With the objectives to acquire the fundamental data of the territorial resource, understandthe impacts of human activities on the land use and cover patterns and evaluate the potential of thefuture exploitation, an intensive land cover classification with an accuracy of 93% has beencompleted for North Ningxia by remote sensing technique based on the adoption of a combinationmethod composed of texture training, maximum likelihood classification and post-processing such asre-allocation and aggregation. This classification result was incorporated with the contemporaneoussocio-economic and meteorological data for cross-sectional regression modelling to reveal the spatialdeterminants of the land cover patterns and understand the human-environmental relationships. Atentative evaluation on the potential of soil exploitation in the near future was carried out incombination with our land use and cover change detection results aiming at supplying some usefulreferences for the central and local governments in their sustainable land use planning.