Search

In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual information allows us to create an information measure that quantifies how much information flows between any two neurons of a deep learning model. To that end, we propose NIF, Neural Information Flow, a technique for codifying information flow that exposes deep learning model internals and provides feature attributions., Comment: ICASSP 2020 (shorter version appeared at AAAI-19 Workshop on Network Interpretability for Deep Learning)

To improve precipitation predictions and enable accurate rainfall models for smart water networks, it is imperative to account for multivariate and multiscale precipitation dynamics with long-memory temporal relationships, long-range spatial dependencies, and low-frequency variability. While prior art has motivated the use of complex networks to capture these trends, existing work is limited to specific climate phenomena (such as El Nino) and regions. In this paper we employ a comprehensive assessment of complex networks with respect to multivariate dynamics across multiple temporal and spatial scales (multiscale). Our work is the first to incorporate both carbon emissions and precipitation anomalies data into a multivariate analysis. By effectively substantiating the ability of complex networks to capture multivariate and multiscale climate dynamics, we postulate their potential as reanalysis and assessment tools to enhance regional water models of arbitrary range and granularity, and to eventually enable reliable smart water systems.

Forecasting short-term river flowrate is an important problem for flood planning/preparation and hydropower management. In this paper, we propose K-Hop Learning, a novel feature extraction method, which utilizes network information to learn upcoming river flow peaks 24-hours in advance. We then use these learned features to forecast flowrate 24-hours ahead at various locations in the Ohio River Basin, USA. Our results clearly demonstrate that the predictions using K-Hop Learning are far superior to several traditional timeseries-based, machine learning models such as SVM Regression. Further, in contrast to these existing timeseries-based models, the upcoming river flow peaks are predicted very accurately by our approach. Overall, using K-Hop Learning, we significantly reduce the prediction RMSE by 57--82% depending on the river size.

In this paper, we construct the first human carbon emissions network which connects more than a thousand geographical locations based on their daily carbon emissions. We use this network to enable a data-driven analysis for a myriad of scientific knowledge discovery tasks. Specifically, we demonstrate that our carbon emissions network is strongly correlated with oil prices and socio-economic events like regional wars and financial crises. Further, we propose the first multilayer network approach that couples carbon emissions with climate (temperature) anomalies and identifies climate anomaly outlier locations across 60 years of documented carbon emissions data; these outlier locations, despite having different emission trends, experience similar temperature anomalies. Overall, we demonstrate how using network science as a key data analysis technique can reveal a treasure trove of knowledge hidden beneath the carbon emissions data.