Model application niche analysis: Assessing the transferability and generalizability of ecological models

Guidelines for model adaptation: A study of the transferability of a general seagrass ecosystem Dynamic Bayesian Networks model

In general, it is not feasible to collect enough empirical data to capture the entire range of processes that define a complex system, either intrinsically or when viewing the system from a different geographical or temporal perspective. In this context, an alternative approach is to consider model transferability, which is the act of translating a model built for one environment to another less well‐known situation. Model transferability and adaptability may be extremely beneficial—approaches that aid in the reuse and adaption of models, particularly for sites with limited data, would benefit from widespread model uptake. Besides the reduced effort required to develop a model, data collection can be simplified when transferring a model to a different application context. The research presented in this paper focused on a case study to identify and implement guidelines for model adaptation. Our study adapted a general Dynamic Bayesian Networks (DBN) of a seagrass ecosystem to a new location where nodes were similar, but the conditional probability tables varied. We focused on two species of seagrass (Zostera noltei and Zostera marina) located in Arcachon Bay, France. Expert knowledge was used to complement peer‐reviewed literature to identify which components needed adjustment including parameterization and quantification of the model and desired outcomes. We adopted both linguistic labels and scenario‐based elicitation to elicit from experts the conditional probabilities used to quantify the DBN. Following the proposed guidelines, the model structure of the general DBN was retained, but the conditional probability tables were adapted for nodes that characterized the growth dynamics in Zostera spp. population located in Arcachon Bay, as well as the seasonal variation on their reproduction. Particular attention was paid to the light variable as it is a crucial driver of growth and physiology for seagrasses. Our guidelines provide a way to adapt a general DBN to specific ecosystems to maximize model reuse and minimize re‐development effort. Especially important from a transferability perspective are guidelines for ecosystems with limited data, and how simulation and prior predictive approaches can be used in these contexts.

Fusion neural networks for plant classification: learning to combine RGB, hyperspectral, and lidar data

Airborne remote sensing offers unprecedented opportunities to efficiently monitor vegetation, but methods to delineate and classify individual plant species using the collected data are still actively being developed and improved. The Integrating Data science with Trees and Remote Sensing (IDTReeS) plant identification competition openly invited scientists to create and compare individual tree mapping methods. Participants were tasked with training taxon identification algorithms based on two sites, to then transfer their methods to a third unseen site, using field-based plant observations in combination with airborne remote sensing image data products from the National Ecological Observatory Network (NEON). These data were captured by a high resolution digital camera sensitive to red, green, blue (RGB) light, hyperspectral imaging spectrometer spanning the visible to shortwave infrared wavelengths, and lidar systems to capture the spectral and structural properties of vegetation. As participants in the IDTReeS competition, we developed a two-stage deep learning approach to integrate NEON remote sensing data from all three sensors and classify individual plant species and genera. The first stage was a convolutional neural network that generates taxon probabilities from RGB images, and the second stage was a fusion neural network that “learns” how to combine these probabilities with hyperspectral and lidar data. Our two-stage approach leverages the ability of neural networks to flexibly and automatically extract descriptive features from complex image data with high dimensionality. Our method achieved an overall classification accuracy of 0.51 based on the training set, and 0.32 based on the test set which contained data from an unseen site with unknown taxa classes. Although transferability of classification algorithms to unseen sites with unknown species and genus classes proved to be a challenging task, developing methods with openly available NEON data that will be collected in a standardized format for 30 years allows for continual improvements and major gains for members of the computational ecology community. We outline promising directions related to data preparation and processing techniques for further investigation, and provide our code to contribute to open reproducible science efforts.

Synthesis of Two Decades of US EPA's Ecosystem Services Research to Inform Environmental, Community, and Sustainability Decision Making

A conceptual framework is helpful to understand what types of ecosystem services (ES) information is needed to support decision making. Principles of structured decision making are helpful for articulating how ES consideration can influence different elements in a given decision context resulting in changes to the environment, human health, and well-being. This article presents a holistic view of an ES framework, summarizing two decades of the US EPA's ES research, including recent advances in final ES, those ES that provide benefits directly to people. Approximately 150 peer-reviewed publications, technical reports, and book chapters characterize a large ES research portfolio. In introducing framework elements and the suite of relevant US EPA research for each element, both challenges and opportunities are identified. Lessons from research to advance each of the final ES elements can be useful for identifying gaps and future science needs. Ultimately, the goal of this article is to help the reader develop an operational understanding of the final ES conceptual framework, an understanding of the state of science for a number of ES elements, and an introduction to some ES tools, models, and frameworks that may be of use in their case-study applications or decision-making contexts.

Applying circuit theory and landscape linkage maps to reintroduction planning for California Condors

Conservation practitioners are increasingly looking to species translocations as a tool to recover imperiled taxa. Quantitative predictions of where animals are likely to move when released into new areas would allow managers to better address the social, institutional, and ecological dimensions of conservation translocations. Using >5 million California condor (Gymnogyps californianus) occurrence locations from 75 individuals, we developed and tested circuit-based models to predict condor movement away from release sites. We found that circuit-based models of electrical current were well calibrated to the distribution of condor movement data in southern and central California (continuous Boyce Index = 0.86 and 0.98, respectively). Model calibration was improved in southern California when additional nodes were added to the circuit to account for nesting and feeding areas, where condor movement densities were higher (continuous Boyce Index = 0.95). Circuit-based projections of electrical current around a proposed release site in northern California comported with the condor’s historical distribution and revealed that, initially, condor movements would likely be most concentrated in northwestern California and southwest Oregon. Landscape linkage maps, which incorporate information on landscape resistance, complement circuit-based models and aid in the identification of specific avenues for population connectivity or areas where movement between populations may be constrained. We found landscape linkages in the Coast Range and the Sierra Nevada provided the most connectivity to a proposed reintroduction site in northern California. Our methods are applicable to conservation translocations for other species and are flexible, allowing researchers to develop multiple competing hypotheses when there are uncertainties about landscape or social attractants, or uncertainties in the landscape conductance surface.

Drivers and spatial structure of abiotic and biotic properties of lakes, wetlands, and streams at the national scale

Broad-scale studies have improved our ability to make predictions about how freshwater biotic and abiotic properties will respond to changes in climate and land use intensification. Further, fine-scaled studies of lakes, wetlands, or streams have documented the important role of hydrologic connections for understanding many freshwater biotic and abiotic processes. However, lakes, wetlands, and streams are typically studied in isolation of one another at both fine and broad scales. Therefore, it is not known whether these three freshwater types (lakes, wetlands, and streams) respond similarly to ecosystem and watershed drivers nor how they may respond to future global stresses. In this study, we asked, do lake, wetland, and stream biotic and abiotic properties respond to similar ecosystem and watershed drivers and have similar spatial structure at the national scale? We answered this question with three U.S. conterminous data sets of freshwater ecosystems. We used random forest (RF) analysis to quantify the multi-scaled drivers related to variation in nutrients and biota in lakes, wetlands, and streams simultaneously; we used semivariogram analysis to quantify the spatial structure of biotic and abiotic properties and to infer possible mechanisms controlling the ecosystem properties of these freshwater types. We found that abiotic properties responded to similar drivers, had large ranges of spatial autocorrelation, and exhibited multi-scale spatial structure, regardless of freshwater type. However, the dominant drivers of variation in biotic properties depended on freshwater type and had smaller ranges of spatial autocorrelation. Our study is the first to document that drivers and spatial structure differ more between biotic and abiotic variables than across freshwater types, suggesting that some properties of freshwater ecosystems may respond similarly to future global changes.

The 2011 National Wetland Condition Assessment: overview and an invitation

The first National Wetland Condition Assessment (NWCA) was conducted in 2011 by the US Environmental Protection Agency (USEPA) and its federal and state partners, using a survey design that allowed inference of results to national and regional scales. Vegetation, algae, soil, water chemistry, and hydrologic data were collected at each of 1138 locations across the conterminous United States (US). Ecological condition was assessed in relation to a disturbance gradient anchored by least disturbed (reference) and most disturbed sites identified using chemical, physical, and biological disturbance indices based on site-level data. A vegetation multimetric index (VMMI) was developed as an indicator of condition, and included four metrics: a floristic quality assessment index, relative importance of native plants, number of disturbance-tolerant plant species, and relative cover of native monocots. Potential stressors to wetland condition were identified and incorporated into two indicators of vegetation alteration, four indicators of hydrologic alteration, a soil heavy metal index, and a nonnative plant indicator and were used to quantify national and regional stressor extent, and the associated relative and attributable risk. Approximately 48 ± 6% of the national wetland area was found to be in good condition and 32 ± 6% in poor condition as defined by the VMMI. Across the conterminous US, approximately 20% of wetland area had high or very high stressor levels related to nonnative plants. Vegetation removal, hardening, and ditching stressors had the greatest extent of wetland area with high stressor levels, affecting 23-27% of the wetland area in the NWCA sampled population. The results from the 2016 NWCA will build on those from the 2011 assessment and initiate the ability to report on trends in addition to status. The data and tools produced by the NWCA can be used by others to further our knowledge of wetlands in the conterminous US.

Fine-scale spatial homogenization of microbial habitats: a multivariate index of headwater wetland complex condition

With growing public awareness that wetlands are important to society, there are intensifying efforts to understand the ecological condition of those wetlands that remain, and to develop indicators of wetland condition. Indicators based on soils are not well developed and are absent in some current assessment protocols; these could be advantageous, particularly for soils, which are complex habitats for plants, invertebrates, and microbial communities. In this study, we examine whether multivariate soil indicators, correlated with microbial biomass and community composition, can be used to distinguish reference standard (i.e., high condition) headwater wetland complexes from impacted headwater wetland complexes in central Pennsylvania, USA. Our reference standard sites existed in forested landscapes, while our impacted sites were situated in multi-use landscapes and were affected by a range of land-use legacies in the 1900s. We found that current assessment protocols are likely underrepresenting sampling needs to accurately represent site mean soil properties. On average, more samples were required to represent soil property means in reference standard sites compared to impacted sites. Reference standard and impacted sites also had noticeably different types of microbial habitats for the two multivariate soil indices assessed, and impacted sites were more homogenized in terms of the fine-scale (i.e., 1 and 5 m) spatial variability of these indices. Our study shows promise for the use of multivariate soil indices as indicators of wetland condition and provides insights into the sample sizes and scales at which soil sampling should occur during assessments. Future work is needed to test the generalizability of these findings across wetland types and ecoregions and establish definitive links between structural changes in microbial habitats and changes in wetland soil functioning.