Agriculture is frequently hampered by soil salinity, which has a negative impact on crop growth and yield. This study aims to identify the optimal timing of satellite data acquisition to predict soil salinity levels indirectly using satellite images in cotton growth fields as a basis. Data was collected in the Mingbulak district of Uzbekistan, where soil electrical conductivity (EC) was measured in a laboratory using soil samples collected from various fields with similar management practices. In this research, we present a linear regression model that uses satellite data and the Normalized Difference Salinity Index (NDSI) to forecast soil salinity levels indirectly. The results of the linear regression analysis showed a positive correlation between the soil electrical conductivity values and the NDSI values for each month, with August having the highest correlation (R2 = 0.70). The study found that the cotton growth stages and the process of soil salinity formation in the study area were the main factors affecting the correlation between electrical conductivity and NDSI. The model developed in this study has R2 value of 0.70. This suggests a moderate to strong relationship between the two variables, which is promising for the indirect assessment of soil salinity using the NDSI index. The study discovered a positive relationship between soil electrical conductivity and NDSI values, which were highest in pre-flowering and flowering stages of cotton. Our findings show that satellite-based estimation and modeling with NDSI can be used to indirectly assess cotton field soil salinity, especially during the pre-flowering and flowering stages. This study contributes to the development of optimal satellite data acquisition timing, which can improve soil salinity predictions and agricultural productivity.