<p>Accurate population mean estimation is crucial in survey sampling, particularly when dealing with missing or partial data. The intrinsic uncertainty and indeterminacy found in these datasets frequently pose challenges for computational imputation approaches. In this article, by including neutrosophic logic into the imputation process, some novel neutrosophic imputation approaches and their corresponding resultant neutrosophic estimators for population mean estimation are presented along with their properties under simple random sampling (SRS). Neutrosophic logic offers a strong foundation for overcoming the drawbacks of conventional approaches because of its capacity to handle indeterminate and uncertain data. We show that the proposed novel neutrosophic imputation performs better than the conventional neutrosophic imputation approaches through comprehensive simulations and practical experiments. The simulation and practical results demonstrate how the proposed approaches may be used to increase the precision of statistical studies, particularly in domains where ambiguity and partial data are common.</p>