The Mississippi Alluvial Valley is a floodplain along the southern extent of the Mississippi River extending from southern Missouri to the Gulf of Mexico. This area once encompassed nearly 10 million ha of floodplain forests, most of which has been converted to agriculture over the past two centuries. Conservation programs in this region revolve around protection of existing forest and reforestation of converted lands. Therefore, an accurate and up to date classification of forest cover is essential for conservation planning, including efforts that prioritize areas for conservation activities. We used object-based image analysis with Random Forest classification to quickly and accurately classify forest cover. We used Landsat band, band ratio, and band index statistics to identify and define similar objects as our training sets instead of selecting individual training points. This provided a single rule-set that was used to classify each of the 11 Landsat 5 Thematic Mapper scenes that encompassed the Mississippi Alluvial Valley. We classified 3,307,910±85,344ha (32% of this region) as forest. Our overall classification accuracy was 96.9% with Kappa statistic of 0.96. Because this method of forest classification is rapid and accurate, assessment of forest cover can be regularly updated and progress toward forest habitat goals identified in conservation plans can be periodically evaluated.

First posted July 23, 2015 For additional information, contact: Director, National Wetlands Research Center U.S. Geological Survey700 Cajundome Blvd.Lafayette, LA 70506 http://www.nwrc.usgs.gov/ Coastal zone managers and researchers often require detailed information regarding emergent marsh vegetation types (that is, fresh, intermediate, brackish, and saline) for modeling habitat capacities and needs of marsh dependent taxa (such as waterfowl and alligator). Detailed information on the extent and distribution of emergent marsh vegetation types throughout the northern Gulf of Mexico coast has been historically unavailable. In response, the U.S. Geological Survey, in collaboration with the Gulf Coast Joint Venture, the University of Louisiana at Lafayette, Ducks Unlimited, Inc., and the Texas A&M University-Kingsville, produced a classification of emergent marsh vegetation types from Corpus Christi Bay, Texas, to Perdido Bay, Alabama. This study incorporates about 9,800 ground reference locations collected via helicopter surveys in coastal wetland areas. Decision-tree analyses were used to classify emergent marsh vegetation types by using ground reference data from helicopter vegetation surveys and independent variables such as multitemporal satellite-based multispectral imagery from 2009 to 2011, bare-earth digital elevation models based on airborne light detection and ranging (lidar), alternative contemporary land cover classifications, and other spatially explicit variables. Image objects were created from 2010 National Agriculture Imagery Program color-infrared aerial photography. The final classification is a 10-meter raster dataset that was produced by using a majority filter to classify image objects according to the marsh vegetation type covering the majority of each image object. The classification is dated 2010 because the year is both the midpoint of the classified multitemporal satellite-based imagery (2009–11) and the date of the high-resolution airborne imagery that was used to develop image objects. The seamless classification produced through this work can be used to help develop and refine conservation efforts for priority natural resources.

Tidally influenced wetlands along the Texas coast provide important habitat for wintering waterfowl and myriad other fish and wildlife species. Because habitat values may differ among marsh salinity zones (e.g., waterfowl food resources and use are greatest in fresh and intermediate marsh), the spatial distribution of marsh types is important for understanding the capacity of coastal landscapes to support waterfowl and other wildlife populations and informing coastal restoration priorities. Additionally, documenting spatial patterns of coastal marsh types is necessary for projecting future landscape change and examining impacts of environmental processes (e.g., tropical storms, sea level rise). We used a helicopter-based vegetation survey and remotely sensed imagery to delineate marsh types along the central Texas coast into four categories: fresh, intermediate, brackish, and saline. We recorded vegetation composition at 342 sample points and combined these data with Landsat Thematic Mapper imagery to perform a supervised classification of marsh types throughout our 122,995 ha survey area. Our initial coarse classification delineating coastal marsh from other habitat types was 92 % accurate. Intermediate, brackish, and saline marsh each comprised about 30 % of the coastal marsh in our study area. Freshwater marsh comprised < 1 % and may have been underrepresented within the coastal zone due to placement of the inland boundary of our study area. Our final classification of marsh types was 77.2 % accurate which will provide a framework for further delineation efforts. We offer several considerations for future coastal marsh delineation efforts along the Texas coast.