Green Innovation Adoption and Regional Landscape Sustainability: A County-Level Assessment Using Open Multi-Source Geospatial Data

How the diffusion of green innovation technologies translates into regional landscape sustainability is still poorly resolved, in part because most studies rely on a single data source that cannot separate an adoption signal from confounding climatic and terrain influences. To make progress on this identification problem, an empirical framework is assembled that fuses openly licensed observations, Landsat and Sentinel-2 imagery, OpenStreetMap layers, NPP-VIIRS nighttime lights, and public statistical yearbooks, and embeds them in a spatial econometric design, so that the adoption–pattern–service–sustainability chain can be traced across 72 county-level units spanning Ningxia, eastern Gansu, and northern Shaanxi over 2013–2022. Pixel- and object-level integration, entropy weighting, and principal component reduction jointly deliver a fused representation whose coefficient of determination against held-out reference data exceeds 0.85 while the reconstruction error falls by roughly a third relative to single-source baselines. A spatial Durbin specification then decomposes adoption’s association with sustainability into a dominant direct component and a smaller, distance-bounded spillover, and roughly one-quarter of the total travels through landscape reconfiguration; the result survives the placebo, subsample, and variable-substitution checks, and is strongly conditioned by the terrain and local economic capacity. These findings favour a spatially coordinated, capacity-targeted transition policy rather than uniform deployment. Two caveats should be read alongside them: adoption is measured through proxies whose validity, though corroborated against county-level green-patent and installed-capacity records, is not perfect, and external validation across contrasting landscapes remains outstanding.