English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The high concentration level of the environmental factors, such as a highammonia concentration and pH level, affect the water quality, affecting fish'ssurvival and mass death. Therefore, there is a critical need to develop controlstrategies to determine optimal, efficient, and reliable feeding and waterquality monitoring processes. In this paper, we revisit the representative fishgrowth model describing the total biomass change by incorporating the fishpopulation density and mortality. Since the measurement data of the totalbiomass and population from the aquaculture systems are limited and difficultto obtain, we validate the new dynamic population model with the individualfish growth data for tracking control purposes. We specifically focus onrelative feeding as a manipulated variable to design traditional and optimalcontrol to track the desired weight reference within the sub-optimaltemperature and dissolved oxygen profiles under different levels of unionizedammonia exposure. Then, we propose a Q-learning approach that learns an optimalfeeding control policy from the simulated data of the fish growth weighttrajectories while managing the ammonia effects. The proposed Q-learningfeeding control prevents fish mortality and achieves good tracking errors ofthe fish weight under the different levels of unionized ammonia. However, itmaintains a relative food consumption that potentially underfeeds the fish.Finally, we propose an optimal algorithm that optimizes the feeding and waterquality of the dynamic fish population growth process. We also show that themodel predictive control decreases fish mortality and reduces food consumptionin all different cases of unionized ammonia exposure.

Model-based versus model-free feeding control and water quality monitoring for fish growth tracking in aquaculture systems