Geographic Information Sciences Commons^™

Poverty Mapping Using Convolutional Neural Networks Trained On High And Medium Resolution Satellite Images, With An Application In Mexico, Boris Babenko, Jonathan Hersh, David Newhouse, Anusha Ramakrishnan, Tom Swartz

Economics Faculty Articles and Research

Mapping the spatial distribution of poverty in developing countries remains an important and costly challenge. These “poverty maps” are key inputs for poverty targeting, public goods provision, political accountability, and impact evaluation, that are all the more important given the geographic dispersion of the remaining bottom billion severely poor individuals. In this paper we train Convolutional Neural Networks (CNNs) to estimate poverty directly from high and medium resolution satellite images. We use both Planet and Digital Globe imagery with spatial resolutions of 3-5 m2 and 50 cm2 respectively, covering all 2 million km2 of Mexico. Benchmark poverty estimates come from …

A Summer At Azavea Working With Nonprofit Organizations: The Summer Of Maps Fellowship, Sarah Gates

Sustainability and Social Justice

This report details my experience as a Summer of Maps Fellow at Azavea during June 2017 to August 2017. As a Summer of Maps Fellow I worked with nonprofit organizations, the Fair Tech Collective and the World Resources Institute, on two geospatial analysis projects. For the Fair Tech Collective I analyzed data on refinery flaring pollution, air toxin concentrations, and sensitive receptor populations to produce a series of maps and infographics detailing the impacts of petrochemical pollution in the San Francisco Bay Area. For the World Resources Institute I used data-driven methods to analyze conservation efforts in the Central African …

Greening The Gateway Cities: Summer Internship With The Clark University Human Environment Regional Observatory (Hero) And Massachusetts Department Of Conservation And Recreation (Dcr), Zhiwen Zhu

Sustainability and Social Justice

This report provides a detailed account of my internship experience with the Clark University Human-Environment Regional Observatory (HERO) and Massachusetts Department of Conservation and Recreation (DCR) in the summer of 2017. This internship concerns the urban tree health assessment in three ‘Greening the Gateway’ cities in Massachusetts. During the internship, I conducted tree survey field work, database management, mapping, tree survey data analysis and urban tree plantation benefits microclimate simulation. During the internship I worked with the professors and students at Clark University and University of Massachusetts, Amherst, and the staff from Department of Conservation and Recreation (DCR), Worcester Tree …

Spatial Analysis Of Ethnic And Racial Segregation In The Chicago Metropolitan Area, 2000–2014, Roy Yao

Department of Geography: Dissertations, Theses, and Student Research

Racial segregation has long been a great concern in the United States. Scholars study and measure racial segregation over different time periods to trace the changing patterns of racial segregation. Chicago, as the nation’s third largest city, also ranked on top of the most segregated cities. Previous studies measured racial segregation in Chicago only numerically; few studies have used geospatial statistic methods to identify racial segregation patterns in the Chicago metropolitan area. This study uses “Hotspot Analysis” (Getis Ord Gi*) to identify Chicago’s most recent segregation patterns among four major ethnic and racial groups: White, African American, Hispanic and Asian. …

Moving Mountains : A Study Examining Long-Term Impacts Of Mountaintop Removal Coal Mining On Mortality In The Appalachian Region Using Geographic Information Sciences Techniques., James Howard Kent Pugh

Electronic Theses and Dissertations

Over the last hundred years, the Appalachian region has been dominated by the coal industry. It has also been and currently is one of the unhealthiest regions in the United States. Recent scholarship has examined the relationship between coal mining and health and mortality rates in the Appalachian region. The first study incorporates air quality and pollution data to examine if coal mining counties have higher levels of pollution and if this pollution contributes to mortality disadvantage. In the second study, I construct a population-based coal-exposure measure to better evaluate the relationship between coal mining and health I find that …

Semi-Automated Surface Water Detection With Synthetic Aperture Radar Data: A Wetland Case Study, Amir Behnamian, Sarah Banks, Lori White, Brian Brisco, Koreen Millard, Jon Pasher, Zhaohua Chen, Jason Duffe, Laura Bourgeau-Chavez, Michael Battaglia

Michigan Tech Publications, Part 1

In this study, a new method is proposed for semi-automated surface water detection using synthetic aperture radar data via a combination of radiometric thresholding and image segmentation based on the simple linear iterative clustering superpixel algorithm. Consistent intensity thresholds are selected by assessing the statistical distribution of backscatter values applied to the mean of each superpixel. Higher-order texture measures, such as variance, are used to improve accuracy by removing false positives via an additional thresholding process used to identify the boundaries of water bodies. Results applied to quad-polarized RADARSAT-2 data show that the threshold value for the variance texture measure …

A Spatial Collaboration: Building A Multi-Institution Geospatial Data Discovery Portal, Mara Blake, Karen Majewicz, Ryan Mattke, Kathleen W. Weessies

Collaborative Librarianship

As academic education and research increasingly take advantage of geospatial data and methodologies, we see a corresponding exponential growth in the number of available geospatial resources in the form of GIS datasets and scanned historical maps. However, users can experience difficulty finding these resources due to the unconnected multitude of platforms and clearinghouses that host them. Additionally, the resources are not always well described with web semantic metadata that facilitates discovery. In response to this challenge, The Big Ten Academic Alliance Geospatial Data Project began in 2015 to provide discoverability, facilitate access, and connect scholars to geospatial resources. Our project …

Geospatial Tools And Data Provided By Itap/Research Computing, Larry Biehl

Purdue GIS Day

The presentation will provide the audience information about the geospatial applications that are available on campus including Esri ArcGIS, ERDAS Imagine, Exelis ENVI, Trimble eCognition and others. The information will include where to go to download the software installers and how to set up the licensing for them. The discussion will also go over the new software installer file download process.

Archaeological Investigation Of An Iron Age Fortress On Dana Island, Turkey, Nathan C. Mcburnett

Purdue GIS Day

In this project, the Bogsak Archaeological survey team investigated a fortress on the northern crest of the mountain on Dana Island, located just off the coast of Turkey in the Rough Cilician Region. Although the interior remains of the fortress, consisting of a large number of ceramics and architectural features such as a basilica, were dated to the Late Roman Era, we found that the fortress itself actually predates this. Based on ceramic remains being used as aggregate in the fortress wall, the team was able to date the fortress itself to the Iron Age (Classical Era). GIS software was …

Using Gis To Determine Locations For Safety Improvements, Mario Romero, Etienne Tino Atisso, Taojun Wang, Laura Slusher, Andrew Tarko

Purdue GIS Day

Crash location is a critical piece of information for any type of safety-related analysis; however, there is often a high percentage of error in crash latitude and longitude coordinates. Currently, a time-consuming, manual process is used in Indiana to correct faulty crash location coordinates. The Crash Location Improvement Program (CLIP) is a tool developed by the Purdue University Center for Road Safety, with support from Indiana LTAP, which allows users to quickly and easily identify and correct crash coordinates, allowing for a more accurate safety analysis. After correcting the coordinates, crash location maps, heat maps, and other visualization tools are …

Spatiotemporal Computing For Enabling Scientific Research And Engineering Development: A Gis Practice, Chaowei Yang

Purdue GIS Day

No abstract provided.

Using Space Based Earth Observations To Understand Our Changing Planet, Kumar C. Navulur

Purdue GIS Day

"Satellite remote sensing has come a long way in the last 2 decades to map and monitor our changing planet. Technology trends include increasing spatial resolution (pixel size), number of spectral bands that can be leveraged to extract information, and frequency of revisit globally. Satellite industry has be improving the location accuracy from space to enable various precision applications on the earth. Advances in cloud computing and other technologies now allow for creation of mosaics and information layers at scale. The latest trend is analytics that allows for predictive intelligence.

The author will discuss practical application of satellite imagery for …

Spatial Analysis Of Landfills In Respect To Flood Events And Sea-Level Rise Using Arcgis Pro, Benjamin S. Taylor, Songlin Fei

Purdue GIS Day

"Recently in the news, media coverage of flood events has garnered attention due to tropical storms like Hurricane Harvey and the costly damages that resulted. Under climate change, events like sea-level rise (SLR) and flooding are projected to increase which threaten infrastructure, making it necessary for proper planning before, during, and after installation of landfills to mitigate risk. Studies in Austria and the UK have revealed that many landfills are located in flood zones in addition to coastal areas affected by coastal erosion. In the United States, there have been minimal analysis’ on landfill locations related to flood events and …

Geodata Science Education At Purdue, Wen-Wen Tung

Purdue GIS Day

This presentation introduces a group of Purdue faculty’s effort to create a set of geodata science graduate-level education programs.

Earthquake-Induced Collapsed Building Detection With Vhr Synthetic Aperture Radar Images, Fan Wu, Jie Shan, Chao Wang

Purdue GIS Day

"Compared with optical sensors, Synthetic Aperture Radar (SAR) can provide important damage information due to its ability to map areas affected by earthquakes independently from weather conditions and solar illumination. In 2013, a new TerraSAR-X mode named staring spotlight (ST), whose azimuth resolution was improved to 0.24 m, was introduced for various applications. This very high resolution (VHR) data source made it possible to extract detailed information from individual buildings.

We present a new concept for individual building damage assessment using a post-event sub-meter VHR SAR image and a building footprint map. With the building footprint map, the original footprints …

What Is Exciting At The Libraries? – Gis Resources At Libraries, Nicole Kong

Purdue GIS Day

This presentation introduce the new GIS resources offered from Purdue University Libraries. These new support areas include the D-VELoP GIS computing lab, new Esri Development Center (EDC), GIS data portal, GIS data server, Insights for ArcGIS, and GIS VR technology.

Towards New Weather And Climate Baselines For Assessing Weather And Climate Extremes, Impacts, And Risks, Fiona Williamson, Rob Allan, Roseanne D'Arrigo

Research Collection College of Integrative Studies

Initiatives to recover (sourcing, imaging, digitizing) historic datasets for generating more accurate longterm climate models have only gained momentum over the last decade, despite a long precedent of compelling arguments as to the value of historic weather observations (Le Roy Ladurie, 1972; Lamb, 1977). Although such work is relatively well established in Europe, the United States, China, and Japan; Southeast Asia currently has a dearth of data rescue initiatives with a long historical focus. The reasons behind this include a perception of the paucity of surviving data; the scattered nature of data due to shifts between colonial rule and independence …

Modeling Check-In Behavior With Geographical Neighborhood Influence Of Venues, Thanh Nam Doan, Ee Peng Lim

Research Collection School Of Computing and Information Systems

With many users adopting location-based social networks (LBSNs) to share their daily activities, LBSNs become a gold mine for researchers to study human check-in behavior. Modeling such behavior can benefit many useful applications such as urban planning and location-aware recommender systems. Unlike previous studies [4,6,12,17] that focus on the effect of distance on users checking in venues, we consider two venue-specific effects of geographical neighborhood influence, namely, spatial homophily and neighborhood competition. The former refers to the fact that venues share more common features with their spatial neighbors, while the latter captures the rivalry of a venue and its nearby …

Gis Analysis Of Dvāravatī Dharmacakras And The Rise Of Buddhism In Thailand, Areerut Patnukao

LSU Doctoral Dissertations

This dissertation explores how GIS as well as spatial and statistical analyses could be used to advance the understanding of Dvāravatī settlement and Dharmacakras locations. The research employs archaeological and geographical parameters to measure and quantify the patterns of Dvāravatī settlements, Dharmacakra locations, their interrelationship, and their relationship with environmental setting. The different types of spatial analyses, parameter settings within each analysis, and approaches are used to examine and explore the differences and commonalities of these variables at three different geographic levels: national, regional, and river basin levels.

Four distinct approaches are incorporated in this study. Chi-Square analysis shows significant …

Forming Community Partnerships, Lori Foley

CHAR

In the event of a disaster, regardless of the type or scope, the first response is always local. For the institutions and organizations charged with safeguarding the nation’s cultural and historic resources – museums, historical societies, libraries, and municipal offices, to name just a few – building relationships with local first responders and emergency managers before disaster strikes is key to ensuring the safety of staff and collections. State emergency management agencies are also collaborating with their state cultural agencies to protect these valuable and vulnerable resources. The resulting emergency networks better position the local community and the state to …