Beitang landscape is a production system and land use pattern that ancient people created to adapt to droughts and floods during a long traditional farming culture. It has a critical reference meaning for water resource use and water systems protection in modern cities. Taking the Shangzhuang Basin (China) as an example, this study used multi-source data, such as remote sensing images, Beitang vector dataset, land-use dataset, elevation, slope, river, road, and field survey, to investigate the spatial distribution and influencing factors Beitang landscape. Results showed that in a typical small watershed basin, an area of ponds accounted for 1.0%, about 12 ponds per square kilometer—the average area of ponds is 814 m², of which the vast majority is less than 1000 m². The study found that the spatial distribution of Beitang in the Shangzhuang Basin has cluster characteristics, influenced by elevation, slope, aspect, river, roads, villages, farmland, woodland, and other factors, all of which have closely related to the natural environment development and human activities. The upstream, middle, and downstream of three Beitang landscapes were coordinated to support the Beitang landscape system in the small watershed of the basin. Findings provided a model for protecting and utilizing natural water systems in rural areas during the construction of sponge cities.

This paper presents Geo-Esthetics, an application-oriented workflow that uses remote sensing imagery as source morphology for generative design. The study addresses a design problem: how can large-scale terrestrial textures be extracted, abstracted, and organized as pattern references for parametric and visual design? Nine representative geomorphological settings were selected. For each case, Sentinel-2 imagery was cropped into a 2 km × 2 km geographic window, enhanced using spectral-index selection and Contrast Limited Adaptive Histogram Equalization (CLAHE), and used as an image prompt in Midjourney v6.0. A consistent prompt structure and parameter setting were applied. Four variants were generated for each case and screened according to topological fidelity, level of abstraction, and design applicability. Box-counting dimension and lacunarity were calculated to compare morphological complexity between source images and generated patterns. The cases show that hydrological, tectonic, desert, agricultural, and reef morphologies can be translated into design-oriented pattern prototypes for paving, façades, interfaces, acoustic elements, and biomimetic surfaces. The contribution of this work lies mainly in design methodology: it provides a documented workflow for connecting Earth observation data, generative AI, and design ideation, while retaining clear boundaries around model reproducibility, prompt sensitivity, case representativeness, and perceptual evaluation.