Showing papers by "Pang-Ning Tan published in 2019"

Winter Precipitation and Summer Temperature Predict Lake Water Quality at Macroscales

Abstract: Climate change can have strong effects on aquatic ecosystems, including disrupting nutrient cycling and mediating processes that affect primary production. Past studies have been conducted mostly on individual or small groups of ecosystems, making it challenging to predict how future climate change will affect water quality at broad scales. We used a subcontinental‐scale database to address three objectives: (1) identify which climate metrics best predict lake water quality, (2) examine whether climate influences different nutrient and productivity measures similarly, and (3) quantify the potential effects of a changing climate on lakes. We used climate data to predict lake water quality in ~11,000 north temperate lakes across 17 U.S. states. We developed a novel machine learning method that jointly models different measures of water quality using 48 climate metrics and accounts for properties inherent in macroscale data (e.g., spatial autocorrelation). Our results suggest that climate metrics related to winter precipitation and summer temperature were strong predictors of lake nutrients and productivity. However, we found variation in the magnitude and direction of the relationship between climate and water quality. We predict that a likely future climate change scenario of warmer summer temperatures will lead to increased nutrient concentrations and algal biomass across lakes (median ~3%–9% increase), whereas increased winter precipitation will have highly variable effects. Our results emphasize the importance of heterogeneity in the response of individual ecosystems to climate and are a caution to extrapolating relationships across space.

OPTANE: an OPtimal transport algorithm for NEtwork alignment

Abstract: Networks provide a powerful representation tool for modeling dyadic interactions among interconnected entities in a complex system. For many applications such as social network analysis, it is common for the entities to appear in more than one network. Network alignment (NA) is an important first step towards learning the entities' behavior across multiple networks by finding the correspondence between similar nodes in different networks. However, learning the proper alignment matrix in noisy networks is a challenge due to the difficulty in preserving both the neighborhood topology and feature consistency of the aligned nodes. In this paper, we present OPTANE, a robust unsupervised network alignment framework, inspired from an optimal transport theory perspective. The framework provides a principled way to combine node similarity with topology information to learn the alignment matrix. Experimental results conducted on both synthetic and real-world data attest to the effectiveness of the OPTANE framework compared to other baseline approaches.

Hierarchical LSTM Framework for Long-Term Sea Surface Temperature Forecasting

Abstract: 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.

You have been CAUTE!: early detection of compromised accounts on social media

Abstract: 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.

Spatially Constrained Spectral Clustering Algorithms for Region Delineation.

Abstract: Regionalization is the task of dividing up a landscape into homogeneous patches with similar properties. Although this task has a wide range of applications, it has two notable challenges. First, it is assumed that the resulting regions are both homogeneous and spatially contiguous. Second, it is well-recognized that landscapes are hierarchical such that fine-scale regions are nested wholly within broader-scale regions. To address these two challenges, first, we develop a spatially constrained spectral clustering framework for region delineation that incorporates the tradeoff between region homogeneity and spatial contiguity. The framework uses a flexible, truncated exponential kernel to represent the spatial contiguity constraints, which is integrated with the landscape feature similarity matrix for region delineation. To address the second challenge, we extend the framework to create fine-scale regions that are nested within broader-scaled regions using a greedy, recursive bisection approach. We present a case study of a terrestrial ecology data set in the United States that compares the proposed framework with several baseline methods for regionalization. Experimental results suggest that the proposed framework for regionalization outperforms the baseline methods, especially in terms of balancing region contiguity and homogeneity, as well as creating regions of more similar size, which is often a desired trait of regions.