Spatially balanced sampling designs for environmental surveys

Causal Inference With Observational Data and Unobserved Confounding Variables

Experiments have long been the gold standard for causal inference in Ecology. As Ecology tackles progressively larger problems, however, we are moving beyond the scales at which randomised controlled experiments are feasible. To answer causal questions at scale, we need to also use observational data -something Ecologists tend to view with great scepticism. The major challenge using observational data for causal inference is confounding variables: variables affecting both a causal variable and response of interest. Unmeasured confounders-known or unknown-lead to statistical bias, creating spurious correlations and masking true causal relationships. To combat this omitted variable bias, other disciplines have developed rigorous approaches for causal inference from observational data that flexibly control for broad suites of confounding variables. We show how ecologists can harness some of these methods-causal diagrams to identify confounders coupled with nested sampling and statistical designs-to reduce risks of omitted variable bias. Using an example of estimating warming effects on snails, we show how current methods in Ecology (e.g., mixed models) produce incorrect inferences due to omitted variable bias and how alternative methods can eliminate it, improving causal inferences with weaker assumptions. Our goal is to expand tools for causal inference using observational and imperfect experimental data in Ecology.

Development of a generalized pseudo-probabilistic approach for characterizing ecological conditions in estuaries using secondary data

Under the best circumstances, achieving or sustaining optimum ecological conditions in estuaries is challenging. Persistent information gaps in estuarine data make it difficult to differentiate natural variability from potential regime shifts. Long-term monitoring is critical for tracking ecological change over time. In the United States (US), many resource management programs are working at maximum capacity to address existing state and federal water quality mandates (e.g., pollutant load limits, climate impact mitigation, and fisheries management) and have little room to expand routine sampling efforts to conduct periodic ecological baseline assessments, especially at state and local scales. Alternative design, monitoring, and assessment approaches are needed to help offset the burden of addressing additional data needs to increase understanding about estuarine system resilience when existing monitoring data are sparse or spatially limited. Research presented here offers a pseudo-probabilistic approach that allows for the use of found or secondary data, such as data on hand and other acquired data, to generate statistically robust characterizations of ecological conditions in estuaries. Our approach uses a generalized pseudo-probabilistic framework to synthesize data from different contributors to inform probabilistic-like baseline assessments. The methodology relies on simple geospatial techniques and existing tools (R package functions) developed for the US Environmental Protection Agency to support ecological monitoring and assessment programs like the National Coastal Condition Assessment. Using secondary estuarine water quality data collected in the Northwest Florida (US) estuaries, demonstrations suggest that the pseudo-probabilistic approach produces estuarine condition assessment results with reasonable statistical confidence, improved spatial representativeness, and value-added information. While the pseudo-probabilistic framework is not a substitute for fully evolved monitoring, it offers a scalable alternative to bridge the gap between limitations in resource management capability and optimal monitoring strategies to track ecological baselines in estuaries over time.

Well-spread samples with dynamic sample sizes

A spatial sampling design determines where sample locations are placed in a study area so that population parameters can be estimated with relatively high precision. If the response variable has spatial trends, spatially balanced or well-spread designs give precise results for commonly used estimators. This article proposes a new method that draws well-spread samples over arbitrary auxiliary spaces and can be used for master sampling applications. All we require is a measure of the distance between population units. Numerical results show that the method generates well-spread samples and compares favorably with existing designs. We provide an example application using several auxiliary variables to estimate total aboveground biomass over a large study area in Eastern Amazonia, Brazil. Multipurpose surveys are also considered, where the totals of aboveground biomass, primary production, and clay content (3 responses) are estimated from a single well-spread sample over the auxiliary space.

The distribution of metal and petroleum-derived contaminants within sediments around oil and gas infrastructure in the Gippsland Basin, Australia

As oil and gas infrastructure comes to the end of its working life, a decommissioning decision must be made: should the infrastructure be abandoned in situ, repurposed, partially removed, or fully removed? Environmental contaminants around oil and gas infrastructure could influence these decisions because contaminants in sediments could degrade the value of the infrastructure as habitat, enter the seafood supply if the area is re-opened for commercial and/or recreational fishing, or be made biologically available as sediment is resuspended when the structures are moved. An initial risk hypothesis, however, may postulate that these concerns are only relevant if contaminant concentrations are above screening values that predict the possibility of environmental harm or contaminant bioaccumulation. To determine whether a substantive contaminants-based risk assessment is needed for infrastructure in the Gippsland Basin (South-eastern Australia), we measured the concentration of metals and polycyclic aromatic hydrocarbons (PAHs) in benthic sediments collected around eight platforms earmarked for decommissioning. The measurements were compared to preset screening values and to background contaminant concentrations in reference sites. Lead (Pb), zinc (Zn), PAHs and other contaminants were occasionally measured at concentrations that exceeded reference values, most often within 150 m of the platforms. The exceedance of a few screening values by contaminants at some platforms indicates that these platforms require further analysis to determine the contaminant risks associated with any decommissioning option.

A simulated annealing-based algorithm for selecting balanced samples

Balanced sampling is a random method for sample selection, the use of which is preferable when auxiliary information is available for all units of a population. However, implementing balanced sampling can be a challenging task, and this is due in part to the computational efforts required and the necessity to respect balancing constraints and inclusion probabilities. In the present paper, a new algorithm for selecting balanced samples is proposed. This method is inspired by simulated annealing algorithms, as a balanced sample selection can be interpreted as an optimization problem. A set of simulation experiments and an example using real data shows the efficiency and the accuracy of the proposed algorithm.