In relation to the Deepwater Horizon (DWH) oil spill, the DWH Natural Resource Damage Assessment Trustees prioritized intentional investments with the capacity to inform future avian restoration and adaptive management activities. For more than a decade, aerial photographic nest surveys and dotting (i.e., counting) analyses have been implemented across the northern Gulf coast. Collectively, this information is maintained within the Avian Data Monitoring Portal (avianmonitoring.com). The approaches, however, are time-consuming and labor intensive to collect and analyze. This talk will focus on novel efforts to extend these datasets using remote sensing and machine learning (ML). We will discuss the utility of ML tools for bird detection including the detection of multiple species of birds and nests. We will also discuss novel ways of using aerial and satellite imagery for habitat classification to make predictive maps of bird nesting areas. Using Queen Bess Island, LA, as a case study, we will analyze time series of remote sensing imagery and the use of ML tools to better understand habitat changes following island restoration and gain deeper insight into bird-habitat relationships. The results of this work can be used to inform future restoration planning efforts and help facilitate the design of effective and more efficient monitoring surveys.