This manuscript introduces a long-term, high-resolution oasis land-cover dataset, which is valuable for understanding the spatio-temporal dynamics of oasis systems and for related environmental and resource management applications. However, the current manuscript still contains several issues, including technical details and result presentation, that need to be addressed. My specific comments are provided below.

Major comments:

1. In the introduction section, the overview of current continuous land cover data is not sufficient. Specifically, all land cover datasets mentioned in Section 2.8 lack sufficient description.
2. The validation of land cover dynamics in China's oases from 1987 to 2024 should be clarified.
3. The manuscript applies the LandTrendr algorithm, but key parameter settings (e.g., maximum segments, recovery threshold) are not clearly described in the main text. Please clarify whether default parameters were used or provide the main parameter values.

Minor revision:

Line 97 The manuscript states that the tasseled cap transformation was applied using coefficients from Crist et al. (1985). Given that this study uses Landsat 5, 7, and 8 data, the authors should check and clarify whether the cited coefficients are appropriate for all sensors involved.

Line 126 “…a single composite disturbance metric (MAGPCA)”, “PCA” should be a subscript.

Line 129  “…we obtained DURmode and YODmode maps”, “mode” should be a subscript.

Line 136 In Section 2.6, the manuscript describes an evaluation of the dispersion of the detected year-of-disturbance (YOD). However, the results of this analysis (e.g., in figures or tables) are missing. The authors should provide the relevant results to support this analysis.

Line 195 The manuscript reports accuracy assessment results, but it is unclear whether the training and validation samples are spatially well distributed across the study area. Additional details on the spatial distribution of the samples should be provided.

Line 321 Grammatical error: “producing a high spatio-temporal resolution land cover datasets for oases are essential …”.

This work produced a valuable datasets on the oasis of China. Generally, the method for data production is reasonable. My concerns mainly related to the basic definition of oasis. The detail comments are given below.

• The definition of oasis must be clearly described. The present version of the preprint defined it as "all land-cover types other than barren land". Oasis is a geographical complex of various land cover types including areas with vegetation cover and non vegetation cover. According to the nature of the oasis, it is defined following several criteria at least: (1) located in desert areas; (2) with water sources in the forms such as streams, rivers, ground water, constructed channels et al.;(3) specific plants and other organisms formed azonal vegetated landscape.
• In desert areas, the precipitation and the water resources featured with great annual fluctuation. Thus the abrupt change in reflectance may not indicate a change in land cover types. I suggest a caution when use annual indices such as NDVI in mapping, and considered the impacts of climate fluctuation on the accuracy.
• As to the comparison with other land cover products, resolutions of the land cover products matters. For instance, spatial resolution of MCD12Q1 is 500 m, while ESACCI_LC is 300 m. The comparison with land cover dataset greatly differed in spatial resolution is no sense. What's more, evaluating the accuracy of other datasets using the samples collected for OasisMap30 directly may not reasonable due to the difference in resolution.

After going through the manuscript, there are some errors, or unreasonable expressions. Some examples are given below.

• Figure 2, the table overlays with map.
• In figure S2, there are errors in label of X axis.
• In line 80-81, the remark "we manually inspected the imagery and masked out mountain regions and clearly unvegetated deserts (e.g., the Taklamakan Desert)" is not consistent to the data described in the next sections and the supplement. Oasis in the Taklamakan Desert also were mapped.
• As illustrated in Figure 2 and 3, the legend non-oasis is not reasonable. According to the definition of oasis, fragmented barren areas within an oasis are elements of oasis. I suggest a modification of the relevant figures.
• In Figure 3, the dashed lines were used to show the mountains. However, mountains also areas. To avoid the misunderstanding of readers, change the symbols of mountains. For instance, only keep the text labels.

High spatio-temporal resolution maps of oasis land cover are valuable for understanding ecological and societal development processes in dryland regions. It is an interesting work on high-spatio-temporal resolution oasis mapping, which can enhance studies on oasis landscape pattern and sustainable development of oasis region. There are some suggestion and comments, from my side, to revise and improve this manuscrit.

1.  The scientific question of this study should be reorganized and rewritten for more clear and specific, especially for mapping techniques and methods on oasis data. 

2.  How the random forest model on land-cover classification used in this study, how to get the independent variables? 

3. More discussion should be added, on the methodogical techniques,  innovation, novelty, also the significance.