Developing an automated iterative near‐term forecasting system for an ecological study

Employing hybrid deep learning for near-real-time forecasts of sensor-based algal parameters in a Microcystis bloom-dominated lake

Harmful cyanobacterial blooms (CyanoHABs) are increasingly impacting the ecosystem of lakes, reservoirs and estuaries globally. The integration of real-time monitoring and deep learning technology has opened up new horizons for early warnings of CyanoHABs. However, unlike traditional methods such as pigment quantification or microscopy counting, the high-frequency data from in-situ fluorometric sensors display unpredictable fluctuations and variability, posing a challenge for predictive models to discern underlying trends within the time-series sequence. This study introduces a hybrid framework for near-real-time CyanoHABs predictions in a cyanobacterium Microcystis-dominated lake - Lake Dianchi, China. The proposed model was validated using hourly Chlorophyll-a (Chl a) concentrations and algal cell densities. Our results demonstrate that applying decomposition-based singular spectrum analysis (SSA) significantly enhances the prediction accuracy of subsequent CyanoHABs models, particularly in the case of temporal convolutional network (TCN). Comparative experiments revealed that the SSA-TCN model outperforms other SSA-based deep learning models for predicting Chl a (R2 = 0.45-0.93, RMSE = 2.29-5.89 μg/L) and algal cell density (R2 = 0.63-0.89, RMSE = 9489.39-16,015.37 cells/mL) at one to four steps ahead predictions. The forecast of bloom intensities achieved a remarkable accuracy of 98.56 % and an average precision rate of 94.04 % ± 0.05 %. In addition, scenarios involving various input combinations of environmental factors demonstrated that water temperature emerged as the most effective driver for CyanoHABs predictions, with a mean RMSE of 2.94 ± 0.12 μg/L, MAE of 1.55 ± 0.09 μg/L, and R2 of 0.83 ± 0.01. Overall, the newly developed approach underscores the potential of a well-designed hybrid deep-learning framework for accurately predicting sensor-based algal parameters. It offers novel perspectives for managing CyanoHABs through online monitoring and artificial intelligence in aquatic ecosystems.

Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs

This forecasting approach may be useful for water managers and associated public health managers to predict near-term future high-risk cyanobacterial harmful algal blooms (cyanoHAB) occurrence. Freshwater cyanoHABs may grow to excessive concentrations and cause human, animal, and environmental health concerns in lakes and reservoirs. Knowledge of the timing and location of cyanoHAB events is important for water quality management of recreational and drinking water systems. No quantitative tool exists to forecast cyanoHABs across broad geographic scales and at regular intervals. Publicly available satellite monitoring has proven effective in detecting cyanobacteria biomass near-real time within the United States. Weekly cyanobacteria abundance was quantified from the Ocean and Land Colour Instrument (OLCI) onboard the Sentinel-3 satellite as the response variable. An Integrated Nested Laplace Approximation (INLA) hierarchical Bayesian spatiotemporal model was applied to forecast World Health Organization (WHO) recreation Alert Level 1 exceedance >12 μg L-1 chlorophyll-a with cyanobacteria dominance for 2192 satellite resolved lakes in the United States across nine climate zones. The INLA model was compared against support vector classifier and random forest machine learning models; and Dense Neural Network, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Gneural Network (GNU) neural network models. Predictors were limited to data sources relevant to cyanobacterial growth, readily available on a weekly basis, and at the national scale for operational forecasting. Relevant predictors included water surface temperature, precipitation, and lake geomorphology. Overall, the INLA model outperformed the machine learning and neural network models with prediction accuracy of 90% with 88% sensitivity, 91% specificity, and 49% precision as demonstrated by training the model with data from 2017 through 2020 and independently assessing predictions with data from the 2021 calendar year. The probability of true positive responses was greater than false positive responses and the probability of true negative responses was less than false negative responses. This indicated the model correctly assigned lower probabilities of events when they didn't exceed the WHO Alert Level 1 threshold and assigned higher probabilities when events did exceed the threshold. The INLA model was robust to missing data and unbalanced sampling between waterbodies.

Forecasting insect dynamics in a changing world

Predicting how insects will respond to stressors through time is difficult because of the diversity of insects, environments, and approaches used to monitor and model. Forecasting models take correlative/statistical, mechanistic models, and integrated forms; in some cases, temporal processes can be inferred from spatial models. Because of heterogeneity associated with broad community measurements, models are often unable to identify mechanistic explanations. Many present efforts to forecast insect dynamics are restricted to single-species models, which can offer precise predictions but limited generalizability. Trait-based approaches may offer a good compromise that limits the masking of the ranges of responses while still offering insight. Regardless of the modeling approach, the data used to parameterize a forecasting model should be carefully evaluated for temporal autocorrelation, minimum data needs, and sampling biases in the data. Forecasting models can be tested using near-term predictions and revised to improve future forecasts.

AIMS for wildlife: Developing an automated interactive monitoring system to integrate real-time movement and environmental data for true adaptive management

To effectively manage species and habitats at multiple scales, population and land managers require rapid information on wildlife use of managed areas and responses to landscape conditions and management actions. GPS tracking studies of wildlife are particularly informative to species ecology, habitat use, and conservation. Combining GPS data with administrative data and a diverse suite of remotely sensed, geo-referenced environmental (e.g., climatic) data, would more comprehensively inform how animals interact with and utilize habitats and ecosystems and our goal was to create a conceptual model for a system that would accomplish this - the 'Automated Interactive Monitoring System (AIMS) for Wildlife'. Our objective for this study was to develop a Customized Wildlife Report (CWR) - the first AIMS for Wildlife deliverable product. CWRs collate and summarize our 8-year GPS tracking dataset of ∼11 million locations from 1338 individual (16 species) avifauna and make actionable, real-time data on animal movements and trends in a specific area of interest available to managers and stakeholders for rapid application in day-to-day management. The CWR exemplar presented in this paper was developed to address needs identified by habitat managers of Sacramento National Wildlife Refuge and illustrates the highly specific, information offered and how it contributes to assessing the efficacy of conservation actions while allowing for near real-time adaptive management. The report can be easily customized for any of the thousands of wildlife refuges or regional areas of interest in the United States, emphasizing the broad application of an animal movement data stream. Utilizing diverse, extensive telemetry data streams through scientific collaboration can aid managers and conservation stakeholders with short and long-term research and conservation planning and help address a cadre of issues from local-scale habitat management to improving the understanding of landscape level impacts like drought, wildfire, and climate change on wildlife populations.

The Internet of Animals: what it is, what it could be

One of the biggest trends in ecology over the past decade has been the creation of standardized databases. Recently, this has included live data, formal linkages between disparate databases, and automated analytics, a synergy that we recognize as the Internet of Animals (IoA). Early IoA systems relate animal locations to remote-sensing data to predict species distributions and detect disease outbreaks, and use live data to inform management of endangered species. However, meeting the future potential of the IoA concept will require solving challenges of taxonomy, data security, and data sharing. By linking data sets, integrating live data, and automating workflows, the IoA has the potential to enable discoveries and predictions relevant to human societies and the conservation of animals.

The effects of light pollution on migratory animal behavior

Light pollution is a global threat to biodiversity, especially migratory organisms, some of which traverse hemispheric scales. Research on light pollution has grown significantly over the past decades, but our review of migratory organisms demonstrates gaps in our understanding, particularly beyond migratory birds. Research across spatial scales reveals the multifaceted effects of artificial light on migratory species, ranging from local and regional to macroscale impacts. These threats extend beyond species that are active at night - broadening the scope of this threat. Emerging tools for measuring light pollution and its impacts, as well as ecological forecasting techniques, present new pathways for conservation, including transdisciplinary approaches.

Progress and opportunities in advancing near-term forecasting of freshwater quality

Near-term freshwater forecasts, defined as sub-daily to decadal future predictions of a freshwater variable with quantified uncertainty, are urgently needed to improve water quality management as freshwater ecosystems exhibit greater variability due to global change. Shifting baselines in freshwater ecosystems due to land use and climate change prevent managers from relying on historical averages for predicting future conditions, necessitating near-term forecasts to mitigate freshwater risks to human health and safety (e.g., flash floods, harmful algal blooms) and ecosystem services (e.g., water-related recreation and tourism). To assess the current state of freshwater forecasting and identify opportunities for future progress, we synthesized freshwater forecasting papers published in the past 5 years. We found that freshwater forecasting is currently dominated by near-term forecasts of water quantity and that near-term water quality forecasts are fewer in number and in the early stages of development (i.e., non-operational) despite their potential as important preemptive decision support tools. We contend that more freshwater quality forecasts are critically needed and that near-term water quality forecasting is poised to make substantial advances based on examples of recent progress in forecasting methodology, workflows, and end-user engagement. For example, current water quality forecasting systems can predict water temperature, dissolved oxygen, and algal bloom/toxin events 5 days ahead with reasonable accuracy. Continued progress in freshwater quality forecasting will be greatly accelerated by adapting tools and approaches from freshwater quantity forecasting (e.g., machine learning modeling methods). In addition, future development of effective operational freshwater quality forecasts will require substantive engagement of end users throughout the forecast process, funding, and training opportunities. Looking ahead, near-term forecasting provides a hopeful future for freshwater management in the face of increased variability and risk due to global change, and we encourage the freshwater scientific community to incorporate forecasting approaches in water quality research and management.

BIRDIE: A data pipeline to inform wetland and waterbird conservation at multiple scales

Introduction

Efforts to collect ecological data have intensified over the last decade. This is especially true for freshwater habitats, which are among the most impacted by human activity and yet lagging behind in terms of data availability. Now, to support conservation programmes and management decisions, these data need to be analyzed and interpreted; a process that can be complex and time consuming. The South African Biodiversity Data Pipeline for Wetlands and Waterbirds (BIRDIE) aims to help fast and efficient information uptake, bridging the gap between raw ecological datasets and the information final users need.

Methods

BIRDIE is a full data pipeline that takes up raw data, and estimates indicators related to waterbird populations, while keeping track of their associated uncertainty. At present, we focus on the assessment of species abundance and distribution in South Africa using two citizen-science bird monitoring datasets, namely: the African Bird Atlas Project and the Coordinated Waterbird Counts. These data are analyzed with occupancy and state-space models, respectively. In addition, a suite of environmental layers help contextualize waterbird population indicators, and link these to the ecological condition of the supporting wetlands. Both data and estimated indicators are accessible to end users through an online portal and web services.

Results and discussion

We have designed a modular system that includes tasks, such as: data cleaning, statistical analysis, diagnostics, and computation of indicators. Envisioned users of BIRDIE include government officials, conservation managers, researchers and the general public, all of whom have been engaged throughout the project. Acknowledging that conservation programmes run at multiple spatial and temporal scales, we have developed a granular framework in which indicators are estimated at small scales, and then these are aggregated to compute similar indicators at broader scales. Thus, the online portal is designed to provide spatial and temporal visualization of the indicators using maps, time series and pre-compiled reports for species, sites and conservation programmes. In the future, we aim to expand the geographical coverage of the pipeline to other African countries, and develop more indicators specific to the ecological structure and function of wetlands.

Assessing Ecosystem State Space Models: Identifiability and Estimation

Hierarchical probability models are being used more often than non-hierarchical deterministic process models in environmental prediction and forecasting, and Bayesian approaches to fitting such models are becoming increasingly popular. In particular, models describing ecosystem dynamics with multiple states that are autoregressive at each step in time can be treated as statistical state space models (SSMs). In this paper, we examine this subset of ecosystem models, embed a process-based ecosystem model into an SSM, and give closed form Gibbs sampling updates for latent states and process precision parameters when process and observation errors are normally distributed. Here, we use simulated data from an example model (DALECev) and study the effects changing the temporal resolution of observations on the states (observation data gaps), the temporal resolution of the state process (model time step), and the level of aggregation of observations on fluxes (measurements of transfer rates on the state process). We show that parameter estimates become unreliable as temporal gaps between observed state data increase. To improve parameter estimates, we introduce a method of tuning the time resolution of the latent states while still using higher-frequency driver information and show that this helps to improve estimates. Further, we show that data cloning is a suitable method for assessing parameter identifiability in this class of models. Overall, our study helps inform the application of state space models to ecological forecasting applications where (1) data are not available for all states and transfers at the operational time step for the ecosystem model and (2) process uncertainty estimation is desired.

Advancing freshwater ecological forecasts: Harmful algal blooms in Lake Erie

Ecological models help provide forecasts of ecosystem responses to natural and anthropogenic stresses. However, their ability to create reliable predictions requires forecasts with track records sufficiently long to build confidence, skill assessments, and treating uncertainty quantitatively. We use Lake Erie harmful algal blooms as a case study to help formalize ecological forecasting. Key challenges for models include uncertainty in the deterministic structure of the load-bloom relationship and the need to assess alternative drivers (e.g., biologically available phosphorus load, spring load, longer term cumulative load) with a larger dataset. We enhanced a Bayesian model considering new information and an expanded data set, test it through cross validation and blind forecasts, quantify and discuss its uncertainties, and apply it for assessing historical and future scenarios. Allowing a segmented relationship between bloom size and spring load indicates that loading above 0.15 Gg/month will have a substantially higher marginal impact on bloom size. The new model explains 84 % of interannual variability (9.09 Gg RMSE) when calibrated to the 19-year data set and 66 % of variability in cross validation (12.58 Gg RMSE). Blind forecasts explain 84 % of HAB variability between 2014 and 2020, which is substantially better than the actual forecast track record (R² = 0.32) over this same period. Because of internal phosphorus recycling, represented by the long-term cumulative load, it could take over a decade for HABs to fully respond to loading reductions, depending on the pace of those reductions. Thus, the desired speed and endpoint of the lake's recovery should be considered when updating and adaptively managing load reduction targets. Results are discussed in the context of ecological forecasting best pactices: incorporate new knowledge and data in model construction; account for multiple sources of uncertainty; evaluate predictive skill through validation and hindcasting; and answer management questions related to both short-term forecasts and long-term scenarios.

A probabilistic epidemiological model for infectious diseases: The case of COVID-19 at global-level

This study has developed a probabilistic epidemiological model a few weeks after the World Health Organization declared COVID-19 a pandemic (based on the little data available at that time). The aim was to assess relative risks for future scenarios and evaluate the effectiveness of different management actions for 1 year ahead. We quantified, categorized, and ranked the risks for scenarios such as business as usual, and moderate and strong mitigation. We estimated that, in the absence of interventions, COVID-19 would have a 100% risk of explosion (i.e., more than 25% infections in the world population) and 34% (2.6 billion) of the world population would have been infected until the end of simulation. We analyzed the suitability of model scenarios by comparing actual values against estimated values for the first 6 weeks of the simulation period. The results proved to be more suitable with a business-as-usual scenario in Asia and moderate mitigation in the other continents. If everything went on like this, we would have 55% risk of explosion and 22% (1.7 billion) of the world population would have been infected. Strong mitigation actions in all continents could reduce these numbers to, 7% and 3% (223 million), respectively. Although the results were based on the data available in March 2020, both the model and probabilistic approach proved to be practicable and could be a basis for risk assessment in future pandemic episodes with unknown virus, especially in the early stages, when data and literature are scarce.

PERFICT: A Re-imagined foundation for predictive ecology

Making predictions from ecological models—and comparing them to data—offers a coherent approach to evaluate model quality, regardless of model complexity or modelling paradigm. To date, our ability to use predictions for developing, validating, updating, integrating and applying models across scientific disciplines while influencing management decisions, policies, and the public has been hampered by disparate perspectives on prediction and inadequately integrated approaches. We present an updated foundation for Predictive Ecology based on seven principles applied to ecological modelling: make frequent Predictions, Evaluate models, make models Reusable, Freely accessible and Interoperable, built within Continuous workflows that are routinely Tested (PERFICT). We outline some benefits of working with these principles: accelerating science; linking with data science; and improving science‐policy integration.

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.

Near-term forecasting of companion animal tick paralysis incidence: An iterative ensemble model

Tick paralysis resulting from bites from Ixodes holocyclus and I. cornuatus is one of the leading causes of emergency veterinary admissions for companion animals in Australia, often resulting in death if left untreated. Availability of timely information on periods of increased risk can help modulate behaviors that reduce exposures to ticks and improve awareness of owners for the need of lifesaving preventative ectoparasite treatment. Improved awareness of clinicians and pet owners about temporal changes in tick paralysis risk can be assisted by ecological forecasting frameworks that integrate environmental information into statistical time series models. Using an 11-year time series of tick paralysis cases from veterinary clinics in one of Australia's hotspots for the paralysis tick Ixodes holocyclus, we asked whether an ensemble model could accurately forecast clinical caseloads over near-term horizons. We fit a series of statistical time series (ARIMA, GARCH) and generative models (Prophet, Generalised Additive Model) using environmental variables as predictors, and then combined forecasts into a weighted ensemble to minimise prediction interval error. Our results indicate that variables related to temperature anomalies, levels of vegetation moisture and the Southern Oscillation Index can be useful for predicting tick paralysis admissions. Our model forecasted tick paralysis cases with exceptional accuracy while preserving epidemiological interpretability, outperforming a field-leading benchmark Exponential Smoothing model by reducing both point and prediction interval errors. Using online particle filtering to assimilate new observations and adjust forecast distributions when new data became available, our model adapted to changing temporal conditions and provided further reduced forecast errors. We expect our model pipeline to act as a platform for developing early warning systems that can notify clinicians and pet owners about heightened risks of environmentally driven veterinary conditions.

Iterative data-driven forecasting of the transmission and management of SARS-CoV-2/COVID-19 using social interventions at the county-level

The control of the initial outbreak and spread of SARS-CoV-2/COVID-19 via the application of population-wide non-pharmaceutical mitigation measures have led to remarkable successes in dampening the pandemic globally. However, with countries beginning to ease or lift these measures fully to restart activities, concern is growing regarding the impacts that such reopening of societies could have on the subsequent transmission of the virus. While mathematical models of COVID-19 transmission have played important roles in evaluating the impacts of these measures for curbing virus transmission, a key need is for models that are able to effectively capture the effects of the spatial and social heterogeneities that drive the epidemic dynamics observed at the local community level. Iterative forecasting that uses new incoming epidemiological and social behavioral data to sequentially update locally-applicable transmission models can overcome this gap, potentially resulting in better predictions and policy actions. Here, we present the development of one such data-driven iterative modelling tool based on publicly available data and an extended SEIR model for forecasting SARS-CoV-2 at the county level in the United States. Using data from the state of Florida, we demonstrate the utility of such a system for exploring the outcomes of the social measures proposed by policy makers for containing the course of the pandemic. We provide comprehensive results showing how the locally identified models could be employed for accessing the impacts and societal tradeoffs of using specific social protective strategies. We conclude that it could have been possible to lift the more disruptive social interventions related to movement restriction/social distancing measures earlier if these were accompanied by widespread testing and contact tracing. These intensified social interventions could have potentially also brought about the control of the epidemic in low- and some medium-incidence county settings first, supporting the development and deployment of a geographically-phased approach to reopening the economy of Florida. We have made our data-driven forecasting system publicly available for policymakers and health officials to use in their own locales, so that a more efficient coordinated strategy for controlling SARS-CoV-2 region-wide can be developed and successfully implemented.

A niche for null models in adaptive resource management

As global systems rapidly change, our collective ability to predict future ecological dynamics will become increasingly important for successful natural resource management. By merging stakeholder objectives with system uncertainty, and by adapting actions to changing systems and knowledge, adaptive resource management (ARM) provides a rigorous platform for making sound decisions in a changing world. Critically, however, applications of ARM could be improved by employing benchmarks (i.e., points of reference) for determining when learning is occurring through the cycle of monitoring, modeling, and decision-making steps in ARM. Many applications of ARM use multiple model-based hypotheses to identify and reduce systematic uncertainty over time, but generally lack benchmarks for gauging discovery of scientific evidence and learning. This creates the danger of thinking that directional changes in model weights or rankings are indicative of evidence for hypotheses, when possibly all competing models are inadequate. There is thus a somewhat obvious, but yet to be filled niche for including benchmarks for learning in ARM. We contend that carefully designed "ecological null models," which are structured to produce an expected ecological pattern in the absence of a hypothesized mechanism, can serve as suitable benchmarks. Using a classic case study of mallard harvest management that is often used to demonstrate the successes of ARM for learning about ecological mechanisms, we show that simple ecological null models, such as population persistence (Nt +1 = Nt ), provide more robust near-term forecasts of population abundance than the currently used mechanistic models. More broadly, ecological null models can be used as benchmarks for learning in ARM that trigger the need for discarding model parameterizations and developing new ones when prevailing models underperform the ecological null model. Identifying mechanistic models that surpass these benchmarks will improve learning through ARM and help decision-makers keep pace with a rapidly changing world.

Coding for Life: Designing a Platform for Projecting and Protecting Global Biodiversity

Time is running out to limit further devastating losses of biodiversity and nature's contributions to humans. Addressing this crisis requires accurate predictions about which species and ecosystems are most at risk to ensure efficient use of limited conservation and management resources. We review existing biodiversity projection models and discover problematic gaps. Current models usually cannot easily be reconfigured for other species or systems, omit key biological processes, and cannot accommodate feedbacks with Earth system dynamics. To fill these gaps, we envision an adaptable, accessible, and universal biodiversity modeling platform that can project essential biodiversity variables, explore the implications of divergent socioeconomic scenarios, and compare conservation and management strategies. We design a roadmap for implementing this vision and demonstrate that building this biodiversity forecasting platform is possible and practical.

Assessing Pathways of Climate Change Effects in SpaDES: An Application to Boreal Landbirds of Northwest Territories Canada

Distributions of landbirds in Canadian northern forests are expected to be affected by climate change, but it remains unclear which pathways are responsible for projected climate effects. Determining whether climate change acts indirectly through changing fire regimes and/or vegetation dynamics, or directly through changes in climatic suitability may allow land managers to address negative trajectories via forest management. We used SpaDES, a novel toolkit built in R that facilitates the implementation of simulation models from different areas of knowledge to develop a simulation experiment for a study area comprising 50 million ha in the Northwest Territories, Canada. Our factorial experiment was designed to contrast climate effects pathways on 64 landbird species using climate-sensitive and non-climate sensitive models for tree growth and mortality, wildfire, and landbirds. Climate-change effects were predicted to increase suitable habitat for 73% of species, resulting in average net gain of 7.49 million ha across species. We observed higher species turnover in the northeastern, south-central (species loss), and western regions (species gain). Importantly, we found that most of the predicted differences in net area of occupancy across models were attributed to direct climate effects rather than simulated vegetation change, despite a similar relative importance of vegetation and climate variables in landbird models. Even with close to a doubling of annual area burned by 2100, and a 600 kg/ha increase in aboveground tree biomass predicted in this region, differences in landbird net occupancy across models attributed to climate-driven forest growth were very small, likely resulting from differences in the pace of vegetation and climate changes, or vegetation lags. The effect of vegetation lags (i.e., differences from climatic equilibrium) varied across species, resulting in a wide range of changes in landbird distribution, and consequently predicted occupancy, due to climate effects. These findings suggest that hybrid approaches using statistical models and landscape simulation tools could improve wildlife forecasts when future uncoupling of vegetation and climate is anticipated. This study lays some of the methodological groundwork for ecological adaptive management using the new platform SpaDES, which allows for iterative forecasting, mixing of modeling paradigms, and tightening connections between data, parameterization, and simulation.

Challenges in updating habitat suitability models: An example with the lesser prairie-chicken

Habitat loss from land-use change is one of the top causes of declines in wildlife species of concern. As such, it is critical to assess and reassess habitat suitability as land cover and anthropogenic features change for both monitoring and developing current information to inform management decisions. However, there are obstacles that must be overcome to develop consistent assessments through time. A range-wide lek habitat suitability model for the lesser prairie-chicken (Tympanuchus pallidicinctus), currently under review by the U. S. Fish and Wildlife Service for potential listing under the Endangered Species Act, was published in 2016. This model was based on lek data from 2002 to 2012, land cover data ranging from 2001 to 2013, and anthropogenic features from circa 2011, and has been used to help guide lesser prairie-chicken management and anthropogenic development actions. We created a second iteration model based on new lek surveys (2015 to 2019) and updated predictors (2016 land cover and cleaned/updated anthropogenic data) to evaluate changes in lek suitability and to quantify current range-wide habitat suitability. Only three of 11 predictor variables were directly comparable between the iterations, making it difficult to directly assess what predicted changes resulted from changes in model inputs versus actual landscape change. The second iteration model showed a similar positive relationship with land cover and negative relationship with anthropogenic features to the first iteration, but exhibited more variation among candidate models. Range-wide, more suitable habitat was predicted in the second iteration. The Shinnery Oak Ecoregion, however, exhibited a loss in predicted suitable habitat that could be due to predictor source changes. Iterated models such as this are important to ensure current information is being used in conservation and development decisions.

Advancing estuarine ecological forecasts: seasonal hypoxia in Chesapeake Bay

Ecological forecasts are quantitative tools that can guide ecosystem management. The coemergence of extensive environmental monitoring and quantitative frameworks allows for widespread development and continued improvement of ecological forecasting systems. We use a relatively simple estuarine hypoxia model to demonstrate advances in addressing some of the most critical challenges and opportunities of contemporary ecological forecasting, including predictive accuracy, uncertainty characterization, and management relevance. We explore the impacts of different combinations of forecast metrics, drivers, and driver time windows on predictive performance. We also incorporate multiple sets of state-variable observations from different sources and separately quantify model prediction error and measurement uncertainty through a flexible Bayesian hierarchical framework. Results illustrate the benefits of (1) adopting forecast metrics and drivers that strike an optimal balance between predictability and relevance to management, (2) incorporating multiple data sources in the calibration data set to separate and propagate different sources of uncertainty, and (3) using the model in scenario mode to probabilistically evaluate the effects of alternative management decisions on future ecosystem state. In the Chesapeake Bay, the subject of this case study, we find that average summer or total annual hypoxia metrics are more predictable than monthly metrics and that measurement error represents an important source of uncertainty. Application of the model in scenario mode suggests that absent watershed management actions over the past decades, long-term average hypoxia would have increased by 7% compared to 1985. Conversely, the model projects that if management goals currently in place to restore the Bay are met, long-term average hypoxia would eventually decrease by 32% with respect to the mid-1980s.

Evaluating probabilistic ecological forecasts

Probabilistic near-term forecasting facilitates evaluation of model predictions against observations and is of pressing need in ecology to inform environmental decision-making and effect societal change. Despite this imperative, many ecologists are unfamiliar with the widely used tools for evaluating probabilistic forecasts developed in other fields. We address this gap by reviewing the literature on probabilistic forecast evaluation from diverse fields including climatology, economics, and epidemiology. We present established practices for selecting evaluation data (end-sample hold out), graphical forecast evaluation (times-series plots with uncertainty, probability integral transform plots), quantitative evaluation using scoring rules (log, quadratic, spherical, and ranked probability scores), and comparing scores across models (skill score, Diebold-Mariano test). We cover common approaches, highlight mathematical concepts to follow, and note decision points to allow application of general principles to specific forecasting endeavors. We illustrate these approaches with an application to a long-term rodent population time series currently used for ecological forecasting and discuss how ecology can continue to learn from and drive the cross-disciplinary field of forecasting science.

Provoking a Cultural Shift in Data Quality

Ecological studies require quality data to describe the nature of ecological processes and to advance understanding of ecosystem change. Increasing access to big data has magnified both the burden and the complexity of ensuring quality data. The costs of errors in ecology include low use of data, increased time spent cleaning data, and poor reproducibility that can result in a misunderstanding of ecosystem processes and dynamics, all of which can erode the efficacy of and trust in ecological research. Although conceptual and technological advances have improved ecological data access and management, a cultural shift is needed to embed data quality as a cultural practice. We present a comprehensive data quality framework to evoke this cultural shift. The data quality framework flexibly supports different collaboration models, supports all types of ecological data, and can be used to describe data quality within both short- and long-term ecological studies.

Iterative model predictions for wildlife populations impacted by rapid climate change

To improve understanding and management of the consequences of current rapid environmental change, ecologists advocate using long-term monitoring data series to generate iterative near-term predictions of ecosystem responses. This approach allows scientific evidence to increase rapidly and management strategies to be tailored simultaneously. Iterative near-term forecasting may therefore be particularly useful for adaptive monitoring of ecosystems subjected to rapid climate change. Here, we show how to implement near-term forecasting in the case of a harvested population of rock ptarmigan in high-arctic Svalbard, a region subjected to the largest and most rapid climate change on Earth. We fitted state-space models to ptarmigan counts from point transect distance sampling during 2005-2019 and developed two types of predictions: (1) explanatory predictions to quantify the effect of potential drivers of ptarmigan population dynamics, and (2) anticipatory predictions to assess the ability of candidate models of increasing complexity to forecast next-year population density. Based on the explanatory predictions, we found that a recent increasing trend in the Svalbard rock ptarmigan population can be attributed to major changes in winter climate. Currently, a strong positive effect of increasing average winter temperature on ptarmigan population growth outweighs the negative impacts of other manifestations of climate change such as rain-on-snow events. Moreover, the ptarmigan population may compensate for current harvest levels. Based on the anticipatory predictions, the near-term forecasting ability of the models improved nonlinearly with the length of the time series, but yielded good forecasts even based on a short time series. The inclusion of ecological predictors improved forecasts of sharp changes in next-year population density, demonstrating the value of ecosystem-based monitoring. Overall, our study illustrates the power of integrating near-term forecasting in monitoring systems to aid understanding and management of wildlife populations exposed to rapid climate change. We provide recommendations for how to improve this approach.

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.

Ecological forecasts to inform near-term management of threats to biodiversity

Ecosystems are being altered by rapid and interacting changes in natural processes and anthropogenic threats to biodiversity. Uncertainty in historical, current and future effectiveness of actions hampers decisions about how to mitigate changes to prevent biodiversity loss and species extinctions. Research in resource management, agriculture and health indicates that forecasts predicting the effects of near-term or seasonal environmental conditions on management greatly improve outcomes. Such forecasts help resolve uncertainties about when and how to operationalize management. We reviewed the scientific literature on environmental management to investigate whether near-term forecasts are developed to inform biodiversity decisions in Australia, a nation with one of the highest recent extinction rates across the globe. We found that forecasts focused on economic objectives (e.g. fisheries management) predict on significantly shorter timelines and answer a broader range of management questions than forecasts focused on biodiversity conservation. We then evaluated scientific literature on the effectiveness of 484 actions to manage seven major terrestrial threats in Australia, to identify opportunities for near-term forecasts to inform operational conservation decisions. Depending on the action, between 30% and 80% threat management operations experienced near-term weather impacts on outcomes before, during or after management. Disease control, species translocation/reintroduction and habitat restoration actions were most frequently impacted, and negative impacts such as increased species mortality and reduced recruitment were more likely than positive impacts. Drought or dry conditions, and rainfall, were the most frequently reported weather impacts, indicating that near-term forecasts predicting the effects of low or excessive rainfall on management outcomes are likely to have the greatest benefits. Across the world, many regions are, like Australia, becoming warmer and drier, or experiencing more extreme rainfall events. Informing conservation decisions with near-term and seasonal ecological forecasting will be critical to harness uncertainties and lower the risk of threat management failure under global change.

End-user involvement to improve predictions and management of populations with complex dynamics and multiple drivers

Sustainable management of wildlife populations can be aided by building models that both identify current drivers of natural dynamics and provide near-term predictions of future states. We employed a Strategic Foresight Protocol (SFP) involving stakeholders to decide the purpose and structure of a dynamic state-space model for the population dynamics of the Willow Ptarmigan, a popular game species in Norway. Based on local knowledge of stakeholders, it was decided that the model should include food web interactions and climatic drivers to provide explanatory predictions. Modeling confirmed observations from stakeholders that climate change impacts Ptarmigan populations negatively through intensified outbreaks of insect defoliators and later onset of winter. Stakeholders also decided that the model should provide anticipatory predictions. The ability to forecast population density ahead of the harvest season was valued by the stakeholders as it provides the management extra time to consider appropriate harvest regulations and communicate with hunters prior to the hunting season. Overall, exploring potential drivers and predicting short-term future states, facilitate collaborative learning and refined data collection, monitoring designs, and management priorities. Our experience from adapting a SFP to a management target with inherently complex dynamics and drivers of environmental change, is that an open, flexible, and iterative process, rather than a rigid step-wise protocol, facilitates rapid learning, trust, and legitimacy.

Forecasting semi-arid biome shifts in the Anthropocene

Shrub encroachment, forest decline and wildfires have caused large-scale changes in semi-arid vegetation over the past 50 years. Climate is a primary determinant of plant growth in semi-arid ecosystems, yet it remains difficult to forecast large-scale vegetation shifts (i.e. biome shifts) in response to climate change. We highlight recent advances from four conceptual perspectives that are improving forecasts of semi-arid biome shifts. Moving from small to large scales, first, tree-level models that simulate the carbon costs of drought-induced plant hydraulic failure are improving predictions of delayed-mortality responses to drought. Second, tracer-informed water flow models are improving predictions of species coexistence as a function of climate. Third, new applications of ecohydrological models are beginning to simulate small-scale water movement processes at large scales. Fourth, remotely-sensed measurements of plant traits such as relative canopy moisture are providing early-warning signals that predict forest mortality more than a year in advance. We suggest that a community of researchers using modeling approaches (e.g. machine learning) that can integrate these perspectives will rapidly improve forecasts of semi-arid biome shifts. Better forecasts can be expected to help prevent catastrophic changes in vegetation states by identifying improved monitoring approaches and by prioritizing high-risk areas for management.

Automated data-intensive forecasting of plant phenology throughout the United States

Phenology, the timing of cyclical and seasonal natural phenomena such as flowering and leaf out, is an integral part of ecological systems with impacts on human activities like environmental management, tourism, and agriculture. As a result, there are numerous potential applications for actionable predictions of when phenological events will occur. However, despite the availability of phenological data with large spatial, temporal, and taxonomic extents, and numerous phenology models, there have been no automated species-level forecasts of plant phenology. This is due in part to the challenges of building a system that integrates large volumes of climate observations and forecasts, uses that data to fit models and make predictions for large numbers of species, and consistently disseminates the results of these forecasts in interpretable ways. Here, we describe a new near-term phenology-forecasting system that makes predictions for the timing of budburst, flowers, ripe fruit, and fall colors for 78 species across the United States up to 6 months in advance and is updated every four days. We use the lessons learned in developing this system to provide guidance developing large-scale near-term ecological forecast systems more generally, to help advance the use of automated forecasting in ecology.

Remote sensing and modeling fusion for investigating the ecosystem water-carbon coupling processes

The water and carbon cycles are tightly linked and play a key role in the material and energy flows between terrestrial ecosystems and the atmosphere, but the interactions of water and carbon cycles are not quite clear. The global climate change and intensive human activities could also complicate the water and carbon coupling processes. Better understanding the coupled water-carbon cycles and their spatiotemporal evolution can inform management and decision-making efforts regarding carbon uptake, food production, water resources, and climate change. The integration of remote sensing and numeric modeling is an attractive approach to address the challenge. Remote sensing can provide extensive data for a number of variables at regional scale and support models, whereas process-based modeling can facilitate investigating the processes that remote sensing cannot well handle (e.g., below-ground and lateral material movement) and backcast/forecast the impacts of environmental change. Over the past twenty years, an increasing number of studies using a variety of remote sensing products together with numeric models have examined the water-carbon interactions. This article reviewed the methodologies for integrating remote sensing data into these models and the modeling of water-carbon coupling processes. We first summarized the major remote sensing datasets and models used for studying the coupled water-carbon cycles. We then provided an overview of the methods for integrating remote sensing data into water-carbon models, and discussed their strengths and challenges. We also prospected the development of potential new remote sensing datasets, modeling methods, and their potential applications in the field of eco-hydrology.