GrowthEstimate

GrowthEstimate is a neural computational model for estimating salmonids' and other species' weight-specific growth rate (SGR). The model uses recurrent neural networks of reservoir computing type and relies on three key biological factors related to growth: weight, digestive efficiency (measured by the pyloric caecal activity ratio of trypsin to chymotrypsin), and protein growth efficiency (measured by the condition factor).

The model was trained using four datasets of different salmonids with size variations and evaluated with 15% of each dataset, resulting in acceptable SGR outputs. Additional tests with other species showed similarities between the estimated and real SGR values and the same ranking of wild population growth.

GrowthEstimate is particularly useful for precise and comparable growth estimation of living resources at individual levels, especially in natural ecosystems where the studied individuals, environmental conditions, food availability, and consumption rates cannot be controlled. The model can help minimize uncertainty in wild stock assessment processes and improve knowledge in nutritional ecology by understanding the biochemical effects of climate change and environmental impact on the growth performance of aquatic living resources in both wild and aquaculture settings.