Dehazing of remote sensing satellite images is crucial for enhancing their quality and improving visual applications. Existing dehazing methods often struggle with the complexities of non-uniform haze distribution in remote sensing imagery. To address this, we introduce the Multi System Self-Correction Network(MSSCN), a novel approach that integrates a Multi System Joint Estimation (MSJE) module and a Self-Correction (SC) module. The MSJE module augments the model’s generalization capability by formulating dehazing as an ensemble problem. The SC module iteratively refines intermediate features, enabling effective handling of non-homogeneous hazy scenes. Rigorous experimental evaluations demonstrate that the MSSCN method outperforms state-of-the-art methods on benchmark remote sensing dehazing datasets, achieving higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) values. The proposed method exhibits robust performance in dehazing remote sensing images with varying haze intensities, showcasing its potential for practical applications.