Architecture of ThermoONet. The network consists of three branch networks with distinct inputs, parameter group, p₁, p_2-8, and the radiation flux function, E, where E is presented as some discrete locations with m elements sampled on [t̄₁,t̄₂,...,t̄_m]. A layer incorporating the attention mechanism processes the Hadamard product of the outputs from branch net₁ and branch net₂. The resulting output from this layer [$[b_1^1,b_2^1,...,b_p^1$] is then element-wise multiplied (Hadamard product), with the output from branch net₃ [$[b_1^2,b_2^2,...,b_p^2$]. The average of the resulting values is taken as the final output.