This paper introduces neural Bayes estimators for censored peaks-over-threshold models, enhancing computational efficiency in spatial extremal dependence modeling. The method uses data augmentation to encode censoring information in the neural network input, challenging traditional likelihood-based approaches. The estimators were applied to assess extreme particulate matter concentrations over Saudi Arabia, demonstrating efficacy in high-dimensional models. Why it matters: The research offers a computationally efficient alternative for environmental modeling and risk assessment in the region.
KAUST postdoctoral fellow Carolina Euán received the Sylvia Esterby Presentation Award from the International Environmentrics Society (TIES) for her talk on a spatio-temporal model applied to drought data in Mexico. The research, conducted with KAUST Associate Professor Ying Sun, focuses on modeling dependence between processes observed in two categories, such as dry or rainy days. Euán joined KAUST in 2016 after completing her Ph.D. in statistics from the Research Center in Mathematics (CIMAT), Guanajuato, Mexico. Why it matters: This award recognizes the quality of environmental statistics research being conducted at KAUST and its applicability to understanding complex environmental phenomena in the region and beyond.
Emilio Porcu from Khalifa University presented on temporally evolving generalized networks, where graphs evolve over time with changing topologies. The presentation addressed challenges in building semi-metrics and isometric embeddings for these networks. The research uses kernel specification and network-based metrics and is illustrated using a traffic accident dataset. Why it matters: This work advances the application of kernel methods to dynamic graph structures, relevant for modeling evolving relationships in various domains.
KAUST alumna Yuan Yan received an honorable mention from the American Statistical Association (ASA) for her paper on "Vector Autoregressive Models with Spatially Structured Coefficients for Time Series on a Spatial Grid." Yan, who graduated from KAUST in 2018, was part of Professor Marc Genton's Spatio-Temporal Statistics & Data Science group. She is now a postdoctoral fellow at Dalhousie University, researching fisheries science using spatial statistical models. Why it matters: This recognition highlights the quality of research and education at KAUST, especially in the field of spatio-temporal statistics, and its impact on addressing real-world sustainability challenges.
This paper introduces a novel approach for monitoring and analyzing the evolution of complex geographic objects in satellite image time-series. The method uses a spatiotemporal graph and constraint satisfaction problems (CSP) to model and analyze object changes. Experiments on real-world satellite images from Saudi Arabian cities demonstrate the effectiveness of the proposed approach.
KAUST Ph.D. student Yuxiao Li received a Student Paper Award from the American Statistical Association (ASA) for his paper on efficient estimation of non-stationary spatial covariance functions. The award-winning paper is Li's first research paper at KAUST, completed as a member of the Environmental Statistics Group led by Professor Ying Sun. His research focuses on short-term space-time precipitation modeling, addressing the challenges of modeling rainfall zeros and amounts along with complex spatio-temporal dependencies. Why it matters: This award recognizes KAUST's contributions to advanced statistical methods for environmental modeling, highlighting the university's strength in addressing complex environmental challenges.
KAUST Assistant Professor Paula Moraga has authored a new textbook, "Spatial Statistics for Data Science: Theory and Practice with R," based on her lectures. The book is available for free on her website and in hard copy through the publisher. Dr. Moraga's research focuses on developing statistical methods and computational tools for geospatial data analysis and health surveillance, with applications in reducing disease burden and identifying high-risk populations. Why it matters: The publication strengthens KAUST's research profile in spatial data science and offers valuable open-source resources for addressing critical challenges in public health and resource management within Saudi Arabia and the broader region.
Researchers propose a spatio-temporal model for high-resolution wind forecasting in Saudi Arabia using Echo State Networks and stochastic partial differential equations. The model reduces spatial information via energy distance, captures dynamics with a sparse recurrent neural network, and reconstructs data using a non-stationary stochastic partial differential equation approach. The model achieves more accurate forecasts of wind speed and energy, potentially saving up to one million dollars annually compared to existing models.