Sekou L. Remy

Julian Kuehnert, Deborah McGlynn, Sekou L. Remy et al.

As acute climate change impacts weather and climate variability, there is increased demand for robust climate impact model predictions from which forecasts of the impacts can be derived. The quality of those predictions are limited by the climate drivers for the impact models which are nonlinear and highly variable in nature. One way to estimate the uncertainty of the model drivers is to assess the distribution of ensembles of climate forecasts. To capture the uncertainty in the impact model outputs associated with the distribution of the input climate forecasts, each individual forecast ensemble member has to be propagated through the physical model which can imply high computational costs. It is therefore desirable to train a surrogate model which allows predictions of the uncertainties of the output distribution in ensembles of climate drivers, thus reducing resource demands. This study considers a climate driven disease model, the Liverpool Malaria Model (LMM), which predicts the malaria transmission coefficient R0. Seasonal ensembles forecasts of temperature and precipitation with a 6-month horizon are propagated through the model, predicting the distribution of transmission time series. The input and output data is used to train surrogate models in the form of a Random Forest Quantile Regression (RFQR) model and a Bayesian Long Short-Term Memory (BLSTM) neural network. Comparing the predictive performance, the RFQR better predicts the time series of the individual ensemble member, while the BLSTM offers a direct way to construct a combined distribution for all ensemble members. An important element of the proposed methodology is that accounting for non-normal distributions of climate forecast ensembles can be captured naturally by a Bayesian formulation.

Michiaki Tatsubori, Takao Moriyama, Tatsuya Ishikawa et al.

When providing the boundary conditions for hydrological flood models and estimating the associated risk, interpolating precipitation at very high temporal resolutions (e.g. 5 minutes) is essential not to miss the cause of flooding in local regions. In this paper, we study optical flow-based interpolation of globally available weather radar images from satellites. The proposed approach uses deep neural networks for the interpolation of multiple video frames, while terrain information is combined with temporarily coarse-grained precipitation radar observation as inputs for self-supervised training. An experiment with the Meteonet radar precipitation dataset for the flood risk simulation in Aude, a department in Southern France (2018), demonstrated the advantage of the proposed method over a linear interpolation baseline, with up to 20% error reduction.

Julian Kuehnert, Hiwot Tadesse, Chris Dearden et al.

Geospatial observations combined with computational models have become key to understanding the physical systems of our environment and enable the design of best practices to reduce societal harm. Cloud-based deployments help to scale up these modeling and AI workflows. Yet, for practitioners to make robust conclusions, model tuning and testing is crucial, a resource intensive process which involves the variation of model input variables. We have developed the Variational Exploration Module which facilitates the optimization and validation of modeling workflows deployed in the cloud by orchestrating workflow executions and using Bayesian and machine learning-based methods to analyze model behavior. User configurations allow the combination of diverse sampling strategies in multi-agent environments. The flexibility and robustness of the model-agnostic module is demonstrated using real-world applications.

Sekou L. Remy, Oliver E. Bent

In this work we present a framework which may transform research and praxis in epidemic planning. Introduced in the context of the ongoing COVID-19 pandemic, we provide a concrete demonstration of the way algorithms may learn from epidemiological models to scale their value for epidemic preparedness. Our contributions in this work are two fold: 1) a novel platform which makes it easy for decision making stakeholders to interact with epidemiological models and algorithms developed within the Machine learning community, and 2) the release of this work under the Apache-2.0 License. The objective of this paper is not to look closely at any particular models or algorithms, but instead to highlight how they can be coupled and shared to empower evidence-based decision making.

Sharon Okwako, Irene Wanyana, Alice Namale et al.

The COVID-19 crisis has emphasized the need for scientific methods such as machine learning to speed up the discovery of solutions to the pandemic. Harnessing machine learning techniques requires quality data, skilled personnel and advanced compute infrastructure. In Africa, however, machine learning competencies and compute infrastructures are limited. This paper demonstrates a cross-border collaborative capacity building approach to the application of machine learning techniques in discovering answers to COVID-19 questions.

Parthasarathy Suryanarayanan, Prithwish Chakraborty, Piyush Madan et al.

In this work we introduce Disease Progression Modeling workbench 360 (DPM360) opensource clinical informatics framework for collaborative research and delivery of healthcare AI. DPM360, when fully developed, will manage the entire modeling life cycle, from data analysis (e.g., cohort identification) to machine learning algorithm development and prototyping. DPM360 augments the advantages of data model standardization and tooling (OMOP-CDM, Athena, ATLAS) provided by the widely-adopted OHDSI initiative with a powerful machine learning training framework, and a mechanism for rapid prototyping through automatic deployment of models as containerized services to a cloud environment.

Sekou L Remy, Aisha Walcott-Bryant, Nelson K Bore et al.

In popular usage, Data Gravity refers to the ability of a body of data to attract applications, services and other data. In this work we introduce a broader concept, "Digital Gravity" which includes not just data, but other elements of the AI/ML workflow. This concept is born out of our recent experiences in developing and deploying an AI-based decision support platform intended for use in a public health context. In addition to data, examples of additional considerations are compute (infrastructure and software), DevSecOps (personnel and practices), algorithms/programs, control planes, middleware (considered separately from programs), and even companies/service providers. We discuss the impact of Digital Gravity on the pathway to adoption and suggest preliminary approaches to conceptualize and mitigate the friction caused by it.

Ndivhuwo Makondo, Arinze Lawrence Folarin, Simphiwe Nhlahla Zitha et al.

Previous work on policy learning for Malaria control has often formulated the problem as an optimization problem assuming the objective function and the search space have a specific structure. The problem has been formulated as multi-armed bandits, contextual bandits and a Markov Decision Process in isolation. Furthermore, an emphasis is put on developing new algorithms specific to an instance of Malaria control, while ignoring a plethora of simpler and general algorithms in the literature. In this work, we formally study the formulation of Malaria control and present a comprehensive analysis of several formulations used in the literature. In addition, we implement and analyze several reinforcement learning algorithms in all formulations and compare them to black box optimization. In contrast to previous work, our results show that simple algorithms based on Upper Confidence Bounds are sufficient for learning good Malaria policies, and tend to outperform their more advanced counterparts on the malaria OpenAI Gym environment.

Parthasarathy Suryanarayanan, Ching-Huei Tsou, Ananya Poddar et al.

The Coronavirus disease 2019 (COVID-19) global pandemic has transformed almost every facet of human society throughout the world. Against an emerging, highly transmissible disease with no definitive treatment or vaccine, governments worldwide have implemented non-pharmaceutical intervention (NPI) to slow the spread of the virus. Examples of such interventions include community actions (e.g. school closures, restrictions on mass gatherings), individual actions (e.g. mask wearing, self-quarantine), and environmental actions (e.g. public facility cleaning). We present the Worldwide Non-pharmaceutical Interventions Tracker for COVID-19 (WNTRAC), a comprehensive dataset consisting of over 6,000 NPIs implemented worldwide since the start of the pandemic. WNTRAC covers NPIs implemented across 261 countries and territories, and classifies NPI measures into a taxonomy of sixteen NPI types. NPI measures are automatically extracted daily from Wikipedia articles using natural language processing techniques and manually validated to ensure accuracy and veracity. We hope that the dataset is valuable for policymakers, public health leaders, and researchers in modeling and analysis efforts for controlling the spread of COVID-19.

Skyler Speakman, Srihari Sridharan, Sekou Remy et al.

This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing an anomalous input. Detecting anomalies is a critical component for multiple machine learning problems including detecting adversarial noise. More broadly, this work is a step towards giving neural networks the ability to recognize an out-of-distribution sample. This is the first work to introduce "Subset Scanning" methods from the anomalous pattern detection domain to the task of detecting anomalous input of neural networks. Subset scanning treats the detection problem as a search for the most anomalous subset of node activations (i.e., highest scoring subset according to non-parametric scan statistics). Mathematical properties of these scoring functions allow the search to be completed in log-linear rather than exponential time while still guaranteeing the most anomalous subset of nodes in the network is identified for a given input. Quantitative results for detecting and characterizing adversarial noise are provided for CIFAR-10 images on a simple convolutional neural network. We observe an "interference" pattern where anomalous activations in shallow layers suppress the activation structure of the original image in deeper layers.

Ravi Kiran Raman, Roman Vaculin, Michael Hind et al.

Large-scale computational experiments, often running over weeks and over large datasets, are used extensively in fields such as epidemiology, meteorology, computational biology, and healthcare to understand phenomena, and design high-stakes policies affecting everyday health and economy. For instance, the OpenMalaria framework is a computationally-intensive simulation used by various non-governmental and governmental agencies to understand malarial disease spread and effectiveness of intervention strategies, and subsequently design healthcare policies. Given that such shared results form the basis of inferences drawn, technological solutions designed, and day-to-day policies drafted, it is essential that the computations are validated and trusted. In particular, in a multi-agent environment involving several independent computing agents, a notion of trust in results generated by peers is critical in facilitating transparency, accountability, and collaboration. Using a novel combination of distributed validation of atomic computation blocks and a blockchain-based immutable audits mechanism, this work proposes a universal framework for distributed trust in computations. In particular we address the scalaibility problem by reducing the storage and communication costs using a lossy compression scheme. This framework guarantees not only verifiability of final results, but also the validity of local computations, and its cost-benefit tradeoffs are studied using a synthetic example of training a neural network.

Sekou L. Remy

In this work, our aim is to identify whether the choice of virtualization strategy influences the performance of simulations in robotics. Performance is quantified in the error between a reference trajectory and the actual trajectory for the ball moving along the surface of a smooth plate. The two-sample Kolmogorov-Smirnov test is used to assess significance of variations in performance under the different experimental settings. Our results show that the selection of virtualization technology does have a significant effect on simulation, and moreover this effect can be amplified by the use of some operating systems. While these results are a strong cause for caution, they also provide reason for optimism for those considering 'repeatable robotics research' using virtualization.

Victor Akinwande, Sekou L. Remy

Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.

Oliver Bent, Sekou L. Remy, Stephen Roberts et al.

The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity. Healthcare policy makers across the globe are facing problems under challenging constraints, with limited tools to help them make data driven decisions. In this work we frame the process of finding an optimal malaria policy as a stochastic multi-armed bandit problem, and implement three agent based strategies to explore the policy space. We apply a Gaussian Process regression to the findings of each agent, both for comparison and to account for stochastic results from simulating the spread of malaria in a fixed population. The generated policy spaces are compared with published results to give a direct reference with human expert decisions for the same simulated population. Our novel approach provides a powerful resource for policy makers, and a platform which can be readily extended to capture future more nuanced policy spaces.

Jeff Kinnison, Sekou L. Remy

This paper presents a novel application of Genetic Algorithms(GAs) to quantify the performance of Platform as a Service (PaaS), a cloud service model that plays a critical role in both industry and academia. While Cloud benchmarks are not new, in this novel concept, the authors use a GA to take advantage of the elasticity in Cloud services in a graceful manner that was not previously possible. Using Google App Engine, Heroku, and Python Anywhere with three distinct classes of client computers running our GA codebase, we quantified the completion time for application of the GA to search for the parameters of controllers for dynamical systems. Our results show statistically significant differences in PaaS performance by vendor, and also that the performance of the PaaS performance is dependent upon the client that uses it. Results also show the effectiveness of our GA in determining the level of service of PaaS providers, and for determining if the level of service of one PaaS vendor is repeatable with another. Such a concept could then increase the appeal of PaaS Cloud services by making them more financially appealing.

Sekou L. Remy

Modern robotics often involves the use of web technologies as a means to cope with the complexity of design and operation. Many of these technologies have been formalized into standards, which are often avoided by those in robotics and controls because of a sometimes warranted fear that "the web" is too slow, or too uncertain for meaningful control applications. In this work we argue that while web technologies may not be applicable for all control, they should not be dismissed outright because they can provide critical help with system integration. Web technologies have also advanced significantly over the past decade. We present the details of an application of a web server to perform open and close-loop control (between 3Hz and 1kHz) over a variety of different network topologies. In our study we also consider the impact of a web browser to implement the control of the plant. Our results confirm that meaningful control can be performed using web technologies, and also highlight design choices that can limit their applicability.