Sensor networks are revolutionizing environmental monitoring by producing massive quantities of data that are being made publically available in near real time. These data streams pose a challenge for ecologists because traditional approaches to quality assurance and quality control are no longer practical when confronted with the size of these data sets and the demands of real-time processing. Automated methods for rapidly identifying and (ideally) correcting problematic data are essential. However, advances in sensor hardware have outpaced those in software, creating a need for tools to implement automated quality assurance and quality control procedures, produce graphical and statistical summaries for review, and track the provenance of the data. Use of automated tools would enhance data integrity and reliability and would reduce delays in releasing data products. Development of community-wide standards for quality assurance and quality control would instill confidence in sensor data and would improve interoperability across environmental sensor networks.

The ecological sciences have benefited greatly from recent advances in wireless sensor technologies. These technologies allow researchers to deploy networks of automated sensors, which can monitor a landscape at very fine temporal and spatial scales. However, these networks are subject to harsh conditions, which lead to malfunctions in individual sensors and failures in network communications. The resulting data streams often exhibit incorrect data measurements and missing values. Identifying and correcting these is time-consuming and error-prone. We present a method for real-time automated data quality control (QC) that exploits the spatial and temporal correlations in the data to distinguish sensor failures from valid observations. The model adapts to each deployment site by learning a Bayesian network structure that captures spatial relationships between sensors, and it extends the structure to a dynamic Bayesian network to incorporate temporal correlations. This model is able to flag faulty observations and predict the true values of the missing or corrupt readings. The performance of the model is evaluated on data collected by the SensorScope Project. The results show that the spatiotemporal model demonstrates clear advantages over models that include only temporal or only spatial correlations, and that the model is capable of accurately imputing corrupted values.

We study the problem of learning probabilistic models of high-level strategic behavior in the real-time strategy (RTS) game StarCraft. The models are automatically learned from sets of game logs and aim to capture the common strategic states and decision points that arise in those games. Unlike most work on behavior/strategy learning and prediction in RTS games, our data-centric approach is not biased by or limited to any set of preconceived strategic concepts. Further, since our behavior model is based on the well-developed and generic paradigm of hidden Markov models, it supports a variety of uses for the design of AI players and human assistants. For example, the learned models can be used to make probabilistic predictions of a player's future actions based on observations, to simulate possible future trajectories of a player, or to identify uncharacteristic or novel strategies in a game database. In addition, the learned qualitative structure of the model can be analyzed by humans in order to categorize common strategic elements. We demonstrate our approach by learning models from 331 expert-level games and provide both a qualitative and quantitative assessment of the learned model's utility.

Abstract-To avoid ecological collapse, we must manage Earth's ecosystems sustainably. Viewed as a control problem, the two central challenges of ecosystem management are to acquire a model of the system that is sufficient to guide good decision making and then optimize the control policy against that model. This paper describes three efforts aimed at addressing the first of these challenges-machine learning methods for modeling ecosystems. The first effort focuses on automated quality control of environmental sensor data. Next, we consider the problem of learning species distribution models from citizen science observational data. Finally, we describe a novel approach to modeling the migration of birds. A major challenge for all of these methods is to scale up to large, spatially-distributed systems.