Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.

Empirical networks often exhibit different meso-scale structures, such as community and core–periphery structures. Core–periphery structure typically consists of a well-connected core and a periphery that is well connected to the core but sparsely connected internally. Most core–periphery studies focus on undirected networks. We propose a generalization of core–periphery structure to directed networks. Our approach yields a family of core–periphery block model formulations in which, contrary to many existing approaches, core and periphery sets are edge-direction dependent. We focus on a particular structure consisting of two core sets and two periphery sets, which we motivate empirically. We propose two measures to assess the statistical significance and quality of our novel structure in empirical data, where one often has no ground truth. To detect core–periphery structure in directed networks, we propose three methods adapted from two approaches in the literature, each with a different trade-off between computational complexity and accuracy. We assess the methods on benchmark networks where our methods match or outperform standard methods from the literature, with a likelihood approach achieving the highest accuracy. Applying our methods to three empirical networks—faculty hiring, a world trade dataset and political blogs—illustrates that our proposed structure provides novel insights in empirical networks.

Our work is motivated by an interest in constructing a protein–protein interaction network that captures key features associated with Parkinson’s disease. While there is an abundance of subnetwork construction methods available, it is often far from obvious which subnetwork is the most suitable starting point for further investigation. We provide a method to assess whether a subnetwork constructed from a seed list (a list of nodes known to be important in the area of interest) differs significantly from a randomly generated subnetwork. The proposed method uses a Monte Carlo approach. As different seed lists can give rise to the same subnetwork, we control for redundancy by constructing a minimal seed list as the starting point for the significance test. The null model is based on random seed lists of the same length as a minimum seed list that generates the subnetwork; in this random seed list the nodes have (approximately) the same degree distribution as the nodes in the minimum seed list. We use this null model to select subnetworks which deviate significantly from random on an appropriate set of statistics and might capture useful information for a real world protein–protein interaction network. The software used in this paper are available for download at https://sites.google.com/site/elliottande/ . The software is written in Python and uses the NetworkX library. Supplementary data are available at Bioinformatics online.

Here we consider the communications tactics appropriate for a group of agents that need to “swarm” together in a challenging communications environment. Swarms are increasingly important in a number of applications, including land, air, sea and space exploration, and their constituent agents could be satellites, drones, or other autonomous vehicles. A particularly difficult problem is to autonomously connect a swarm of agents together in a situation where stringent communication constraints are present, whether due to a need for stealth, restricted on-board power, external requirements to avoid certain broadcast directions, or equipment & hardware limitations. Here we present a novel, discrete, geometry-free model applicable to multi-agent swarm communications where a group of agents need to connect together and where the constraints on the communications dominate the algorithmic outcomes. No global knowledge of the agent locations is held and hence our framework proposes agent-centric performance metrics. We demonstrate our model using a set of candidate connectivity tactics and we show how simulated outcome distributions, risks and connectivity depend on the ratio of information gain to information loss. We also show that checking for excessive round-trip-times can be an effective minimal-information filter for determining which agents to no longer target with messages. The framework and algorithms that are presented here have wider application in testing efficient communication tactics across agent swarms in designated scenarios and testing the connectivity outcomes for future systems and missions.

Importance: Non-healing diabetic ulcerations of the foot lead to amputations and premature mortality. Microburst Insulin Infusion has demonstrated an ability to accelerate healing in otherwise non-healing wounds. Objective: To demonstrate the benefit of adding Microburst Insulin Infusion to conventional diabetic wound care to significantly decrease wound healing time. Methods: A case series of five patients received Microburst Insulin Infusion therapy for significant peripheral diabetic ulcerations after failing conventional wound care. These five cases were treated from 4 independent Microburst Insulin Infusion clinics. Four of the wounds exceeded 6 cm². Patient charts were reviewed and relevant data was collected. All individuals in this manuscript have given written informed consent to publish these case details. Setting: Multicenter referral clinics providing Microburst Insulin Infusion Therapy Exposure: Microburst Insulin Infusion is an adjunctive treatment to conventional diabetic therapy performed in an outpatient clinic setting. A weight based oral glucose dose is administered while pulsatile intravenous insulin is delivered by the Bionica Microdose pump. The treatment is comprised of three 1 hour sessions and occurs up to five times a week, when the patient presents with un-healing wounds. Main Outcomes and Measures: Time to wound healing. A secondary outcome was failure of wound healing. Hypothesis for this study was formulated post treatment. Results: A significant decrease in wound healing time was observed when utilizing Microburst Insulin Infusion. The mean time to complete healing was 84.2 days compared to 133 days in published literature(1). The patient with a foot wound measuring an amazing 228.6 cm² healed in 102 days and amputation was not necessary. There were no treatment failures in this small series. As a result of decreased healing time, there was an absence of infection and no amputations were required for these wounds. Conclusion and Relevance: The addition of Microburst Insulin Infusion therapy resulted in a shortening of the time to healing by 49 days (7 weeks) for patients with poor response to conventional wound care. This is a 37% reduction in the time to heal thus reducing risk of infection and additional healthcare costs. The mechanism of action of Microburst Insulin Infusion in healing diabetic wounds is still unclear, but may involve an improved cellular metabolism, decreased inflammation and increased levels of Nitric oxide that enhance peripheral vascular supply and tissue healing.

This paper is motivated by the task of detecting anomalies in networks of financial transactions, with accounts as nodes and a directed weighted edge between two nodes denoting a money transfer. The weight of the edge is the transaction amount. Examples of anomalies in networks include long paths of large transaction amounts, rings of large payments, and cliques of accounts. There are many methods available which detect such specific structures in networks. Here we introduce a method which is able to detect previously unspecified anomalies in networks. The method is based on a combination of features from network comparison and spectral analysis as well as local statistics, yielding 140 main features. We then use a simple feature sum method, as well as a random forest method, in order to classify nodes as normal or anomalous. We test the method first on synthetic networks which we generated, and second on a set of synthetic networks which were generated without the methods team having access to the ground truth. The first set of synthetic networks was split in a training set of 70 percent of the networks, and a test set of 30 percent of the networks. The resulting classifier was then applied to the second set of synthetic networks. We compare our method with Oddball, a widely used method for anomaly detection in networks, as well as to random classification. While Oddball outperforms random classification, both our feature sum method and our random forest method outperform Oddball. On the test set, the random forest outperforms feature sum, whereas on the second synthetic data set, initially feature sum tends to pick up more anomalies than random forest, with this behaviour reversing for lower-scoring anomalies. In all cases, the top 2 percent of flagged anomalies contained on average over 90 percent of the planted anomalies.