Staying afloat in the sensor data deluge

Graph neural network-based anomaly detection for river network systems

Background

Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology.Anomaly detection is crucial for identifying erroneous patterns in sensor data, but can be a challenging task due to the complexity and variability of the data, even under typical conditions. This paper presents a solution to the challenging task of anomaly detection for river network sensor data, which is essential for accurate and continuous monitoring.

Methods

We use a graph neural network model, the recently proposed Graph Deviation Network (GDN), which employs graph attention-based forecasting to capture the complex spatio-temporal relationships between sensors. We propose an alternate anomaly threshold criteria for the model, GDN+, based on the learned graph. To evaluate the model's efficacy, we introduce new benchmarking simulation experiments with highly-sophisticated dependency structures and subsequence anomalies of various types. We also introduce software called gnnad.

Results

We further examine the strengths and weaknesses of this baseline approach, GDN, in comparison to other benchmarking methods on complex real-world river network data.

Conclusions

Findings suggest that GDN+ outperforms the baseline approach in high-dimensional data, while also providing improved interpretability.

Seasonal variations of polycyclic aromatic hydrocarbons in coastal sediments of a marine resource hot spot: the case of pars special economic energy zone, Iran

Polycyclic aromatic hydrocarbons (PAHs) are an important group of compounds of major environmental concern, which are in the class of persistent organic pollutants. Therefore, the key purpose of this research was to analyze seasonal fluctuations and to determine the probability of polycyclic aromatic hydrocarbons in coastal sediments of the Iranian Marine Resource Center based on the evaluation of 16 US-EPA important PAH compounds. These compounds have been collected from intertidal sediments located in the marine resources of southern Iran in different seasons. These samples of the surficial sediment were collected at the PSEEZ area using a stainless steel grab sampler in four seasons, from depths between 0.5 and 30 m. Surface sediment samples were removed by spoons and carefully placed in an aluminum foil; they were taken to the laboratory on ice and held at 20° C until their study. After extraction, by using a rotary evaporator apparatus, samples were condensed. The assay was added to roughly 2 g of activated copper flasks in the refrigerator for 36 h for desulfurization. Among different seasons, the highest concentration was observed in winter, with a mean of 281.3 ng g^-1. According to ecological risk assessment (concentrations of possible effects, low effect range, degree of threshold effects, and median effect range), PAH risks in surface sediments of PSEEZ were lower than the threshold results levels (TEL), possible effects levels (PEL), low range of effects (ERL), and median range of effects (ERM), indicating that a biological effect would rarely occur. The dry weight scale of the concentration of ∑PAHs ranges from 145.7 to 348.42 ng g^-1 with a mean quantity of 260.52 ng g^-1. Therefore, according to the amount of ∑PAH concentration, the sediments in the PSEEZ area indicated moderate to heavy pollutions. In this way, the sedimentary surface ecosystems of the Persian Gulf were considered as moderately polluted compared with other ecosystems worldwide. Our study highlighted some of the research gaps in PAH contamination studies and the level of PAH contamination. Therefore, this study will provide a scientific background, planning, and policies for PAH pollution control and environmental protection in Iran and similar regions around the world.

High frequency data provide new insights into evaluating and modeling nitrogen retention in reservoirs

Freshwater ecosystems including lakes and reservoirs are hot spots for retention of excess nitrogen (N) from anthropogenic sources, providing valuable ecological services for downstream and coastal ecosystems. Despite previous investigations, current quantitative understanding on the influential factors and underlying mechanisms of N retention in lentic freshwater systems is insufficient due to data paucity and limitation of modeling techniques. Our ability to reliably predict N retention for these systems therefore remains uncertain. Emerging high frequency monitoring techniques and well-developed ecosystem modeling shed light on this issue. In the present study, we explored the retention of NO₃-N during a five-year period (2013-2017) in both annual and weekly scales in a highly flushed reservoir in Germany. We found that annual-averaged NO₃-N retention efficiency could be up to 17% with an overall retention efficiency of ∼4% in such a system characterized by a water residence time (WRT) of ∼4 days. On the weekly scale, the reservoir displayed negative retention in winter (i.e. a source of NO₃-N) and high positive retention in summer (i.e. a sink for NO₃-N). We further identified the critical role of Chl-a concentration together with the well-recognized effects from WRT in dictating NO₃-N retention efficiency, implying the significance of biological processes including phytoplankton dynamics in driving NO₃-N retention. Furthermore, our modeling approach showed that an established process-based ecosystem model (PCLake) accounted for 58.0% of the variance in NO₃-N retention efficiency, whereas statistical models obtained a lower value (40.5%). This finding exemplified the superior predictive power of process-based models over statistical models whenever ecological processes were at play. Overall, our study highlights the importance of high frequency data in providing new insights into evaluating and modeling N retention in reservoirs.

The role of satellite remote sensing in structured ecosystem risk assessments

The current set of global conservation targets requires methods for monitoring the changing status of ecosystems. Protocols for ecosystem risk assessment are uniquely suited to this task, providing objective syntheses of a wide range of data to estimate the likelihood of ecosystem collapse. Satellite remote sensing can deliver ecologically relevant, long-term datasets suitable for analysing changes in ecosystem area, structure and function at temporal and spatial scales relevant to risk assessment protocols. However, there is considerable uncertainty about how to select and effectively utilise remotely sensed variables for risk assessment. Here, we review the use of satellite remote sensing for assessing spatial and functional changes of ecosystems, with the aim of providing guidance on the use of these data in ecosystem risk assessment. We suggest that decisions on the use of satellite remote sensing should be made a priori and deductively with the assistance of conceptual ecosystem models that identify the primary indicators representing the dynamics of a focal ecosystem.

Wireless Concrete Strength Monitoring of Wind Turbine Foundations

Wind turbine foundations are typically cast in place, leaving the concrete to mature under environmental conditions that vary in time and space. As a result, there is uncertainty around the concrete’s initial performance, and this can encourage both costly over-design and inaccurate prognoses of structural health. Here, we demonstrate the field application of a dense, wireless thermocouple network to monitor the strength development of an onshore, reinforced-concrete wind turbine foundation. Up-to-date methods in fly ash concrete strength and maturity modelling are used to estimate the distribution and evolution of foundation strength over 29 days of curing. Strength estimates are verified by core samples, extracted from the foundation base. In addition, an artificial neural network, trained using temperature data, is exploited to demonstrate that distributed concrete strengths can be estimated for foundations using only sparse thermocouple data. Our techniques provide a practical alternative to computational models, and could assist site operators in making more informed decisions about foundation design, construction, operation and maintenance.

Automatic High Frequency Monitoring for Improved Lake and Reservoir Management

Recent technological developments have increased the number of variables being monitored in lakes and reservoirs using automatic high frequency monitoring (AHFM). However, design of AHFM systems and posterior data handling and interpretation are currently being developed on a site-by-site and issue-by-issue basis with minimal standardization of protocols or knowledge sharing. As a result, many deployments become short-lived or underutilized, and many new scientific developments that are potentially useful for water management and environmental legislation remain underexplored. This Critical Review bridges scientific uses of AHFM with their applications by providing an overview of the current AHFM capabilities, together with examples of successful applications. We review the use of AHFM for maximizing the provision of ecosystem services supplied by lakes and reservoirs (consumptive and non consumptive uses, food production, and recreation), and for reporting lake status in the EU Water Framework Directive. We also highlight critical issues to enhance the application of AHFM, and suggest the establishment of appropriate networks to facilitate knowledge sharing and technological transfer between potential users. Finally, we give advice on how modern sensor technology can successfully be applied on a larger scale to the management of lakes and reservoirs and maximize the ecosystem services they provide.

Conceptions of Good Science in Our Data-Rich World

Scientists have been debating for centuries the nature of proper scientific methods. Currently, criticisms being thrown at data-intensive science are reinvigorating these debates. However, many of these criticisms represent long-standing conflicts over the role of hypothesis testing in science and not just a dispute about the amount of data used. Here, we show that an iterative account of scientific methods developed by historians and philosophers of science can help make sense of data-intensive scientific practices and suggest more effective ways to evaluate this research. We use case studies of Darwin's research on evolution by natural selection and modern-day research on macrosystems ecology to illustrate this account of scientific methods and the innovative approaches to scientific evaluation that it encourages. We point out recent changes in the spheres of science funding, publishing, and education that reflect this richer account of scientific practice, and we propose additional reforms.

New Approaches to Marine Conservation Through the Scaling Up of Ecological Data

In an era of rapid global change, conservation managers urgently need improved tools to track and counter declining ecosystem conditions. This need is particularly acute in the marine realm, where threats are out of sight, inadequately mapped, cumulative, and often poorly understood, thereby generating impacts that are inefficiently managed. Recent advances in macroecology, statistical analysis, and the compilation of global data will play a central role in improving conservation outcomes, provided that global, regional, and local data streams can be integrated to produce locally relevant and interpretable outputs. Progress will be assisted by (a) expanded rollout of systematic surveys that quantify species patterns, including some carried out with help from citizen scientists; (b) coordinated experimental research networks that utilize large-scale manipulations to identify mechanisms underlying these patterns;

Digital technology and the conservation of nature

Digital technology is changing nature conservation in increasingly profound ways. We describe this impact and its significance through the concept of 'digital conservation', which we found to comprise five pivotal dimensions: data on nature, data on people, data integration and analysis, communication and experience, and participatory governance. Examining digital innovation in nature conservation and addressing how its development, implementation and diffusion may be steered, we warn against hypes, techno-fix thinking, good news narratives and unverified assumptions. We identify a need for rigorous evaluation, more comprehensive consideration of social exclusion, frameworks for regulation and increased multi-sector as well as multi-discipline awareness and cooperation. Along the way, digital technology may best be reconceptualised by conservationists from something that is either good or bad, to a dual-faced force in need of guidance.

Building a multi-scaled geospatial temporal ecology database from disparate data sources: fostering open science and data reuse

Although there are considerable site-based data for individual or groups of ecosystems, these datasets are widely scattered, have different data formats and conventions, and often have limited accessibility. At the broader scale, national datasets exist for a large number of geospatial features of land, water, and air that are needed to fully understand variation among these ecosystems. However, such datasets originate from different sources and have different spatial and temporal resolutions. By taking an open-science perspective and by combining site-based ecosystem datasets and national geospatial datasets, science gains the ability to ask important research questions related to grand environmental challenges that operate at broad scales. Documentation of such complicated database integration efforts, through peer-reviewed papers, is recommended to foster reproducibility and future use of the integrated database. Here, we describe the major steps, challenges, and considerations in building an integrated database of lake ecosystems, called LAGOS (LAke multi-scaled GeOSpatial and temporal database), that was developed at the sub-continental study extent of 17 US states (1,800,000 km²). LAGOS includes two modules: LAGOS_GEO, with geospatial data on every lake with surface area larger than 4 ha in the study extent (~50,000 lakes), including climate, atmospheric deposition, land use/cover, hydrology, geology, and topography measured across a range of spatial and temporal extents; and LAGOS_LIMNO, with lake water quality data compiled from ~100 individual datasets for a subset of lakes in the study extent (~10,000 lakes). Procedures for the integration of datasets included: creating a flexible database design; authoring and integrating metadata; documenting data provenance; quantifying spatial measures of geographic data; quality-controlling integrated and derived data; and extensively documenting the database. Our procedures make a large, complex, and integrated database reproducible and extensible, allowing users to ask new research questions with the existing database or through the addition of new data. The largest challenge of this task was the heterogeneity of the data, formats, and metadata. Many steps of data integration need manual input from experts in diverse fields, requiring close collaboration.

Spatial and temporal epidemiological analysis in the Big Data era

Concurrent with global economic development in the last 50 years, the opportunities for the spread of existing diseases and emergence of new infectious pathogens, have increased substantially. The activities associated with the enormously intensified global connectivity have resulted in large amounts of data being generated, which in turn provides opportunities for generating knowledge that will allow more effective management of animal and human health risks. This so-called Big Data has, more recently, been accompanied by the Internet of Things which highlights the increasing presence of a wide range of sensors, interconnected via the Internet. Analysis of this data needs to exploit its complexity, accommodate variation in data quality and should take advantage of its spatial and temporal dimensions, where available. Apart from the development of hardware technologies and networking/communication infrastructure, it is necessary to develop appropriate data management tools that make this data accessible for analysis. This includes relational databases, geographical information systems and most recently, cloud-based data storage such as Hadoop distributed file systems. While the development in analytical methodologies has not quite caught up with the data deluge, important advances have been made in a number of areas, including spatial and temporal data analysis where the spectrum of analytical methods ranges from visualisation and exploratory analysis, to modelling. While there used to be a primary focus on statistical science in terms of methodological development for data analysis, the newly emerged discipline of data science is a reflection of the challenges presented by the need to integrate diverse data sources and exploit them using novel data- and knowledge-driven modelling methods while simultaneously recognising the value of quantitative as well as qualitative analytical approaches. Machine learning regression methods, which are more robust and can handle large datasets faster than classical regression approaches, are now also used to analyse spatial and spatio-temporal data. Multi-criteria decision analysis methods have gained greater acceptance, due in part, to the need to increasingly combine data from diverse sources including published scientific information and expert opinion in an attempt to fill important knowledge gaps. The opportunities for more effective prevention, detection and control of animal health threats arising from these developments are immense, but not without risks given the different types, and much higher frequency, of biases associated with these data.

A data management and publication workflow for a large-scale, heterogeneous sensor network

It is common for hydrology researchers to collect data using in situ sensors at high frequencies, for extended durations, and with spatial distributions that produce data volumes requiring infrastructure for data storage, management, and sharing. The availability and utility of these data in addressing scientific questions related to water availability, water quality, and natural disasters relies on effective cyberinfrastructure that facilitates transformation of raw sensor data into usable data products. It also depends on the ability of researchers to share and access the data in useable formats. In this paper, we describe a data management and publication workflow and software tools for research groups and sites conducting long-term monitoring using in situ sensors. Functionality includes the ability to track monitoring equipment inventory and events related to field maintenance. Linking this information to the observational data is imperative in ensuring the quality of sensor-based data products. We present these tools in the context of a case study for the innovative Urban Transitions and Aridregion Hydrosustainability (iUTAH) sensor network. The iUTAH monitoring network includes sensors at aquatic and terrestrial sites for continuous monitoring of common meteorological variables, snow accumulation and melt, soil moisture, surface water flow, and surface water quality. We present the overall workflow we have developed for effectively transferring data from field monitoring sites to ultimate end-users and describe the software tools we have deployed for storing, managing, and sharing the sensor data. These tools are all open source and available for others to use.

The bright side of transposons in crop evolution

The past decades have revealed an unexpected yet prominent role of so-called 'junk DNA' in the regulation of gene expression, thereby challenging our view of the mechanisms underlying phenotypic evolution. In particular, several mechanisms through which transposable elements (TEs) participate in functional genome diversity have been depicted, bringing to light the 'TEs bright side'. However, the relative contribution of those mechanisms and, more generally, the importance of TE-based polymorphisms on past and present phenotypic variation in crops species remain poorly understood. Here, we review current knowledge on both issues, and discuss how analyses of massively parallel sequencing data combined with statistical methodologies and functional validations will help unravelling the impact of TEs on crop evolution in a near future.

Workflow Systems for Science: Concepts and Tools

The wide availability of high-performance computing systems, Grids and Clouds, allowed scientists and engineers to implement more and more complex applications to access and process large data repositories and run scientific experiments in silico on distributed computing platforms. Most of these applications are designed as workflows that include data analysis, scientific computation methods, and complex simulation techniques. Scientific applications require tools and high-level mechanisms for designing and executing complex workflows. For this reason, in the past years, many efforts have been devoted towards the development of distributed workflow management systems for scientific applications. This paper discusses basic concepts of scientific workflows and presents workflow system tools and frameworks used today for the implementation of application in science and engineering on high-performance computers and distributed systems. In particular, the paper reports on a selection of workflow systems largely used for solving scientific problems and discusses some open issues and research challenges in the area.