Friday, November 14, 2014

Remote Sensing and Photo Interpretation Student Spotlight!!

GIS4035 Photo Interpretation and Remote Sensing, Dr. Brian Fulfrost

Supervised Image Classification

Lab description -  Students utilized unsupervised classification methods to derive Land Use Land Cover off of a satellite image. This week,the students were assigned to utilize supervised classifications  to derive Land Use Land Cover (LULC) classification off of the spectral information contained in the Digital Numbers (DN) stored in remotely sensed imagery. Supervised classification differs from unsupervised methods in its uses of "training sites" (based on a priori knowledge often from ground observations of the information classes being mapped) to guide the classification of the image from spectral values into information (e.g. LULC) classes. It also differs from unsupervised classification in its use of statistics (as opposed to Euclidean spectral distance) to assign pixel values to information classes.

Student Learning Outcomes:

  • Create spectral signatures and AOI feature
  • Produce classified images from satellite data
  • Recognize and eliminate spectral confusion between spectral signatures


The following student was chosen for their exceptional work on the Supervised Image Classification Lab assignment:

Gail Sease 

About Gail: Gail lives in Bakersfield, CA has earned BS and MS degrees in geology but has not worked as a geologist for a long time.   Her occupations over the last 20 years have included oil company geologist, junior college geology instructor, Spanish student, teacher of middle school and high school Spanish, biology and geology, school librarian and school secretary.  Before moving to Bakersfield in 2011, she lived with her family in Bogotá, Colombia and Tripoli, Libya for 8 years.  Gail would like to get back into the oil and gas or minerals industries and is seeking to bring her skills up to date.  GIS expertise is extremely valuable in these and many other fields.  Her sister is currently working on her internship at UWF's GIS Master's certification program and her experiences have convinced Gail that it will be an excellent opportunity.

What we like: Gail has been a hard working engaged student all semester and her work on the labs demonstrates her commitment to learning the concepts and techniques of remote sensing. We like that Gail explained the process of identifying training sites, how they relate to the spectral values, and the process for finding the signatures and spectral bands that have the least spectral confusion and therefore the highest potential of separability for each LULC class. Gail also identified one of the more effective band combos and her description of the spectral distance file assisted with the readers interpretation of her results. which she visually presented in her map. Way to go, Gail!

Thursday, November 6, 2014

Special Topics in GIS Student Spotlight!!

GIS4930 Special Topics in GIS, Instructor Amber Bloechle

Module 3 - Statistical Analysis of Methamphetamine Laboratory Busts in West Virginia, USA with ArcGIS Analyze Week

Lab description - In this project we performed an Ordinary Least Squares (OLS) regression analysis to try and determine if any socio-economic variables affect the location of meth labs using the OLS tool and ESRI's 6 step method. Deliverables this week included the Methods section of our report as well as the final OLS results table and a map showing StdResidual results from final OLS model.

Student Learning Outcomes:

  • Review regression analysis basics, ordinary least squares and geographic weighted regression.
  • Define dependent and independent variables for regression analysis.
  • Run ordinary least squares model. 
  • Complete 6 checks for OLS results to determine which variables are significant/non-significant.

The following student was chosen for their exceptional work on the Statistical Analysis of Methamphetamine Laboratory Busts in West Virginia, USA with ArcGIS Analyze Week assignment:

Brian Roche 

About Brian: Brian hails from St. Louis, Missouri and is currently serving in the US Army.  Already looking ahead to being a civilian again, Brian is taking on the GIS certificate to increase his skillset, and hopefully land a job with the US government!   Outside of GIS, he enjoys a number of hobbies including:  golf, baking, reading history, playing the violin, and travel.  Welcome to the spotlight Brian!

What we like: Brian gave a through, yet summarized report on his analysis methods, incorporating the use of ESRI's 6 step methodology in a concise manner. His map successfully displayed the results of his OLS model and to top things off he clearly went above and beyond to ensure his audiences understanding of the material by including a text box explaining the meaning behind standard residual values.  Fantastic job this week, Brian! Keep up the good work!