Physics-informed neural networks (PINNs) represent a class of versatile function approximators capable of incorporating the physics principles, e.g., partial differential equations (PDEs), governing a specific dataset within the learning process. This approach offers several benefits: it reduces the need for large datasets, allows for solutions without initial boundary condition knowledge, and adapts to varying spatio-temporal scales without the need for retraining. In LandSense, we use PINNs as an alternative to conventional numerical methods for soil hydraulic parameter estimation. During this seminar, we'll explore how we can utilize PINNs effectively, accompanied by practical examples of forward and inverse problems.