sdmTMB: An R Package for Fast, Flexible, and User-Friendly Generalized Linear Mixed Effects Models with Spatial and Spatiotemporal Random Fields

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2022, Volume and Issue: unknown

Published: March 27, 2022

Abstract Geostatistical spatial or spatiotemporal data are common across scientific fields. However, appropriate models to analyse these data, such as generalised linear mixed effects (GLMMs) with Gaussian Markov random fields (GMRFs), computationally intensive and challenging for many users implement. Here, we introduce the R package sdmTMB , which extends flexible interface familiar of lme4, glmmTMB mgcv include latent GMRFs using an SPDE-(stochastic partial differential equation) based approach. SPDE matrices constructed fmesher estimation is conducted via maximum marginal likelihood TMB Bayesian inference tmbstan rstan . We describe model explore case studies that illustrate ’s flexibility in implementing penalised smoothers, non-stationary processes (time-varying spatially varying coefficients), hurdle models, cross-validation anisotropy (directionally dependent correlation). Finally, compare functionality, speed, interfaces related software, demonstrating can be order magnitude faster than R- INLA hope will help open this useful class a wider field geostatistical analysts.

Language: Английский

---

Trade‐offs in covariate selection for species distribution models: a methodological comparison

Ecography, Journal Year: 2019, Volume and Issue: 43(1), P. 11 - 24

Published: Oct. 2, 2019

Species distribution models (SDMs) are a common approach to describing species’ space‐use and spatially‐explicit abundance. With myriad of model types, methods parameterization options available, it is challenging make informed decisions about how build robust SDMs appropriate for given purpose. One key component SDM development the covariates, such as inclusion covariates that reflect underlying processes (e.g. abiotic biotic covariates) act proxies unobserved space time covariates). It unclear different apportion variance among suite influence accuracy performance. To examine trade‐offs in covariation SDMs, we explore attribution spatiotemporal environmental variation across SDMs. We first used simulated species distributions with known preferences compare three types SDM: machine learning (boosted regression tree), semi‐parametric (generalized additive model) mixed‐effects (vector autoregressive model, VAST). then applied same comparative framework case study fish (arrowtooth flounder, pacific cod walleye pollock) eastern Bering Sea, USA. Model type covariate both had significant effects on found including either or typically reproduced patterns abundance tested, but performance was maximized when framework. Our results reveal current generation tools between accurately estimating abundance, spatial patterns, quantifying species–environment relationships. These comparisons can help users better understand sources bias estimate error.

Language: Английский

---

Integrated Modeling to Evaluate Climate Change Impacts on Coupled Social-Ecological Systems in Alaska

Frontiers in Marine Science, Journal Year: 2020, Volume and Issue: 6

Published: Jan. 14, 2020

The Alaska CLimate Integrated Modeling (ACLIM) project represents a comprehensive, multi-year, interdisciplinary effort to characterize and climate-driven changes the Eastern Bering Sea ecosystem, from physics fishing communities. Results ACLIM are being used understand how different regional fisheries management approaches can help promote adaptation sustain fish shellfish populations inform managers fishery dependent communities of risks associated with future climate scenarios. relies on iterative communications outreach that has informed selection This approach ensures research team focuses policy relevant scenarios explore realistic options for Within each cycle, continues improve: methods downscaling models, climate-enhanced biological socio-economic modeling, strategy evaluation within common analytical framework. evolving nature framework improved understanding system responses feedbacks considered projections continue reflect objectives bodies. multi-model projection facilitates quantification relative contributions forcing scenario, parameter, structural uncertainty between models. Ensemble means variance models informs risk assessments under first phase conditions end 21st century complete, catch core species baseline (status quo) two alternative modeling serves as guide multidisciplinary integrated impact decision making in other large marine ecosystems.

Language: Английский

---

Catch per unit effort modelling for stock assessment: A summary of good practices

Fisheries Research, Journal Year: 2023, Volume and Issue: 269, P. 106860 - 106860

Published: Sept. 30, 2023

Language: Английский

---

Spatially varying coefficients can improve parsimony and descriptive power for species distribution models

Ecography, Journal Year: 2023, Volume and Issue: 2023(5)

Published: April 10, 2023

Species distribution models (SDMs) are widely used to relate species occurrence and density local environmental conditions, often include a spatially correlated variable account for spatial patterns in residuals. Ecologists have extended SDMs varying coefficients (SVCs), where the response given covariate varies smoothly over space time. However, SVCs see relatively little use perhaps because they remain less known relative other SDM techniques. We therefore review ecological contexts can improve interpretability descriptive power from SDMs, including responses regional indices that represent teleconnections; density‐dependent habitat selection; detectability; context‐dependent interactions with unmeasured covariates. then illustrate three additional examples detail using vector autoregressive spatio‐temporal (VAST) model. First, decadal trends model identifies arrowtooth flounder Atheresthes stomias Bering Sea 1982 2019. Second, trait‐based joint highlights role of body size temperature community assembly Gulf Alaska. Third, an age‐structured walleye pollock Gadus chalcogrammus contrasts cohorts broad distributions (1996 2009) those more constrained (2002 2015). conclude extend address wide variety be better understand range processes, e.g. dependence, population dynamics.

Language: Английский

---

Shifts in the physical environment in the Pacific Arctic and implications for ecological timing and conditions

Deep Sea Research Part II Topical Studies in Oceanography, Journal Year: 2020, Volume and Issue: 177, P. 104802 - 104802

Published: May 27, 2020

Language: Английский

---

Understanding transboundary stocks’ availability by combining multiple fisheries-independent surveys and oceanographic conditions in spatiotemporal models

ICES Journal of Marine Science, Journal Year: 2022, Volume and Issue: 79(4), P. 1063 - 1074

Published: March 3, 2022

Abstract Shifts in the distribution of groundfish species as oceans warm can complicate management efforts if distributions expand beyond extent existing scientific surveys, changing proportion available to any one survey each year. We developed first-ever model-based biomass estimates for three Bering Sea groundfishes (walleye pollock (Gadus chalcogrammus), Pacific cod macrocephalus), and Alaska plaice (Pleuronectes quadrituberculatus)) by combining fishery-independent bottom trawl data from U.S. Russia a spatiotemporal framework using Vector Autoregressive Spatio-Temporal (VAST) models. estimated fishing-power correction calibrate disparate sets effect an annual oceanographic index explain variation density. Groundfish densities shifted northward relative historical densities, high-density areas spanned international border, particularly years warmer than long-term average. In final year comprehensive (2017), 49%, 65%, 47% was western northern pollock, cod, plaice, respectively, suggesting that availability more regular eastern is declining. conclude partnerships combine past coordinate future collection are necessary track fish they shift areas.

Language: Английский

---

Ecological responses to climate perturbations and minimal sea ice in the northern Bering Sea

Deep Sea Research Part II Topical Studies in Oceanography, Journal Year: 2020, Volume and Issue: 181-182, P. 104914 - 104914

Published: Dec. 1, 2020

Language: Английский

---

Adapting to climate‐driven distribution shifts using model‐based indices and age composition from multiple surveys in the walleye pollock (Gadus chalcogrammus) stock assessment

Fisheries Oceanography, Journal Year: 2020, Volume and Issue: 29(6), P. 541 - 557

Published: Aug. 21, 2020

Abstract The northern Bering Sea is transitioning from an Arctic to subarctic fish community as climate warms. Scientists and managers aim understand how these changing conditions are influencing biomass spatial distribution in this region, both used inform stock assessments fisheries management advice. Here, we use a spatio‐temporal model for walleye pollock ( Gadus chalcogrammus ) provide two inputs its assessment model: (a) alternative model‐based index (b) age compositions. Both were derived multiple fishery‐independent data that span different regions of space time. We developed utilizes the standard surveys despite inconsistencies temporal coverage, found using improved scope total biomass. Age composition information indicated density increasing moving farther north, particularly older pollock. including cold pool extent could be extrapolate densities unsampled years. Stock parameter estimates similar input. This study demonstrates can facilitate rapid changes structure response climate‐driven shifts distribution. conclude assimilating neighboring survey areas, such Chukchi western Sea, would improve understanding efforts distributions change under warming climate.

Language: Английский

---

Impacts of fisheries-dependent spatial sampling patterns on catch-per-unit-effort standardization: A simulation study and fishery application

Fisheries Research, Journal Year: 2021, Volume and Issue: 246, P. 106169 - 106169

Published: Nov. 10, 2021

Abundance indices derived from fisheries-dependent data (catch-per-unit-effort or CPUE) are known to have potential for bias, in part because of the usual non-random nature fisheries spatial distributions. However, given cost and lack availability fisheries-independent surveys, CPUE remains a common informative input stock assessments. Recent research efforts focused on development spatiotemporal delta-generalized linear mixed models (GLMMs) which simultaneously standardize predict abundance unfished areas when estimating index. These can include local seasonal environmental covariates (e.g. sea surface temperature) spatially varying response regional annual El Niño Southern Oscillation) interpolate into areas. Spatiotemporal delta-GLMMs been demonstrated simulation studies perform better than conventional, non-spatial (GLMs). rarely evaluated situations where sampling patterns change over time expansion closures). This study develops framework evaluate 1) how may bias estimated indices, 2) shifts impact our ability estimate temporal changes catchability, 3) including and/or improve estimation sampling. then applied case example pattern changed dramatically (contraction Japanese pole-and-line fishery skipjack tuna Katsuwonus pelamis western central Pacific Ocean). Results simulations indicate that proportion underlying biomass produce similar those produced under random Though were not perfect, GLMMs generally able disentangle catchability too extreme. Lastly, inclusion oceanographic did index some cases resulted degraded model performance.

Language: Английский

---