Progress in modeling quality in aquaculture: an application of the Self-Organizing Map to the study of skeletal anomalies and meristic counts in gilthead seabream (Sparus aurata, L. 1758)

Abstract

One of the most common drawbacks of artificial life conditions\ud imposed by aquaculture is the quite high presence of skeletal\ud anomalies (SAs) in reared fish, which reduce both functional\ud performances and marketing image ⁄ commercial value of the\ud reared lots. Thus, skeletal malformations and their incidence\ud are one of the most important factors affecting fish farmer s\ud production costs, and several efforts have been due to develop\ud appropriate tools in detecting patterns of co-variation among\ud rearing parameters and fish quality. In this paper we explore\ud the advantages of using Self-Organized Maps (SOMs) when\ud dealing with the analysis of correlations between the pattern of\ud SA presence and rearing parameters in gilthead seabream\ud (Sparus aurata L.), that is a largely reared fish of high\ud commercial value. SOM, which is one of the best known neural\ud networks with unsupervised learning rules, were applied to\ud develop a model of the occurrence of SAs, both in terms of\ud type and quantity, in seabream lots from different rearing\ud approaches (extensive, semi-intensive and intensive). The\ud trained SOMs classified lots according to the variation\ud observed in the different weights of SAs, but also allows the\ud detection of a series of correspondence, namely between: (i) the\ud patter of SAs occurrence and the different rearing approach\ud currently used in seabream aquaculture; and (ii) the total SAs\ud incidence and the variability of meristic counts, represent a\ud completely independent dataset. Mesocosms resulted the best\ud rearing approach to produce wild-like fish, whereas intensive\ud rearing is characterized by the large presence of SA. Globally,\ud results suggested that this approach is reliable to be used for\ud estimate the distance between aquaculture products and the\ud wild-like phenotype used as quality reference

Environmental Conditioning of Skeletal Anomalies Typology and Frequency in Gilthead Seabream (Sparus aurata L., 1758) Juveniles

“…The observation that when meristic count variability increases so does the occurrence of skeletal anomalies confirms what has been previously reported [69] in the same species for a larger number of juveniles, subadults and adults.…”

Skeletal Anomaly Monitoring in Rainbow Trout (Oncorhynchus mykiss, Walbaum 1792) Reared under Different Conditions

“…Such high rates of anomalous individuals in reared lots of rainbow trout, never previously described in literature, could be explained by applying the methodology applied in this study, which has now been amply standardized and already applied to other farmed, mostly marine, fish [11]–[13], [15], [16], [33]–[36]. The detailed and mass monitoring of all anomalies affecting the splanchnocranium , vertebral axis and fins was never applied to salmonids, often scored only for vertebrae centra anomalies, or inspected only for externally detectable anomalies (see Table 10 for a brief review of some studies on salmonids anomalies), of furnishing lower deformation rates.…”

Skeletal anomalies in reared European fish larvae and juveniles. Part 2: main typologies, occurrences and causative factors

“…unsupervised artificial neural networks; see Russo et al . , ) may allow integration of multidisciplinary and multilevel data, even if it is characterized by non‐linearity, internal redundancy and noise, and by obtaining classification, pattern recognition and empirical modelling. Such investigations should be aimed in particular to obtain deeper insights into the mechanics of bone anomalies, the anomalous mechanical load acting on developing skeletal elements being one of the most credited causative factors for many vertebrae anomalies, but the molecular pathways linking mechanics and bone development remain largely unknown.…”