ITR: Statistical Pattern Recognition in Environmental Observation and Forecasting Systems

环境观测和预报系统（EOFS）是新兴的新技术，在影响可持续发展方面具有无与伦比的潜力。EOFS有望在从全球到区域和地方子系统的各个领域培育和支持知识的产生、转移和社会应用的新范式。EOFS的核心是及时和定制的获取、生成、处理和交付可靠的、相关的信息给许多非常不同的受众。实现这一概念需要面对多重挑战。一个关键的挑战是开发自动化程序来验证EOFS实时和离线生成的大量观测和模拟数据的质量。基于流程的科学数据质量控制策略，虽然对中等规模的档案数据有效，但要很好地映射到eofs规模的数据集，需要大量的工具劳动。基于模式识别和机器学习的策略作为替代或补充具有重要的前景。根据提议的项目，我们将开发基于统计模式识别和信号处理，在线自适应系统，数据挖掘和高级搜索的方法，以解决关键的质量控制问题，包括：1)检测非平稳，时空系统中的传感器损坏，2)从损坏的传感器数据中估计真实信号，以及3)检测和表征可能出现模型异常的制度。这些质量控制技术将在哥伦比亚河河口和邻近沿海水域的试点生态环境监测系统（http://www.ccalmr.ogi.edu/CORIE）The项目将通过生态环境监测系统（特别是生态环境监测系统）在区域和国家可持续发展问题上的作用产生强大的社会影响。该项目还将包括多层次的跨学科教育机会。

Project SummaryEnvironmental observation and forecasting systems (EOFS) are emerging new technologies with unparalleledpotential to impact sustainable development. EOFS are expected to foster and support new paradigms forgeneration, transfer and social application of knowledge in domains that range from the global earth to itsregional and local sub-systems.At the core of EOFS is the timely and customized acquisition, generation, processing and delivery of reliable,relevant information to many and very diverse audiences. Multiple challenges need to be met to implementthis concept.A critical challenge is the development of automated procedures to verify the quality of the huge amountsof observational and simulation data that are generated by EOFS both in real-time and off-line. Process-based strategies for quality control of scientific data, while effective for moderate-size archival data are toolabor-intensive to map well into EOFS-scale data sets. Strategies based on pattern recognition and machinelearning hold significant promise as an alternative or complement.Under the proposed project, we will develop approaches based in statistical pattern recognition and signalprocessing, on-line adaptive systems, datamining, and advanced search to address critical quality controlissues including: 1) Detecting sensor corruption in non-stationary, spatial-temporal systems, 2) Estimatingtrue signals from corrupted sensor data, and 3) Detecting and characterizing regimes where model anomaliesare likely.These quality control techniques will be developed and exercised on CORIE, a pilot EOFS for the COlumbiaRIver Estuary and adjacent coastal waters (http://www.ccalmr.ogi.edu/CORIE)The project will have strong social impact, through the role of EOFS (and, specifically, CORIE) on regionaland national sustainable development issues. The project will also include cross-disciplinary educationalopportunities at multiple levels.