Performance comparison between spatial interpolation and GLM/GAM in estimating relative abundance indices through a simulation study

Yu, Hao; Jiao, Yan; Carstensen, Laurence W.

doi:10.1016/j.fishres.2013.06.002

Cited by 30 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RK, in our case using GAM 1 OK or GAMM 1 OK models, can account for these trends and was performed better than OK. Similar conclusions were reached in studies of fish (Yu et al 2013), soil (Knotters et al 1995;Odeh et al 1995), and solar radiation distributions (Alsamamra et al 2009). In most cases, the GAM 1 OK approach usually performed better than the GAMM 1 OK, but the reasons for this is unclear; one possibility is that the algorithms used to estimate GAMMs are not giving as stable or as reliable estimates as GAMs using only fixed effects.…”

Section: Discussionsupporting

confidence: 80%

A comparison of methods to estimate abundance and biomass from belt transect surveys

Chang

Shank

Hart

2017

Limnology & Ocean Methods

View full text Add to dashboard Cite

It is becoming increasingly popular to use continuously collected acoustic or optical data to estimate abundance or biomass of fish and invertebrates. However, data from such systems are typically highly spatially autocorrelated and zero‐inflated, and thus simple design‐based estimation techniques are not applicable. Model‐based estimation methods can be used to extrapolate observations along the observed track to larger areas. We tested the precision and accuracy of three model‐based methods using both simulations and field data: Ordinary kriging (OK), Generalized Additive Models with kriged model residuals (GAM + OK), and Generalized Additive Mixed Models with kriged model residuals (GAMM + OK), along with a design‐based method (stratified mean, SM). The GAMM + OK method treats small‐scale variations as random effects, whereas the other approaches aggregate nearby data to reduce autocorrelation and random errors. We found that the GAM + OK method with relatively small aggregation lengths generally gave the best performance of the model‐based methods in terms of both accuracy and precision, followed by GAMM + OK. SM estimates were more accurate and precise than the model‐based estimates in the simulations, but only when the study region was stratified accurately. Based on the simulation and field data analysis results, we selected the GAM + OK method to estimate scallop abundance and biomass for the Georges Bank and the Mid‐Atlantic Bight regions for the years 2011–2015. We also provided SM estimates based on careful stratifications to validate the model‐based estimates.

show abstract

Section: Discussionsupporting

confidence: 80%

A comparison of methods to estimate abundance and biomass from belt transect surveys

Chang

Shank

Hart

2017

Limnology & Ocean Methods

View full text Add to dashboard Cite

show abstract

“…Historically, many efforts have been made to solve the difficulties associated with CPUE standardization [ 7 ] promoting the flexibility and the availability of well-tested and user-friendly tools such as Generalized Linear Models (GLMs) and Generalized Additive Models (GAMs) to perform calculation [ 31 ]. However, while considering the nonlinearity of predictors there is evidence that statistical models such as GAMs perform better than GLMs [ 32 ] even if the survey area is not well covered due to the lack of sampling locations or biased designs [ 33 ]. GAMs proved to be also helpful to understand the environmental processes underlying species distributions [ 34 ].…”

Section: Introductionmentioning

confidence: 99%

Accounting for environmental and fishery management factors when standardizing CPUE data from a scientific survey: A case study for Nephrops norvegicus in the Pomo Pits area (Central Adriatic Sea)

et al. 2022

View full text Add to dashboard Cite

Abundance and distribution of commercial marine resources are influenced by environmental variables, which together with fishery patterns may also influence their catchability. However, Catch Per Unit Effort (CPUE) can be standardized in order to remove most of the variability not directly attributable to fish abundance. In the present study, Generalized Additive Models (GAMs) were used to investigate the effect of some environmental and fishery covariates on the spatial distribution and abundance of the Norway lobster Nephrops norvegicus within the Pomo/Jabuka Pits (Central Adriatic Sea) and to include those that resulted significant in a standardization process. N. norvegicus is a commercially important demersal crustacean, altering its catchability over the 24-h cycle and seasons according to its burrowing behavior. A historically exploited fishing ground for this species, since 2015 subject to specific fisheries management measures, is represented by the meso-Adriatic depressions, which are also characterized by particular oceanographic conditions. Both the species behaviour and the features of this study area influence the dynamics of the population offering a challenging case study for a standardization modelling approach. Environmental and catch data were obtained during scientific trawl surveys properly designed to catch N. norvegicus, thus improving the quality of the model input data. Standardization of CPUE from 2 surveys from 2012 to 2019 was conducted building two GAMs for both biomass and density indices. Bathymetry, fishing pressure, dissolved oxygen and salinity proved to be significant drivers influencing catch distribution. After cross validations, the tuned models were then used to predict new indices for the study area and the two survey series by means of informed spatial grids, composed by constant surface cells, to each of which are associated average values of environmental parameters and specific levels of fishing pressure, depending on the management measures in place. The predictions can be used to better describe the structure and the spatio-temporal distribution of the population providing valuable information to evaluate the status of such an important marine resource.

show abstract

“…However, we show that IK may be preferable for the spatial modelling of catch rate data exhibiting these characteristics, and has the best prediction performance regardless of the life history and distribution patterns of those three species. Compared to other known catch rate estimation techniques such as the generalised linear model (GLM) and generalised additive modelling approach (GAM), kriging allows one to estimate catch rates even in the absence of explanatory variables such as environmental factors (Yu et al, 2013). Also, kriging does not share the shortcomings of spatial GAM/GLM and delta-GLM approaches, including the requirement for explanatory variables, error structure assumptions and interaction effect problems (Yu et al, 2013).…”

Section: Discussionmentioning

confidence: 99%

Evaluation of geostatistical estimators and their applicability to characterise the spatial patterns of recreational fishing catch rates

et al. 2015

View full text Add to dashboard Cite

Western Australians are heavily engaged in recreational fishing activities with a participation rate of approximately 30%. An accurate estimation of the spatial distribution of recreational catch per unit effort (catch rates) is an integral component for monitoring fish population changes and to develop strategies for ecosystem-based marine management. Geostatistical techniques such as kriging can provide useful tools for characterising the spatial distributions of recreational catch rates. However, most recreational fishery data are highly skewed, zero-inflated and when expressed as ratios are impacted by the small number problem which can influence the estimates obtained from the traditional kriging. The applicability of ordinary, indicator and Poisson kriging to recreational catch rate data was evaluated for three aquatic species with different behaviours and distribution patterns. The prediction performance of each estimator was assessed based on cross-validation. For all three species, the accuracy plot of the indicator kriging (IK) showed a better agreement between expected and empirical proportions of catch rate data falling within probability intervals of increasing size, as measured by the goodness statistic. Also, indicator kriging was found to be better in predicting the latent catch rate for the three species compared to ordinary and Poisson kriging. For each species, the spatial maps from the three estimators displayed similar patterns but Poisson kriging produced smoother spatial distributions. We show that the IK estimator may be preferable for the spatial modelling of catch rate data exhibiting these characteristics, and has the best prediction performance regardless of the life history and distribution patterns of those three species.

show abstract

Performance comparison between spatial interpolation and GLM/GAM in estimating relative abundance indices through a simulation study

Cited by 30 publications

References 25 publications

A comparison of methods to estimate abundance and biomass from belt transect surveys

A comparison of methods to estimate abundance and biomass from belt transect surveys

Accounting for environmental and fishery management factors when standardizing CPUE data from a scientific survey: A case study for Nephrops norvegicus in the Pomo Pits area (Central Adriatic Sea)

Evaluation of geostatistical estimators and their applicability to characterise the spatial patterns of recreational fishing catch rates

Contact Info

Product

Resources

About