scholarly journals Can machine learning extract the mechanisms controlling phytoplankton growth from large-scale observations? – A proof-of-concept study

2021 ◽  
Vol 18 (6) ◽  
pp. 1941-1970
Author(s):  
Christopher Holder ◽  
Anand Gnanadesikan
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Phytoplankton Growth ◽  
Qualitative Assessment ◽  
Future Research ◽  
Proof Of Concept ◽  
Physiological Mechanisms ◽  
Concept Study ◽  
Phytoplankton Growth Rate ◽  
The Right

Abstract. A key challenge for biological oceanography is relating the physiological mechanisms controlling phytoplankton growth to the spatial distribution of those phytoplankton. Physiological mechanisms are often isolated by varying one driver of growth, such as nutrient or light, in a controlled laboratory setting producing what we call “intrinsic relationships”. We contrast these with the “apparent relationships” which emerge in the environment in climatological data. Although previous studies have found machine learning (ML) can find apparent relationships, there has yet to be a systematic study examining when and why these apparent relationships diverge from the underlying intrinsic relationships found in the lab and how and why this may depend on the method applied. Here we conduct a proof-of-concept study with three scenarios in which biomass is by construction a function of time-averaged phytoplankton growth rate. In the first scenario, the inputs and outputs of the intrinsic and apparent relationships vary over the same monthly timescales. In the second, the intrinsic relationships relate averages of drivers that vary on hourly timescales to biomass, but the apparent relationships are sought between monthly averages of these inputs and monthly-averaged output. In the third scenario we apply ML to the output of an actual Earth system model (ESM). Our results demonstrated that when intrinsic and apparent relationships operate on the same spatial and temporal timescale, neural network ensembles (NNEs) were able to extract the intrinsic relationships when only provided information about the apparent relationships, while colimitation and its inability to extrapolate resulted in random forests (RFs) diverging from the true response. When intrinsic and apparent relationships operated on different timescales (as little separation as hourly versus daily), NNEs fed with apparent relationships in time-averaged data produced responses with the right shape but underestimated the biomass. This was because when the intrinsic relationship was nonlinear, the response to a time-averaged input differed systematically from the time-averaged response. Although the limitations found by NNEs were overestimated, they were able to produce more realistic shapes of the actual relationships compared to multiple linear regression. Additionally, NNEs were able to model the interactions between predictors and their effects on biomass, allowing for a qualitative assessment of the colimitation patterns and the nutrient causing the most limitation. Future research may be able to use this type of analysis for observational datasets and other ESMs to identify apparent relationships between biogeochemical variables (rather than spatiotemporal distributions only) and identify interactions and colimitations without having to perform (or at least performing fewer) growth experiments in a lab. From our study, it appears that ML can extract useful information from ESM output and could likely do so for observational datasets as well.

scholarly journals A Survey on Machine-Learning Based Security Design for Cyber-Physical Systems

2021 ◽  
Vol 11 (12) ◽  
pp. 5458
Author(s):  
Sangjun Kim ◽  
Kyung-Joon Park
Keyword(s):  
Machine Learning ◽  
Physical System ◽  
Large Scale ◽  
Computing System ◽  
Future Research ◽  
Physical Security ◽  
Computing Systems ◽  
Physical Systems ◽  
Security Research ◽  
Simultaneous Control

A cyber-physical system (CPS) is the integration of a physical system into the real world and control applications in a computing system, interacting through a communications network. Network technology connecting physical systems and computing systems enables the simultaneous control of many physical systems and provides intelligent applications for them. However, enhancing connectivity leads to extended attack vectors in which attackers can trespass on the network and launch cyber-physical attacks, remotely disrupting the CPS. Therefore, extensive studies into cyber-physical security are being conducted in various domains, such as physical, network, and computing systems. Moreover, large-scale and complex CPSs make it difficult to analyze and detect cyber-physical attacks, and thus, machine learning (ML) techniques have recently been adopted for cyber-physical security. In this survey, we provide an extensive review of the threats and ML-based security designs for CPSs. First, we present a CPS structure that classifies the functions of the CPS into three layers: the physical system, the network, and software applications. Then, we discuss the taxonomy of cyber-physical attacks on each layer, and in particular, we analyze attacks based on the dynamics of the physical system. We review existing studies on detecting cyber-physical attacks with various ML techniques from the perspectives of the physical system, the network, and the computing system. Furthermore, we discuss future research directions for ML-based cyber-physical security research in the context of real-time constraints, resiliency, and dataset generation to learn about the possible attacks.

scholarly journals Using in situ simulation to improve care of the acutely ill patient by enhancing interprofessional working: a qualitative proof of concept study in primary care in England

BMJ Open ◽  
2019 ◽  
Vol 9 (7) ◽  
pp. e028572
Author(s):  
Amy Halls ◽  
Mohan Kanagasundaram ◽  
Margaret Lau-Walker ◽  
Hilary Diack ◽  
Simon Bettles
Keyword(s):  
Primary Care ◽  
Training Session ◽  
Medical Emergency ◽  
Future Research ◽  
Proof Of Concept ◽  
In Situ Simulation ◽  
Concept Study ◽  
Interprofessional Working ◽  
General Practices

ObjectiveAcutely unwell patients in the primary care setting are uncommon, but their successful management requires involvement from staff (clinical and non-clinical) working as a cohesive team. Despite the advantages of interprofessional education being well documented, there is little research evidence of this within primary care. Enhancing interprofessional working could ultimately improve care of the acutely ill patient. This proof of concept study aimed to develop an in situ simulation of a medical emergency to use within primary care, and assess its acceptability and utility through participants’ reported experiences.SettingThree research-active General Practices in south east England. Nine staff members per practice consented to participate, representing clinical and non-clinical professions.MethodsThe intervention of an in situ simulation scenario of a cardiac arrest was developed by the research team. For the evaluation, staff participated in individual qualitative semistructured interviews following the in situ simulation: these focused on their experiences of participating, with particular attention on interdisciplinary training and potential future developments of the in situ simulation.ResultsThe in situ simulation was appropriate for use within the participating General Practices. Qualitative thematic analysis of the interviews identified four themes: (1) apprehension and (un)willing participation, (2) reflection on the simulation design, (3) experiences of the scenario and (4) training.ConclusionsThis study suggests in situ simulation can be an acceptable approach for interdisciplinary team training within primary care, being well-received by practices and staff. This contributes to a fuller understanding of how in situ simulation can benefit both workforce and patients. Future research is needed to further refine the in situ simulation training session.

Alignment for Advanced Machine Learning Systems

2020 ◽  
pp. 342-382
Author(s):  
Jessica Taylor ◽  
Eliezer Yudkowsky ◽  
Patrick LaVictoire ◽  
Andrew Critch
Keyword(s):  
Machine Learning ◽  
Side Effects ◽  
Objective Function ◽  
Unintended Consequences ◽  
Learning Systems ◽  
Large Impact ◽  
Future Research ◽  
Objective Functions ◽  
Research Areas ◽  
The Right

This chapter surveys eight research areas organized around one question: As learning systems become increasingly intelligent and autonomous, what design principles can best ensure that their behavior is aligned with the interests of the operators? The chapter focuses on two major technical obstacles to AI alignment: the challenge of specifying the right kind of objective functions and the challenge of designing AI systems that avoid unintended consequences and undesirable behavior even in cases where the objective function does not line up perfectly with the intentions of the designers. The questions surveyed include the following: How can we train reinforcement learners to take actions that are more amenable to meaningful assessment by intelligent overseers? What kinds of objective functions incentivize a system to “not have an overly large impact” or “not have many side effects”? The chapter discusses these questions, related work, and potential directions for future research, with the goal of highlighting relevant research topics in machine learning that appear tractable today.

scholarly journals From Proof of Concept to Scalable Policies: Challenges and Solutions, with an Application

2017 ◽  
Vol 31 (4) ◽  
pp. 73-102 ◽  
Author(s):  
Abhijit Banerjee ◽  
Rukmini Banerji ◽  
James Berry ◽  
Esther Duflo ◽  
Harini Kannan ◽  
...  
Keyword(s):  
Randomized Controlled Trials ◽  
Large Scale ◽  
Fine Tuning ◽  
Controlled Trials ◽  
Proof Of Concept ◽  
Government Schools ◽  
Randomized Controlled ◽  
Randomized Control ◽  
The Right ◽  
Actual Learning

The promise of randomized controlled trials is that evidence gathered through the evaluation of a specific program helps us—possibly after several rounds of fine-tuning and multiple replications in different contexts—to inform policy. However, critics have pointed out that a potential constraint in this agenda is that results from small “proof-of-concept” studies run by nongovernment organizations may not apply to policies that can be implemented by governments on a large scale. After discussing the potential issues, this paper describes the journey from the original concept to the design and evaluation of scalable policy. We do so by evaluating a series of strategies that aim to integrate the nongovernment organization Pratham’s “Teaching at the Right Level” methodology into elementary schools in India. The methodology consists of reorganizing instruction based on children’s actual learning levels, rather than on a prescribed syllabus, and has previously been shown to be very effective when properly implemented. We present evidence from randomized controlled trials involving some designs that failed to produce impacts within the regular schooling system but still helped shape subsequent versions of the program. As a result of this process, two versions of the programs were developed that successfully raised children’s learning levels using scalable models in government schools. We use this example to draw general lessons about using randomized control trials to design scalable policies.

scholarly journals A Proof of Concept Study of Using Machine-Learning in Artificial Aortic Valve Design: From Leaflet Design to Stress Analysis

2019 ◽  
Vol 6 (4) ◽  
pp. 104 ◽  
Author(s):  
Liang Liang ◽  
Bill Sun
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Aortic Valve ◽  
Stress Analysis ◽  
Heart Valves ◽  
Deep Neural Networks ◽  
Design Parameters ◽  
Attractive Alternative ◽  
Proof Of Concept ◽  
Concept Study

Artificial heart valves, used to replace diseased human heart valves, are life-saving medical devices. Currently, at the device development stage, new artificial valves are primarily assessed through time-consuming and expensive benchtop tests or animal implantation studies. Computational stress analysis using the finite element (FE) method presents an attractive alternative to physical testing. However, FE computational analysis requires a complex process of numeric modeling and simulation, as well as in-depth engineering expertise. In this proof of concept study, our objective was to develop machine learning (ML) techniques that can estimate the stress and deformation of a transcatheter aortic valve (TAV) from a given set of TAV leaflet design parameters. Two deep neural networks were developed and compared: the autoencoder-based ML-models and the direct ML-models. The ML-models were evaluated through Monte Carlo cross validation. From the results, both proposed deep neural networks could accurately estimate the deformed geometry of the TAV leaflets and the associated stress distributions within a second, with the direct ML-models (ML-model-d) having slightly larger errors. In conclusion, although this is a proof-of-concept study, the proposed ML approaches have demonstrated great potential to serve as a fast and reliable tool for future TAV design.

Sign in / Sign up

Export Citation Format

Share Document