Auroop R. Ganguly

Knowledge discovery from data streams

Since the beginning of the Internet age and the increased use of ubiquitous computing devices, the large volume and continuous flow of distributed data have imposed new constraints on the design of learning algorithms. Exploring how to extract knowledge structures from evolving and time-changing data, Knowledge Discovery from Data Streams presents a coherent overview of state-of-the-art research in learning from data streams. The book covers the fundamentals that are imperative to understanding data streams and describes important applications, such as TCP/IP traffic, GPS data, sensor networks, and customer click streams. It also addresses several challenges of data mining in the future, when stream mining will be at the core of many applications. These challenges involve designing useful and efficient data mining solutions applicable to real-world problems. In the appendix, the author includes examples of publicly available software and online data sets. This practical, up-to-date book focuses on the new requirements of the next generation of data mining. Although the concepts presented in the text are mainly about data streams, they also are valid for different areas of machine learning and data mining.

Intensification and spatial homogenization of coastal upwelling under climate change

The timing and strength of wind-driven coastal upwelling along the eastern margins of major ocean basins regulate the productivity of critical fisheries and marine ecosystems by bringing deep and nutrient-rich waters to the sunlit surface, where photosynthesis can occur. How coastal upwelling regimes might change in a warming climate is therefore a question of vital importance. Although enhanced land–ocean differential heating due to greenhouse warming has been proposed to intensify coastal upwelling by strengthening alongshore winds, analyses of observations and previous climate models have provided little consensus on historical and projected trends in coastal upwelling. Here we show that there are strong and consistent changes in the timing, intensity and spatial heterogeneity of coastal upwelling in response to future warming in most Eastern Boundary Upwelling Systems (EBUSs). An ensemble of climate models shows that by the end of the twenty-first century the upwelling season will start earlier, end later and become more intense at high but not low latitudes. This projected increase in upwelling intensity and duration at high latitudes will result in a substantial reduction of the existing latitudinal variation in coastal upwelling. These patterns are consistent across three of the four EBUSs (Canary, Benguela and Humboldt, but not California). The lack of upwelling intensification and greater uncertainty associated with the California EBUS may reflect regional controls associated with the atmospheric response to climate change. Given the strong linkages between upwelling and marine ecosystems, the projected changes in the intensity, timing and spatial structure of coastal upwelling may influence the geographical distribution of marine biodiversity.

Multivariate and multiscale dependence in the global climate system revealed through complex networks

A systematic characterization of multivariate dependence at multiple spatio-temporal scales is critical to understanding climate system dynamics and improving predictive ability from models and data. However, dependence structures in climate are complex due to nonlinear dynamical generating processes, long-range spatial and long-memory temporal relationships, as well as low-frequency variability. Here we utilize complex networks to explore dependence in climate data. Specifically, networks constructed from reanalysis-based atmospheric variables over oceans and partitioned with community detection methods demonstrate the potential to capture regional and global dependence structures within and among climate variables. Proximity-based dependence as well as long-range spatial relationships are examined along with their evolution over time, yielding new insights on ocean meteorology. The tools are implicitly validated by confirming conceptual understanding about aggregate correlations and teleconnections. Our results also suggest a close similarity of observed dependence patterns in relative humidity and horizontal wind speed over oceans. In addition, updraft velocity, which relates to convective activity over the oceans, exhibits short spatiotemporal decorrelation scales but long-range dependence over time. The multivariate and multi-scale dependence patterns broadly persist over multiple time windows. Our findings motivate further investigations of dependence structures among observations, reanalysis and model-simulated data to enhance process understanding, assess model reliability and improve regional climate predictions.

Higher trends but larger uncertainty and geographic variability in 21st century temperature and heat waves

Generating credible climate change and extremes projections remains a high-priority challenge, especially since recent observed emissions are above the worst-case scenario. Bias and uncertainty analyses of ensemble simulations from a global earth systems model show increased warming and more intense heat waves combined with greater uncertainty and large regional variability in the 21st century. Global warming trends are statistically validated across ensembles and investigated at regional scales. Observed heat wave intensities in the current decade are larger than worst-case projections. Model projections are relatively insensitive to initial conditions, while uncertainty bounds obtained by comparison with recent observations are wider than ensemble ranges. Increased trends in temperature and heat waves, concurrent with larger uncertainty and variability, suggest greater urgency and complexity of adaptation or mitigation decisions.

Offshoring: The Transition From Economic Drivers Toward Strategic Global Partnership and 24-Hour Knowledge Factory

The changing economic and labor conditions have motivated firms to outsource professional services activities to skilled personnel in less expensive labor markets. This offshoring phenomenon is studied from a political, economic, technological and strategic perspective. Next, an analytical model is developed for achieving strategic advantage from offshoring based on global partnerships. The model studies the impact of offshoring with respect to the complexity and strategic nature of the tasks and presents a decision strategy for obtaining value through offshoring of increasingly complex tasks. The result is an integrated “24-hour knowledge factory†that is based on a sustainable global model rather than a short term fiscal model. This 24-hour paradigm embodies the shift-style workforce that evolved for the manufacturing sector during the Industrial Revolution and relies on a set of critical success factors in the current environment. A case example is provided from IBM to illustrate these underlying critical success factors.

Changes in observed climate extremes in global urban areas

Climate extremes have profound implications for urban infrastructure and human society, but studies of observed changes in climate extremes over the global urban areas are few, even though more than half of the global population now resides in urban areas. Here, using observed station data for 217 urban areas across the globe, we show that these urban areas have experienced significant increases (p-value <0.05) in the number of heat waves during the period 1973–2012, while the frequency of cold waves has declined. Almost half of the urban areas experienced significant increases in the number of extreme hot days, while almost 2/3 showed significant increases in the frequency of extreme hot nights. Extreme windy days declined substantially during the last four decades with statistically significant declines in about 60% in the urban areas. Significant increases (p-value <0.05) in the frequency of daily precipitation extremes and in annual maximum precipitation occurred at smaller fractions (17 and 10% respectively) of the total urban areas, with about half as many urban areas showing statistically significant downtrends as uptrends. Changes in temperature and wind extremes, estimated as the result of a 40 year linear trend, differed for urban and non-urban pairs, while changes in indices of extreme precipitation showed no clear differentiation for urban and selected non-urban stations.

Spatiotemporal data mining in the era of big spatial data: algorithms and applications

Spatial data mining is the process of discovering interesting and previously unknown, but potentially useful patterns from the spatial and spatiotemporal data. However, explosive growth in the spatial and spatiotemporal data, and the emergence of social media and location sensing technologies emphasize the need for developing new and computationally efficient methods tailored for analyzing big data. In this paper, we review major spatial data mining algorithms by closely looking at the computational and I/O requirements and allude to few applications dealing with big spatial data.

Distributed Quantitative Precipitation Forecasting Using Information from Radar and Numerical Weather Prediction Models

The benefits of short-term (1‐6 h), distributed quantitative precipitation forecasts (DQPFs) are well known. However, this area is acknowledged to be one of the most challenging in hydrometeorology. Previous studies suggest that the ‘‘state of the art’’ methods can be enhanced by exploiting relevant information from radar and numerical weather prediction (NWP) models, using process physics and data-dictated tools where each fits best. Tests indicate that improved results are obtained by decomposing the overall problem into component processes, and that each process may require alternative tools ranging from simple interpolation to statistical time series models and artificial neural networks (ANNs). A new hybrid modeling strategy is proposed for DQPF that utilizes measurements from radar [Weather Surveillance Radar-1998 Doppler (WSR-88D) network: 4 km, 1 h] and outputs from NWP models (48-km Eta Model: 48 km, 6 h). The proposed strategy improves distributed QPF over existing methods like radar extrapolation or NWP-based QPF by themselves, as well as combinations of radar extrapolation and NWP-based QPF.

Data Mining for Climate Change and Impacts

Knowledge discovery from temporal, spatial and spatiotemporal data is critical for climate change science and climate impacts. Climate statistics is a mature area. However, recent growth in observations and model outputs, combined with the increased availability of geographical data, presents new opportunities for data miners. This paper maps climate requirements to solutions available in temporal, spatial and spatiotemporal data mining. The challenges result from long-range, long-memory and possibly nonlinear dependence, nonlinear dynamical behavior, presence of thresholds, importance of extreme events or extreme regional stresses caused by global climate change, uncertainty quantification, and the interaction of climate change with the natural and built environments. This paper makes a case for the development of novel algorithms to address these issues, discusses the recent literature, and proposes new directions. An illustrative case study presented here suggests that even relatively simple data mining approaches can provide new scientific insights with high societal impacts.

Knowledge Discovery from Sensor Data

Addressing the issues challenging the sensor community, this book presents innovative solutions in offline data mining and real-time analysis of sensor or geographically distributed data. Illustrated with case studies, it discusses the challenges and requirements for sensor data-based knowledge discovery solutions in high-priority application. The book then explores the fusion between heterogeneous data streams from multiple sensor types and applications in science, engineering, and security. Bringing together researchers from academia, government, and the private sector, this book delineates the application of knowledge modeling in data intensive operations. Multi/Card Deck Copy