Estimating wildlife distribution and abundance from line transect surveys conducted from platforms of opportunity

Abstract

Line transect data obtained from 'platforms of opportunity' are useful for the monitoring of long term trends in dolphin populations which occur over vast areas, yet analyses of such data axe problematic due to violation of fundamental assumptions of line transect methodology. In this thesis we develop methods which allow estimates of dolphin relative abundance to be obtained when certain assumptions of line transect sampling are violated. Generalised additive models are used to model encounter rate and mean school size as a function of spatially and temporally referenced covariates. The estimated relationship between the response and the environmental and locational covariates is then used to obtain a predicted surface for the response over the entire survey region. Given those predicted surfaces, a density surface can then be obtained and an estimate of abundance computed by numerically integrating over the entire survey region. This approach is particularly useful when search effort is not random, in which case standard line transect methods would yield biased estimates. Estimates of f (0) (the inverse of the effective strip (half-)width), an essential component of the line transect estimator, may also be biased due to heterogeneity in detection probabilities. We developed a conditional likelihood approach in which covariate effects are directly incorporated into the estimation procedure. Simulation results indicated that the method performs well in the presence of size-bias. When multiple covariates are used, it is important that covariate selection be carried out. As an example we applied the methods described above to eastern tropical Pacific dolphin stocks. However, uncertainty in stock identification has never been directly incorporated into methods used to obtain estimates of relative or absolute abundance. Therefore we illustrate an approach in which trends in dolphin relative abundance axe monitored by small areas, rather than stocks.