Water is an essential resource for life on Earth, as both people and the ecosystem depend on obtaining access to clean water. However, during the past few decades, uncontrolled use of natural resources, fast industrialization, growing urbanization, and a constantly growing population have collectively shown a negative impact on water quality [1]. Since ions containing heavy metals are among the majority of frequently discharged pollutants, they should be considered serious [2, 3]. Although heavy metals are naturally occurring trace elements in aquatic environments, industrial wastes, geochemical structures, mining, and agricultural practices have raised the levels of these elements. Mercury (Hg), cadmium (Cd), copper (Cu), zinc (Zn), silver (Ag), iron (Fe), platinum (Pt), arsenic (As), chromium (Cr), thallium (Ti), and lead (Pb) are a few examples of heavy metals [4, 5]. Cadmium is one of the most important elements among the metallic contaminants present in wastewater and is frequently discharged by the electroplating, battery, electrode, and metallurgical sectors. The US Environmental Protection Agency (USEPA) has recommended an acceptable concentration of 0.003 mg/L for cadmium in drinking water, but the World Health Organization (WHO) has set a limit contamination threshold of 0.005 mg/L [6].
Humans have been shown to experience negative effects from low levels of cadmium exposure, including liver disease, bone abnormalities, and renal failure. Metal recovery from aqueous solutions is a difficult task for environmental engineers, and many different approaches use different separation techniques [7, 8]. Heavy metal removal from wastewater can be accomplished using a variety of standard methods, including electrolytic recovery, evaporation, chemical oxidation, precipitation, chemical coagulation, solidification, and membrane separation. However, because these methods are highly expensive to treat wastewater with low concentrations of heavy metals, their adoption is constrained by several variables, including technological and economic status [9].
In comparison with alternative traditional treatment techniques, the biosorption process presents potential benefits like reduced operational expenses, reduced amounts of chemical or biological sludge, enhanced efficacy in removing heavy metals from diluted solutions, biosorbent regeneration, the potential for metal recovery, and environmental friendliness [10]. The novel technique of biosorption extracts hazardous metals from aqueous solutions by utilizing either living or dead biomasses. The two primary mechanisms of biosorption are chemical adsorption and physical adsorption (electrostatic attraction–Vanderwaal forces of attraction). For the biosorption of metal ions, a variety of biomasses including bacteria, yeast, fungi, and algae have been utilized extensively [11, 12].
Marine algae have the highest metal binding capabilities of all living materials because their cell walls include lipids, proteins, or polysaccharides. The seaweed's cell walls are made of three different types of biopolymers that give it its biosorption capacity: cellulose, alginate, a heteropolymer made of mannuronic acid and guluronic acid residues, and fucoidan, a heteropolymer composed of sulfated esters of fucose moieties and glucuronic acid. Amino, sulphate, carboxyl, and hydroxyl groups are among the functional groups found in seaweed biomass [13]. When compared to single-species biosorbents, mixed seaweed biosorbents have many advantages for the removal of metals. Due to their various surface properties and chemical compositions, several seaweed species when combined can increase the total capacity for binding metals. Furthermore, increased efficiency and specificity in metal removal techniques can result from the synergistic effects between different seaweed components. In addition, mixed seaweed biosorbents frequently have improved stability and durability, ensuring extended use and efficient metal removal over time [14].
In order to understand the uncertain nonlinear pattern of heavy metal elimination using different treatment procedures, numerous artificial intelligence models have been established. Neural networks, logic, regression, and hybrid models are some of these models. Moreover, these models have been compared to a variety of conventional models, such as mathematical, isothermal, statistical, empirical, and physical models [15]. To model and optimize contamination removal approaches, these classical tools need to identify a goal for each group of input variables; hence, the target can change while the other variables remain constant at the same time [16]. Since these surrogate models have primarily been used for adsorption systems with a single pollutant, it is essential to extend their application to the prediction and modeling of adsorption systems with several adsorbates, or multi-component adsorption. Through the use of adsorption systems, scientific and practical models that utilize numerical computational approaches, such as artificial neural networks (ANNs), can greatly enhance the wastewater treatment process generally [17].
Every year, the tides throw a significant amount of seaweed onto beaches. These organic natural resources are handled as domestic waste since they are waste materials. As of now, researchers have employed a variety of materials to investigate the efficacy of removal from aqueous solutions [18]. Sargassum fusciformis (brown algae), Codium decorticatum (green algae), and Hypnea valentiae (red algae) were the seaweeds found around the coast that were selected for this investigation due to their component availability. The goal of this study is to develop a mixed seaweed biosorbent that can effectively remove cadmium (II) ions from aqueous solutions. The study assessed the impact of various parameters on the removal efficiency. The metal removal mechanism and kinetic parameter estimates were determined by kinetic experiments. Thermodynamic studies were used to confirm the sorption's nature and feasibility. Additionally, analysis and optimization of the ANN model were conducted to predict the mixed sorbent's efficiency in removing Cd (II).