 The study reviewed 112 studies on fusing optical and radar data for land cover and use assessments, finding that fusion improved results compared to using single data sources in a large majority 28 studies of cases. However, the study notes that pre-classification fusion followed by pixel level inputs in traditional classification algorithms was common without a clear rationale on its applicability to specific land use themes being studied. The field requires further development of robust techniques for mapping land uses and changes and systematic procedures to assess the benefits of fusion over larger spatial scales. This article was authored by Neha Joshi, Mathias Bauman, Andrea A. Hammer, and others.