1Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN-47906, USA
2Environment and Conservation Science Program, North Dakota State University, P. O. Box 6050, Fargo, ND-58108, USA
3Department of Geosciences, North Dakota State University, P. O. Box 6050, Fargo, ND-58108, USA
4North Dakota Forest Service, 307 – 1st Street East, Bottineau, ND-58310, USA
Satellite imagery provides an effective platform to detect land-use and land-cover changes over a period of time. The changing land-use patterns over the years are an indicator to prioritize vulnerable areas to conversion processes within the Pipestem Creek Watershed of North Dakota, USA. The study demonstrates the applicability of remote sensing science in change detection. Landsat Thematic Mapper images acquired from the years 1976, 1991, 2000, 2005 and 2011 were used to quantify temporal changes from 1976 to 2011 by image classification techniques. Data analysis and classification were done using the remote sensing software ENVI® 4.5. Post classification confusion matrices were generated to obtain accuracy assessment. The results quantify the land-cover change patterns in the watershed and demonstrate the potential of Landsat data in providing an accurate and cost effective way to analyze land-cover changes over time. This data can be utilized as essential inputs in land management and policy making.
Change detection, land-use/cover, supervised classification, Pipestem Creek
