One of the main reasons for the decline in fish numbers is the insufficient quality of water used in hatcheries. The degree of purification of recycled water does not meet the requirements for water in pools. Thus, in order to reduce pollution concentrations, it is necessary to develop new technologies for the treatment of recycled water from fish farming plants, including through the integration of a lighting and aeration plant into them, as well as a sorption unit using agricultural waste, namely rice straw

The adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the removal of ammonium () from wastewater. The ANFIS model was developed and validated with a data set from a pilot-scale of adsorption system treating aqueous solutions and wastewater from fish farms. The data sets consist of four parameters, which include pH, temperature, an initial concentration of ammonium and amount of adsorbent. The adsorbent was biochar obtained from rice straw. The ANFIS models performance was assessed through the root mean absolute error (RMSE) and was validated by testing data. The results of the study show that the adaptive neuro-fuzzy inference system (ANFIS) is able to predict the percentage of ammonium removal from adsorption column according to the input variables with acceptable accuracy, suggesting that the adaptive neuro-fuzzy inference system model is a valuable tool for estimating the quality of fish farms water. This model of ANFIS leads to cost reduction because prediction can be done without resorting to efforts that require cost and time.

Aerobic biological treatment of waters in artificial conditions is carried out by symbiotic algobacterial community of attached and free-floating organisms in various types of aerotank and biofilters. With the blowers and mixers of different designs, the biomass is saturated with oxygen. Controlled air supply provides the necessary concentration of dissolved oxygen and stimulates the oxidation of organic and inorganic water pollutants symbiotic community.

The article proposes using the agricultural waste of Cashew Nuts Shells (CNS) from the Republic of Côte d’Ivoire to produce activated carbon used in water treatment by physical activation. Washed and crushed CNS was carbonized at 800 °С. The obtained crushed and charred CNS was physically activated with water vapor within the temperature range of 400 to 700 °С. Specific surfaces (SBET) and porous structures of obtained activated carbon samples were investigated by low-temperature nitrogen absorption using X-ray diffraction (phase) analysis. The results showed that an increase in the activation temperature with a fixed activation time leads to larger material specific surface, microporous structure development and higher total volume of mesoand micro pores of activated carbons obtained. The X-ray phase analysis results demonstrated that the degree of graphitization, interlayer spacing and crystallite size change insignificantly. It was shown that CNS can be used for activated carbon production that is not inferior by its sorption properties to analogues currently used for water purification.