.ABC for computationally expensive simulators. Some IBMs take several minutes to complete a run. This is a problem because existing ABC methods require thousands of runs to obtain reliable results.This project will develop new methods to address these issues, driven by the need for accurate fisheries ecological models to guide fisheries management.