The Next Decade of Big Data in Ecosystem Science

Challenges and directions in analytical paleobiology

Over the last 50 years, access to new data and analytical tools has expanded the study of analytical paleobiology, contributing to innovative analyses of biodiversity dynamics over Earth's history. Despite-or even spurred by-this growing availability of resources, analytical paleobiology faces deep-rooted obstacles that stem from the need for more equitable access to data and best practices to guide analyses of the fossil record. Recent progress has been accelerated by a collective push toward more collaborative, interdisciplinary, and open science, especially by early-career researchers. Here, we survey four challenges facing analytical paleobiology from an early-career perspective: (1) accounting for biases when interpreting the fossil record; (2) integrating fossil and modern biodiversity data; (3) building data science skills; and (4) increasing data accessibility and equity. We discuss recent efforts to address each challenge, highlight persisting barriers, and identify tools that have advanced analytical work. Given the inherent linkages between these challenges, we encourage discourse across disciplines to find common solutions. We also affirm the need for systemic changes that reevaluate how we conduct and share paleobiological research.

An Outlook for Deep Learning in Ecosystem Science

Rapid advances in hardware and software, accompanied by public- and private-sector investment, have led to a new generation of data-driven computational tools. Recently, there has been a particular focus on deep learning—a class of machine learning algorithms that uses deep neural networks to identify patterns in large and heterogeneous datasets. These developments have been accompanied by both hype and scepticism by ecologists and others. This review describes the context in which deep learning methods have emerged, the deep learning methods most relevant to ecosystem ecologists, and some of the problem domains they have been applied to. Deep learning methods have high predictive performance in a range of ecological contexts, leveraging the large data resources now available. Furthermore, deep learning tools offer ecosystem ecologists new ways to learn about ecosystem dynamics. In particular, recent advances in interpretable machine learning and in developing hybrid approaches combining deep learning and mechanistic models provide a bridge between pure prediction and causal explanation. We conclude by looking at the opportunities that deep learning tools offer ecosystem ecologists and assess the challenges in interpretability that deep learning applications pose.

Increased adoption of best practices in ecological forecasting enables comparisons of forecastability

Near-term iterative forecasting is a powerful tool for ecological decision support and has the potential to transform our understanding of ecological predictability. However, to this point, there has been no cross-ecosystem analysis of near-term ecological forecasts, making it difficult to synthesize diverse research efforts and prioritize future developments for this emerging field. In this study, we analyzed 178 near-term (≤10-yr forecast horizon) ecological forecasting papers to understand the development and current state of near-term ecological forecasting literature and to compare forecast accuracy across scales and variables. Our results indicated that near-term ecological forecasting is widespread and growing: forecasts have been produced for sites on all seven continents and the rate of forecast publication is increasing over time. As forecast production has accelerated, some best practices have been proposed and application of these best practices is increasing. In particular, data publication, forecast archiving, and workflow automation have all increased significantly over time. However, adoption of proposed best practices remains low overall: for example, despite the fact that uncertainty is often cited as an essential component of an ecological forecast, only 45% of papers included uncertainty in their forecast outputs. As the use of these proposed best practices increases, near-term ecological forecasting has the potential to make significant contributions to our understanding of forecastability across scales and variables. In this study, we found that forecastability (defined here as realized forecast accuracy) decreased in predictable patterns over 1-7 d forecast horizons. Variables that were closely related (i.e., chlorophyll and phytoplankton) displayed very similar trends in forecastability, while more distantly related variables (i.e., pollen and evapotranspiration) exhibited significantly different patterns. Increasing use of proposed best practices in ecological forecasting will allow us to examine the forecastability of additional variables and timescales in the future, providing a robust analysis of the fundamental predictability of ecological variables.

OUP accepted manuscript

Extreme events have increased in frequency globally, with a simultaneous surge in scientific interest about their ecological responses, particularly in sensitive freshwater, coastal, and marine ecosystems. We synthesized observational studies of extreme events in these aquatic ecosystems, finding that many studies do not use consistent definitions of extreme events. Furthermore, many studies do not capture ecological responses across the full spatial scale of the events. In contrast, sampling often extends across longer temporal scales than the event itself, highlighting the usefulness of long-term monitoring. Many ecological studies of extreme events measure biological responses but exclude chemical and physical responses, underscoring the need for integrative and multidisciplinary approaches. To advance extreme event research, we suggest prioritizing pre- and postevent data collection, including leveraging long-term monitoring; making intersite and cross-scale comparisons; adopting novel empirical and statistical approaches; and developing funding streams to support flexible and responsive data collection.

The complementarities of big data and intellectual capital on sustainable value creation; collective intelligence approach

It is evident in the literature that both intellectual capital and big data analytics create value to the organizations independently, but how threats, opportunities, capabilities and value creation for intellectual capital change with big data adoption is largely unexplored. This paper aims to develop an analytical framework for identifying challenges, opportunities, capabilities and value creation in the face of complementarity between big data and components of intellectual capital. The paper uses a Collective Intelligence approach as a theoretical background. Based on Structured Literature Review, the current study has developed an analytical framework for organizations to be used as a decision-making tool while making investment in big data and managing intellectual capital. Findings suggest that the scope of human capital has changed largely as now employees are expected much more than in the past with strong analytical, dynamic, technical and IT capabilities. Structural capital calls for new practices, routines and procedures to be adopted and old methods to unlearn whereas relational capital stresses the importance of network building and social media to create sustainable value for the society.

Collections Education: The Extended Specimen and Data Acumen

Biodiversity scientists must be fluent across disciplines; they must possess the quantitative, computational, and data skills necessary for working with large, complex data sets, and they must have foundational skills and content knowledge from ecology, evolution, taxonomy, and systematics. To effectively train the emerging workforce, we must teach science as we conduct science and embrace emerging concepts of data acumen alongside the knowledge, tools, and techniques foundational to organismal biology. We present an open education resource that updates the traditional plant collection exercise to incorporate best practices in twenty-first century collecting and to contextualize the activities that build data acumen. Students exposed to this resource gained skills and content knowledge in plant taxonomy and systematics, as well as a nuanced understanding of collections-based data resources. We discuss the importance of the extended specimen in fostering scientific discovery and reinforcing foundational concepts in biodiversity science, taxonomy, and systematics.

Effects of ignoring survey design information for data reuse

Data are currently being used, and reused, in ecological research at an unprecedented rate. To ensure appropriate reuse however, we need to ask the question: "Are aggregated databases currently providing the right information to enable effective and unbiased reuse?" We investigate this question, with a focus on designs that purposefully favor the selection of sampling locations (upweighting the probability of selection of some locations). These designs are common and examples are those designs that have uneven inclusion probabilities or are stratified. We perform a simulation experiment by creating data sets with progressively more uneven inclusion probabilities and examine the resulting estimates of the average number of individuals per unit area (density). The effect of ignoring the survey design can be profound, with biases of up to 250% in density estimates when naive analytical methods are used. This density estimation bias is not reduced by adding more data. Fortunately, the estimation bias can be mitigated by using an appropriate estimator or an appropriate model that incorporates the design information. These are only available however, when essential information about the survey design is available: the sample location selection process (e.g., inclusion probabilities), and/or covariates used in their specification. The results suggest that such information must be stored and served with the data to support meaningful inference and data reuse.

causalizeR: a text mining algorithm to identify causal relationships in scientific literature

Complex interactions among multiple abiotic and biotic drivers result in rapid changes in ecosystems worldwide. Predicting how specific interactions can cause ripple effects potentially resulting in abrupt shifts in ecosystems is of high relevance to policymakers, but difficult to quantify using data from singular cases. We present causalizeR (https://github.com/fjmurguzur/causalizeR), a text-processing algorithm that extracts causal relations from literature based on simple grammatical rules that can be used to synthesize evidence in unstructured texts in a structured manner. The algorithm extracts causal links using the relative position of nouns relative to the keyword of choice to extract the cause and effects of interest. The resulting database can be combined with network analysis tools to estimate the direct and indirect effects of multiple drivers at the network level, which is useful for synthesizing available knowledge and for hypothesis creation and testing. We illustrate the use of the algorithm by detecting causal relationships in scientific literature relating to the tundra ecosystem.

Modelling of ecological status of Polish lakes using deep learning techniques

Since 2000, after the Water Framework Directive came into force, aquatic ecosystems' bioassessment has acquired immense practical importance for water management. Currently, due to extensive scientific research and monitoring, we have gathered comprehensive hydrobiological databases. The amount of available data increases with each subsequent year of monitoring, and the efficient analysis of these data requires the use of proper mathematical tools. Our study challenges the comparison of the modelling potential between four indices for the ecological status assessment of lakes based on three groups of aquatic organisms, i.e. phytoplankton, phytobenthos and macrophytes. One of the deep learning techniques, artificial neural networks, has been used to predict values of four biological indices based on the limited set of the physicochemical parameters of water. All analyses were conducted separately for lakes with various stratification regimes as they function differently. The best modelling quality in terms of high values of coefficients of determination and low values of the normalised root mean square error was obtained for chlorophyll a followed by phytoplankton multimetric. A lower degree of fit was obtained in the networks for macrophyte index, and the poorest model quality was obtained for phytobenthos index. For all indices, modelling quality for non-stratified lakes was higher than this for stratified lakes, giving a higher percentage of variance explained by the networks and lower values of errors. Sensitivity analysis showed that among physicochemical parameters, water transparency (Secchi disk reading) exhibits the strongest relationship with the ecological status of lakes derived by phytoplankton and macrophytes. At the same time, all input variables indicated a negligible impact on phytobenthos index. In this way, different explanations of the relationship between biological and trophic variables were revealed.

Beyond ecosystem modeling: A roadmap to community cyberinfrastructure for ecological data-model integration

In an era of rapid global change, our ability to understand and predict Earth's natural systems is lagging behind our ability to monitor and measure changes in the biosphere. Bottlenecks to informing models with observations have reduced our capacity to fully exploit the growing volume and variety of available data. Here, we take a critical look at the information infrastructure that connects ecosystem modeling and measurement efforts, and propose a roadmap to community cyberinfrastructure development that can reduce the divisions between empirical research and modeling and accelerate the pace of discovery. A new era of data-model integration requires investment in accessible, scalable, and transparent tools that integrate the expertise of the whole community, including both modelers and empiricists. This roadmap focuses on five key opportunities for community tools: the underlying foundations of community cyberinfrastructure; data ingest; calibration of models to data; model-data benchmarking; and data assimilation and ecological forecasting. This community-driven approach is a key to meeting the pressing needs of science and society in the 21st century.

Research challenges and opportunities for using big data in global change biology

Global change biology has been entering a big data era due to the vast increase in availability of both environmental and biological data. Big data refers to large data volume, complex data sets, and multiple data sources. The recent use of such big data is improving our understanding of interactions between biological systems and global environmental changes. In this review, we first explore how big data has been analyzed to identify the general patterns of biological responses to global changes at scales from gene to ecosystem. After that, we investigate how observational networks and space-based big data have facilitated the discovery of emergent mechanisms and phenomena on the regional and global scales. Then, we evaluate the predictions of terrestrial biosphere under global changes by big modeling data. Finally, we introduce some methods to extract knowledge from big data, such as meta-analysis, machine learning, traceability analysis, and data assimilation. The big data has opened new research opportunities, especially for developing new data-driven theories for improving biological predictions in Earth system models, tracing global change impacts across different organismic levels, and constructing cyberinfrastructure tools to accelerate the pace of model-data integrations. These efforts will uncork the bottleneck of using big data to understand biological responses and adaptations to future global changes.

The reuse of public datasets in the life sciences: potential risks and rewards

The 'big data' revolution has enabled novel types of analyses in the life sciences, facilitated by public sharing and reuse of datasets. Here, we review the prodigious potential of reusing publicly available datasets and the associated challenges, limitations and risks. Possible solutions to issues and research integrity considerations are also discussed. Due to the prominence, abundance and wide distribution of sequencing data, we focus on the reuse of publicly available sequence datasets. We define 'successful reuse' as the use of previously published data to enable novel scientific findings. By using selected examples of successful reuse from different disciplines, we illustrate the enormous potential of the practice, while acknowledging the respective limitations and risks. A checklist to determine the reuse value and potential of a particular dataset is also provided. The open discussion of data reuse and the establishment of this practice as a norm has the potential to benefit all stakeholders in the life sciences.

Ecological Dynamics: Integrating Empirical, Statistical, and Analytical Methods

Understanding ecological processes and predicting long-term dynamics are ongoing challenges in ecology. To address these challenges, we suggest an approach combining mathematical analyses and Bayesian hierarchical statistical modeling with diverse data sources. Novel mathematical analysis of ecological dynamics permits a process-based understanding of conditions under which systems approach equilibrium, experience large oscillations, or persist in transient states. This understanding is improved by combining ecological models with empirical observations from a variety of sources. Bayesian hierarchical models explicitly couple process-based models and data, yielding probabilistic quantification of model parameters, system characteristics, and associated uncertainties. We outline relevant tools from dynamical analysis and hierarchical modeling and argue for their integration, demonstrating the value of this synthetic approach through a simple predator-prey example.

The global lake area, climate, and population dataset

An increasing population in conjunction with a changing climate necessitates a detailed understanding of water abundance at multiple spatial and temporal scales. Remote sensing has provided massive data volumes to track fluctuations in water quantity, yet contextualizing water abundance with other local, regional, and global trends remains challenging by often requiring large computational resources to combine multiple data sources into analytically-friendly formats. To bridge this gap and facilitate future freshwater research opportunities, we harmonized existing global datasets to create the Global Lake area, Climate, and Population (GLCP) dataset. The GLCP is a compilation of lake surface area for 1.42 + million lakes and reservoirs of at least 10 ha in size from 1995 to 2015 with co-located basin-level temperature, precipitation, and population data. The GLCP was created with FAIR (findable, accessible, interoperable, reusable) data principles in mind and retains unique identifiers from parent datasets to expedite interoperability. The GLCP offers critical data for basic and applied investigations of lake surface area and water quantity at local, regional, and global scales.

Measurement(s)	area of open water • temperature of air • volume of hydrological precipitation • population
Technology Type(s)	digital curation
Factor Type(s)	year • geographic location
Sample Characteristic - Environment	lake

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.12328214

Integrating data mining and transmission theory in the ecology of infectious diseases

Our understanding of ecological processes is built on patterns inferred from data. Applying modern analytical tools such as machine learning to increasingly high dimensional data offers the potential to expand our perspectives on these processes, shedding new light on complex ecological phenomena such as pathogen transmission in wild populations. Here, we propose a novel approach that combines data mining with theoretical models of disease dynamics. Using rodents as an example, we incorporate statistical differences in the life history features of zoonotic reservoir hosts into pathogen transmission models, enabling us to bound the range of dynamical phenomena associated with hosts, based on their traits. We then test for associations between equilibrium prevalence, a key epidemiological metric and data on human outbreaks of rodent-borne zoonoses, identifying matches between empirical evidence and theoretical predictions of transmission dynamics. We show how this framework can be generalized to other systems through a rubric of disease models and parameters that can be derived from empirical data. By linking life history components directly to their effects on disease dynamics, our mining-modelling approach integrates machine learning and theoretical models to explore mechanisms in the macroecology of pathogen transmission and their consequences for spillover infection to humans.

iEcology: Harnessing Large Online Resources to Generate Ecological Insights

Digital data are accumulating at unprecedented rates. These contain a lot of information about the natural world, some of which can be used to answer key ecological questions. Here, we introduce iEcology (i.e., internet ecology), an emerging research approach that uses diverse online data sources and methods to generate insights about species distribution over space and time, interactions and dynamics of organisms and their environment, and anthropogenic impacts. We review iEcology data sources and methods, and provide examples of potential research applications. We also outline approaches to reduce potential biases and improve reliability and applicability. As technologies and expertise improve, and costs diminish, iEcology will become an increasingly important means to gain novel insights into the natural world.

Treating Cancer as an Invasive Species

To cure a patient's cancer is to eradicate invasive cells from the ecosystem of the body. However, the ecologic complexity of this challenge is not well understood. Here we show how results from eradications of invasive mammalian species from islands-one of the few contexts in which invasive species have been regularly cleared-inform new research directions for treating cancer. We first summarize the epidemiologic characteristics of island invader eradications and cancer treatments by analyzing recent datasets from the Database of Invasive Island Species Eradications and The Cancer Genome Atlas, detailing the superior successes of island eradication projects. Next, we compare how genetic and environmental factors impact success in each system. These comparisons illuminate a number of promising cancer research and treatment directions, such as heterogeneity engineering as motivated by gene drives and adaptive therapy; multiscale analyses of how population heterogeneity potentiates treatment resistance; and application of ecological data mining techniques to high-throughput cancer data. We anticipate that interdisciplinary comparisons between tumor progression and invasive species would inspire development of novel paradigms to cure cancer.

Marine fish traits follow fast-slow continuum across oceans

A fundamental challenge in ecology is to understand why species are found where they are and predict where they are likely to occur in the future. Trait-based approaches may provide such understanding, because it is the traits and adaptations of species that determine which environments they can inhabit. It is therefore important to identify key traits that determine species distributions and investigate how these traits relate to the environment. Based on scientific bottom-trawl surveys of marine fish abundances and traits of >1,200 species, we investigate trait-environment relationships and project the trait composition of marine fish communities across the continental shelf seas of the Northern hemisphere. We show that traits related to growth, maturation and lifespan respond most strongly to the environment. This is reflected by a pronounced “fast-slow continuum” of fish life-histories, revealing that traits vary with temperature at large spatial scales, but also with depth and seasonality at more local scales. Our findings provide insight into the structure of marine fish communities and suggest that global warming will favour an expansion of fast-living species. Knowledge of the global and local drivers of trait distributions can thus be used to predict future responses of fish communities to environmental change.

Big Data Analytics Capabilities and Eco-Innovation: A Study of Energy Companies

Increased greenhouse gas (GHG) emissions in the past decades have created concerns about the environment. To stymie global warming and the deterioration of the natural environment, global CO2 emissions need to reach approximately 1.3 tons per capita by 2050. However, in Malaysia, CO2 output per capita—driven by fossil fuel consumption and energy production—is expected to reach approximately 12.1 tons by the year 2020. GHG mitigation strategies are needed to address these challenges. Cleaner production, through eco-innovation, has the potential to arrest CO2 emissions and buttress sustainable development. However, the cleaner production process has been hampered by lack of complete data to support decision making. Therefore, using the resource-based view, a preliminary study consisting of energy and utility firms is undertaken to understand the impact of big data analytics towards eco-innovation. Linear regression through SPSS Version 24 reveals that big data analytics could become a strong predictor of eco-innovation. This paper concludes that information and data are key inputs, and big data technology provides firms the opportunity to obtain information, which could influence its production process—and possibly help arrest increasing CO2 emissions.

Integrating GeoDesign with Landscape Sustainability Science

With an increasing world population and accelerated urbanization, the development of landscape sustainability remains a challenge for scientists, designers, and multiple stakeholders. Landscape sustainability science (LSS) studies dynamic relationships among landscape pattern, ecosystem services, and human well-being with spatially explicit methods. The design of a sustainable landscape needs both landscape sustainability–related disciplines and digital technologies that have been rapidly developing. GeoDesign is a new design method based on a new generation of information technology, especially spatial information technology, to design land systems. This paper discusses the suitability of GeoDesign for LSS to help design sustainable landscapes. Building on a review of LSS and GeoDesign, we conclude that LSS can utilize GeoDesign as a research method and the designed landscape as a research object to enrich and empower the spatially explicit methodology of LSS. To move forward, we suggest to integrate GeoDesign with LSS from six perspectives: strong/weak sustainability, multiple scales, ecosystem services, sustainability indicators, big data application, and the sense of place. Toward this end, we propose a LSS-based GeoDesign framework that links the six perspectives. We expect that this integration between GeoDesign and LSS will help advance the science and practice of sustainability and bring together many disciplines across natural, social, and design sciences.

Open science, reproducibility, and transparency in ecology

Reproducibility is a key tenet of the scientific process that dictates the reliability and generality of results and methods. The complexities of ecological observations and data present novel challenges in satisfying needs for reproducibility and also transparency. Ecological systems are dynamic and heterogeneous, interacting with numerous factors that sculpt natural history and that investigators cannot completely control. Observations may be highly dependent on spatial and temporal context, making them very difficult to reproduce, but computational reproducibility can still be achieved. Computational reproducibility often refers to the ability to produce equivalent analytical outcomes from the same data set using the same code and software as the original study. When coded workflows are shared, authors and editors provide transparency for readers and allow other researchers to build directly and efficiently on primary work. These qualities may be especially important in ecological applications that have important or controversial implications for science, management, and policy. Expectations for computational reproducibility and transparency are shifting rapidly in the sciences. In this work, we highlight many of the unique challenges for ecology along with practical guidelines for reproducibility and transparency, as ecologists continue to participate in the stewardship of critical environmental information and ensure that research methods demonstrate integrity.

Iterative near-term ecological forecasting: Needs, opportunities, and challenges

Two foundational questions about sustainability are "How are ecosystems and the services they provide going to change in the future?" and "How do human decisions affect these trajectories?" Answering these questions requires an ability to forecast ecological processes. Unfortunately, most ecological forecasts focus on centennial-scale climate responses, therefore neither meeting the needs of near-term (daily to decadal) environmental decision-making nor allowing comparison of specific, quantitative predictions to new observational data, one of the strongest tests of scientific theory. Near-term forecasts provide the opportunity to iteratively cycle between performing analyses and updating predictions in light of new evidence. This iterative process of gaining feedback, building experience, and correcting models and methods is critical for improving forecasts. Iterative, near-term forecasting will accelerate ecological research, make it more relevant to society, and inform sustainable decision-making under high uncertainty and adaptive management. Here, we identify the immediate scientific and societal needs, opportunities, and challenges for iterative near-term ecological forecasting. Over the past decade, data volume, variety, and accessibility have greatly increased, but challenges remain in interoperability, latency, and uncertainty quantification. Similarly, ecologists have made considerable advances in applying computational, informatic, and statistical methods, but opportunities exist for improving forecast-specific theory, methods, and cyberinfrastructure. Effective forecasting will also require changes in scientific training, culture, and institutions. The need to start forecasting is now; the time for making ecology more predictive is here, and learning by doing is the fastest route to drive the science forward.

Probing the limits of predictability: data assimilation of chaotic dynamics in complex food webs

The daunting complexity of ecosystems has led ecologists to use mathematical modelling to gain understanding of ecological relationships, processes and dynamics. In pursuit of mathematical tractability, these models use simplified descriptions of key patterns, processes and relationships observed in nature. In contrast, ecological data are often complex, scale-dependent, space-time correlated, and governed by nonlinear relations between organisms and their environment. This disparity in complexity between ecosystem models and data has created a large gap in ecology between model and data-driven approaches. Here, we explore data assimilation (DA) with the Ensemble Kalman filter to fuse a two-predator-two-prey model with abundance data from a 2600+ day experiment of a plankton community. We analyse how frequently we must assimilate measured abundances to predict accurately population dynamics, and benchmark our population model's forecast horizon against a simple null model. Results demonstrate that DA enhances the predictability and forecast horizon of complex community dynamics.