jabbrv-ltwa-all.ldf jabbrv-ltwa-en.ldf Geophysical inversion plays a pivotal role in understanding the Earth’s internal structure. Recently generative neural networks (GNNs), such as normalizing flow models (NFMs), have gained popularity for solving Bayesian inversion problems. However, their effectiveness is often hindered by the loss function bias. This bias occurs due to the global nature of loss functions in NFMs, which lead to inaccuracies when applied to geophysical inversion, where the Earth model is unique. To address this, we propose the Iterative Normalizing Flow Model(INFM), a novel approach that mitigates loss function bias by progressively narrowing the prior distribution’s support set in each iteration, while ensuring that the posterior distribution accurately converges to the target. Our experiments, validated on high-dimensional Bayesian inversion tasks, show that INFM significantly enhances inversion accuracy without increasing network complexity or computational cost. When applied to the Earth’s 1-D structure model inversion, our method revealed key insights, such as a lower core density compared to the PREM model and the presence of anisotropy in both the mantle and core, consistent with previous studies. These findings suggest that the INFM method offer high computational efficiency and accuracy, making it well-suited for large-scale geophysical inversion problems.