The rainfall infiltration model plays a key role in the fields of seepage theory and geological hazard evaluation. To reflect the change in the moisture content in soil during rainfall infiltration, the infiltration process was segmented into stages, and an improved unsaturated wetting front extension model was proposed by introducing unsaturated soil parameters on the basis of the traditional infiltration model. The variation rules of surface moisture content and wetting front depth were revealed under the condition of uniform or non-uniform moisture content distribution in soil. The results indicate that the surface moisture content and wetting front depth increase nonlinearly with time during the infiltration process, and the proposed model is in good agreement with the numerical simulation results, the maximum error is less than 5%, while the growth rate under two hypotheses shows obvious differences for different rainfall intensities. Moreover, due to the variation in the moisture content with time, the proposed model calculates a lower moisture content than that of the traditional model under the same conditions, but the expansion depth of the wetting front is higher and the range of influence on soil is greater.

Transient pore-air pressure in gas-loaded cover soils is difficult to observe between monitoring depths. We develop a coupled water–air inverse physics-informed neural network as a numerical proof of concept. Under a pre-calibrated constitutive model, three numerically sampled depths supply pore-air pressure, pore-water pressure, and saturation targets. An independent air-pressure field represents overpressure; the coupled balances constrain the joint state. On a one-dimensional same-equation benchmark, the full-window gas-pressure error is 0.0463. The data-only ablation reaches 0.0043, while the coupled residuals improve water pressure, saturation, and front monotonicity. Before the 495 s reference injection-base zero-stress crossing, gas-pressure error is 0.0448; on cells with positive reference effective stress, the stress-reduction error is 0.0450. Later states test numerical tracking under overload. The plane-model case fits two-dimensional FLAC2D training series with a one-dimensional residual omitting lateral transport, giving a responding-depth excess-overpressure error of 0.186. A residual-free line-M test evaluates architecture-only interpolation at 11 held-out depths. The configuration-specific Bishop post-process yields zero-to-seven-minute onset times and a 43% minimum-stress spread across three effective-stress parameter forms. These numerical fields support subsequent mechanical interpretation; physical validation requires measured interior states, and stability assessment requires a mechanical model.