Land use and land cover (LULC) has undergone drastic changes with the rapid growth of the global population, economic development, and the expansion of agricultural activities. However, the uncertainty of classification algorithms and image resolution based on satellite data for land cover mapping, particularly cropland cover mapping, needs to be investigated sufficiently. In this study, the influence of different spatial-resolution images on classification results was explored by comparing the differences between four machine learning algorithms for LULC mapping. The classification results of this model were also compared with existing global land cover datasets to determine whether the model was capable of producing reliable results. According to the results of this study, the random forest (RF) classifier outperformed the support vector machine (SVM), decision tree (DT), and artificial neural network (ANN) with an overall accuracy (OA) and kappa coefficient of 81.99% and 0.78, respectively. However, SVM and ANN showed greater accuracy on the water class and unused land class, respectively. With increasing spatial resolution, RF’s accuracy increased initially and then decreased when classifying images with five different spatial resolutions (30 m, 16 m, 10 m, 8 m, and 2 m). In particular, with an OA of 82.54% and a kappa coefficient of 0.78, RF performed the best on images with 8 m resolution. Additionally, the RF-based image with 8 m resolution produced a higher OA of 0.88 for cropland. Topography is the main factor that determines the classification performance of different-resolution images. The classification accuracies of RF10 m and RF30 m (10 m and 30 m resolution images, respectively, using RF) were higher (OAs of 93.59% and 94.59%, respectively) than those of the global land cover dataset (LC10 m and LC30 m, land cover images with 10 m and 30 m resolution, respectively), whose high-resolution images showed more details of the land cover. The results of this study highlight that classification algorithms and image resolution are the sources of uncertainty for land mapping. Obtaining reliable land cover mapping requires the use of appropriate classification algorithms and spatial resolution. With these results, it will be possible to develop a national land monitoring system and basic ecological climate models using LULC.

Erratic rainfall and misalignment between the rainy season and the growing season of winter wheat greatly limit rainfed winter wheat yield in the Loess Plateau of China. To increase the grain yield of winter wheat in this region, the effects of different agronomic practices, including adjusting planting pattern (NR, narrow row spacing), increasing seeding rate (high seeding rate, HS), decreasing basal nitrogen rate and increasing top-dressed nitrogen rate (DBN), and replacing an old cultivar with a new cultivar (NC) on wheat yield were investigated for two consecutive years. The results showed that the current grain yield of rainfed winter wheat in the Loess Plateau could be increased to 5879–7093 kg ha⁻¹ by HS, DBN and NC practices relative to the practice of high-yielding farmers (PF). The increased yield due to HS, DBN and NC was attributed to the higher number of spikes ha⁻¹, 1000-grain weight, and kernels spike⁻¹. Before the flowering stage, HS increased soil water consumption (SWC) in 1–3 m subsoil due to the higher plant population compared with that of PF, whereas DBN decreased SWC in the 0–2 m soil layer compared with that of PF. After the flowering stage, HS, DBN, and NC increased SWC by 8–16 mm in 2–3 m subsoil compared to PF. The water use efficiency (WUE) was increased under DBN and NC in comparison with PF. However, the WUE did not increase under HS as it had the highest evapotranspiration among the five treatments. Increasing the use of subsoil water during the late growth stage by optimizing agronomic practices or applying new cultivars with expansive roots should be the primary approach to increase rainfed winter wheat yield in this region.