Geospatio-temporal data are pervasive across numerous application domains.These rich datasets can be harnessed to predict extreme events such as disease outbreaks, flooding, crime spikes, etc. However, since the extreme events are rare, predicting them is a hard problem. Statistical methods based on extreme value theory provide a systematic way for modeling the distribution of extreme values. In particular, the generalized Pareto distribution (GPD) is useful for modeling the distribution of excess values above a certain threshold. However, applying such methods to large-scale geospatio-temporal data is a challenge due to the difficulty in capturing the complex spatial relationships between extreme events at multiple locations. This paper presents a deep learning framework for long-term prediction of the distribution of extreme values at different locations. We highlight its computational challenges and present a novel framework that combines convolutional neural networks with deep set and GPD. We demonstrate the effectiveness of our approach on a real-world dataset for modeling extreme climate events.

Accurate forecasting of extreme values in time series is critical due to the significant impact of extreme events on human and natural systems. This paper presents DeepExtrema, a novel framework that combines a deep neural network (DNN) with generalized extreme value (GEV) distribution to forecast the block maximum value of a time series. Implementing such a network is a challenge as the framework must preserve the inter-dependent constraints among the GEV model parameters even when the DNN is initialized. We describe our approach to address this challenge and present an architecture that enables both conditional mean and quantile prediction of the block maxima. The extensive experiments performed on both real-world and synthetic data demonstrated the superiority of DeepExtrema compared to other baseline methods.

Zero-inflated, heavy-tailed spatiotemporal data is common across science and engineering, from climate science to meteorology and seismology. A central modeling objective in such settings is to forecast the intensity, frequency, and timing of extreme and non-extreme events; yet in the context of deep learning, this objective presents several key challenges. First, a deep learning framework applied to such data must unify a mixture of distributions characterizing the zero events, moderate events, and extreme events. Second, the framework must be capable of enforcing parameter constraints across each component of the mixture distribution. Finally, the framework must be flexible enough to accommodate for any changes in the threshold used to define an extreme event after training. To address these challenges, we propose Deep Extreme Mixture Model (DEMM), fusing a deep learning-based hurdle model with extreme value theory to enable point and distribution prediction of zero-inflated, heavy-tailed spatiotemporal variables. The framework enables users to dynamically set a threshold for defining extreme events at inference-time without the need for retraining. We present an extensive experimental analysis applying DEMM to precipitation forecasting, and observe significant improvements in point and distribution prediction. All code is available at https://github.com/andrewmcdonald27/DeepExtremeMixtureModel.

Link prediction is an important task in online social networking as it can be used to infer new or previously unknown relationships of a network. However, due to the homophily principle, current algorithms are susceptible to promoting links that may lead to increase segregation of the network—an effect known as filter bubble. In this study, we examine the filter bubble problem from the perspective of algorithm fairness and introduce a dyadic-level fairness criterion based on network modularity measure. We show how the criterion can be utilized as a postprocessing step to generate more heterogeneous links in order to overcome the filter bubble problem. In addition, we also present a novel framework that combines adversarial network representation learning with supervised link prediction to alleviate the filter bubble problem. Experimental results conducted on several real-world datasets showed the effectiveness of the proposed methods compared to other baseline approaches, which include conventional link prediction and fairness-aware methods for i.i.d data.

Convolutional methods are useful for modeling geospatial data as they enable the extraction of broad-scale spatial patterns from the local attributes observed at each location. The weighted aggregation performed by the convolutional operator also helps to smoothen the noisy data collected at the given locations. However, current convolutional methods are primarily designed to learn the spatial dependencies of the input (predictor) variables only. The recent success in applying multi-task learning to various geospatial prediction problems shows that the model parameters themselves may also be spatially related. This suggests the possibility of employing convolutional methods to learn the spatial dependencies among the model parameters at different locations, especially in situations where there are limited training data available to fit accurate local models. In this paper, we investigate three different ways to incorporate convolutions into geospatial prediction models—convolutions on the predictors, model parameters, or a hybrid of both. We provide guidance on when convolution of each type can be fruitfully applied and verify their effectiveness using both synthetic and real-world datasets.

Detection of compromised social media accounts is an important problem as the compromised accounts can be exploited by hackers to spread false and misleading information. In particular, early detection of compromised accounts is essential to mitigating the damages caused by the hackers' posts, which may range from victim shaming to causing widespread public panic and civil unrest. This paper proposes CAUTE, a deep learning framework that simultaneously learns the feature embeddings of the users and their posts in order to identify which, if any, of their posts were written by a different person, i.e. a hacker. Using Twitter as an example of the social media platform, CAUTE learns a tweet-to-user encoder to infer the user features from tweet features and a user-to-tweet encoder to predict the tweet content from a combination of the user features and the tweet meta features. The residual errors of both encoders are then fed into a fully-connected neural network layer to detect whether a post was published by the specified user or by a hacker. Experimental results showed that the features learned by CAUTE are more informative than those generated by conventional representation learning methods. Additionally, CAUTE outperformed several state-of-the-art baseline algorithms in terms of their overall performance and can effectively detect compromised posts early without generating too many false alarms.

Multi-step prediction of sea surface temperature (SST) is a challenging problem because small errors in its shortrange forecasts can be compounded to create large errors at longer ranges. In this paper, we propose a hierarchical LSTM framework to improve the accuracy for long-term SST prediction. Our framework alleviates the error accumulation problem in multi-step prediction by leveraging outputs from an ensemble of physically-based dynamical models. Unlike previous methods, which simply take a linear combination of the outputs to produce a single deterministic forecast, our framework learns a nonlinear relationship among the ensemble member forecasts. In addition, its multi-level structure is designed to capture the temporal autocorrelation between forecasts generated for the same lead time as well as those generated for different lead times. Experiments performed using SST data from the tropical Pacific ocean region show that the proposed framework outperforms various baseline methods in more than 70% of the grid cells located in the study region.

Weather forecasting is an important but challenging problem as one must contend with the inherent non-linearities and spatiotemporal autocorrelation present in the data. This paper presents a novel deep learning approach based on a coupled weighted graph convolutional LSTM (WGC-LSTM) to address these challenges. Specifically, our proposed approach uses an LSTM to capture the inherent temporal autocorrelation of the data and a graph convolution to model its spatial relationships. As the weather condition can be influenced by various spatial factors besides the distance between locations, e.g., topography, prevailing winds and jet streams, imposing a fixed graph structure based on the proximity between locations is insufficient to train a robust deep learning model. Instead, our proposed approach treats the adjacency matrix of the graph as a model parameter that can be learned from the training data. However, this introduces an additional O(|V|2) parameters to be estimated, where V is the number of locations. With large graphs this may also lead to slower performance as well as susceptibility to overfitting. We propose a modified version of our approach that can address this difficulty by assuming that the adjacency matrix is either sparse or low rank. Experimental results using two real-world weather datasets show that WGC-LSTM outperforms all other baseline methods for the majority of the evaluated locations.

In climate and environmental sciences, vast amount of spatio-temporal data have been generated at varying spatial resolutions from satellite observations and computer models. Integrating such diverse sources of data has proven to be useful for building prediction models as the multi-scale data may capture different aspects of the Earth system. In this paper, we present a novel framework called MUSCAT for predictive modeling of multi-scale, spatio-temporal data. MUSCAT performs a joint decomposition of multiple tensors from different spatial scales, taking into account the relationships between the variables. The latent factors derived from the joint tensor decomposition are used to train the spatial and temporal prediction models at different scales for each location. The outputs from these ensemble of spatial and temporal models will be aggregated to generate future predictions. An incremental learning algorithm is also proposed to handle the massive size of the tensors. Experimental results on real-world data from the United States Historical Climate Network (USHCN) showed that MUSCAT outperformed other competing methods in more than 70\% of the locations.