Abstract: The Northeast China is a vital grain production base for China. However, unreasonable use of cultivated land in this region has caused a decline in soil fertility, posing a severe threat to the nation's food security. This study focused on the Youyi Farm in the Sanjiang Plain, where 103 surface soil samples in cropland were collected. Sentinel-2 images in April, May, and June from 2019 to 2023 were selected to predict soil organic matter, total nitrogen, total phosphorus, and total potassium based on a random forest algorithm. To investigate the temporal effects of images on the prediction of these soil fertility properties, the images were first divided into seven-year groups (five single-year-groups: 2019, 2020, 2021, 2022, and 2023, and two multi-year-groups: 2020–2022 and 2019–2023). Then, within each year-group, the images were further divided into four month-groups (three single-month-groups: April, May, and June, and one multi-month-group: April–June). Finally, 28 synthetic images were constructed by combining year-groups and month-groups. The results indicate that the highest prediction accuracy was obtained for soil organic matter, with an R2 of 0.62 and an RMSE of 0.66%. The prediction accuracy of soil total nitrogen was similar to that of organic matter, with an R2 of 0.58 and an RMSE of 0.03%. Total phosphorus predictions were not sufficiently accurate for practical applications, with the highest accuracy of an R2 of 0.13 and RMSE of 98.44 mg/kg. The total potassium achieved a relatively high prediction accuracy of an R2 of 0.53 and RMSE of 0.15%. The results in different year-groups and month-groups indicated that multi-year synthetic images outperformed single-year synthetic images, and the synthetic images from May showed the highest prediction accuracy. Thus, selecting proper temporal images can achieve accurate predictions of soil organic matter, total nitrogen, and total potassium. However, an accurate prediction of total phosphorus may require additional environmental variables. This study provides technical support for soil fertility monitoring in Northeast China.