Estimating relative abundance from catch and effort data, using neural networks

We develop and test a method to estimate relative abundance from catch and effort data using neural networks. Most stock assessment models use time series of relative abundance as their major source of information on abundance levels. These time series of relative abundance are frequently derived from catch-per-unit-of-effort (CPUE) data, using general linearized models (GLMs). GLMs are used to attempt to remove variation in CPUE that is not related to the abundance of the population. However, GLMs are restricted in the types of relationships between the CPUE and the explanatory variables. An alternative approach is to use structural models based on scientific understanding to develop complex non-linear relationships between CPUE and the explanatory variables. Unfortunately, the scientific understanding required to develop these models may not be available. In contrast to structural models, neural networks uses the data to estimate the structure of the non-linear relationship between CPUE and the explanatory variables. Therefore neural networks may provide a better alternative when the structure of the relationship is uncertain. We use simulated data based on a habitat based-method to test the neural network approach and to compare it to the GLM approach. Cross validation and simulation tests show that the neural network performed better than nominal effort and the GLM approach. However, the improvement over GLMs is not substantial. We applied the neural network model to CPUE data for bigeye tuna (Thunnus obesus) in the Pacific Ocean.

Advantages of using crest nets to sample presettlement larvae of reef fishes in the Caribbean Sea

Identifying the spatial and temporal patterns of larval fish supply and settlement is a key step in understanding the connectivity of meta-populations (Sale et al., 2005). Because of the potentially dispersive nature of the pelagic larval phase of most reef fishes, tracking cohorts from hatching to settlement is extremely difficult (but see Jones et al., 1999). However, for many studies it is sufficient to sample larvae immediately before settlement. Many coral reef fish species use mangrove and seagrass beds as nursery habitats (Nagelkerken et al., 2001; Mumby et al., 2004) and larvae of these species must pass over the reef crest in order to arrive at their preferred settlement habitats. The ability to sample this new cohort of larval fishes provides opportunities for researchers to explore the intricacies of the transition from larva to juvenile (Searcy and Sponaugle, 2001). Quantifying the potential settlers also provides valuable information about the spatial and temporal supply of presettlement larvae (Victor, 1986). Therefore a number of larval sampling methods were developed, one of which is the use of crest nets (Dufour and Galzin, 1993).

Exploring the use of neural networks for biomass forecasts in the Peruvian upwelling ecosystem

A pilot study was conducted to study the ability of an artificial neural network to predict the biomass of Peruvian anchoveta Engraulis ringens, given time series of earlier biomasses, and of environmental parameters (ocenographic data and predator abundances). Acceptable predictions of three months or more appear feasible after thorough scrutiny of the input data set.