In shallow water environments, matched-field processing (MFP) and matched-mode processing (MMP) are proven techniques for doing source localization. In these environments, the acoustic field propagates at long range as depth-dependent modes. Given a knowledge of the modes, it is possible to estimate source depth. In MMP, the pressure field is typically sampled over depth with a vertical line array (VLA) in order to extract the mode amplitudes. In this paper, we focus on horizontal line arrays (HLA) as they are generally more practical for at sea applications. Considering an impulsive low-frequency source (1–100 Hz) in a shallow water environment (100–400 m), we propose an efficient method to estimate source depth by modal decomposition of the pressure field recorded on an HLA of sensors. Mode amplitudes are estimated using the frequency-wavenumber transform, which is the 2D Fourier transform of a time-distance section. We first study the robustness of the presented method against noise and against environmental mismatches on simulated data. Then, the method is applied both to at sea and laboratory data. We also show that the source depth estimation is drastically improved by incorporating the sign of the mode amplitudes.