Search Content

Matching Items (3)

Filtering by

All Subjects: Land use
Creators: Barnes, Elizabeth
Creators: Amresh, Ashish

Land use and land cover classification using deep learning techniques

Description

Large datasets of sub-meter aerial imagery represented as orthophoto mosaics are widely available today, and these data sets may hold a great deal of untapped information. This imagery has a potential to locate several types of features; for example, forests, parking lots, airports, residential areas, or freeways in the imagery. However, the appearances of these things vary based on many things including the time that the image is captured, the sensor settings, processing done to rectify the image, and the geographical and cultural context of the region captured by the image. This thesis explores the use of deep convolutional neural networks to classify land use from very high spatial resolution (VHR), orthorectified, visible band multispectral imagery. Recent technological and commercial applications have driven the collection a massive amount of VHR images in the visible red, green, blue (RGB) spectral bands, this work explores the potential for deep learning algorithms to exploit this imagery for automatic land use/ land cover (LULC) classification. The benefits of automatic visible band VHR LULC classifications may include applications such as automatic change detection or mapping. Recent work has shown the potential of Deep Learning approaches for land use classification; however, this thesis improves on the state-of-the-art by applying additional dataset augmenting approaches that are well suited for geospatial data. Furthermore, the generalizability of the classifiers is tested by extensively evaluating the classifiers on unseen datasets and we present the accuracy levels of the classifier in order to show that the results actually generalize beyond the small benchmarks used in training. Deep networks have many parameters, and therefore they are often built with very large sets of labeled data. Suitably large datasets for LULC are not easy to come by, but techniques such as refinement learning allow networks trained for one task to be retrained to perform another recognition task. Contributions of this thesis include demonstrating that deep networks trained for image recognition in one task (ImageNet) can be efficiently transferred to remote sensing applications and perform as well or better than manually crafted classifiers without requiring massive training data sets. This is demonstrated on the UC Merced dataset, where 96% mean accuracy is achieved using a CNN (Convolutional Neural Network) and 5-fold cross validation. These results are further tested on unrelated VHR images at the same resolution as the training set.

ContributorsUba, Nagesh Kumar (Author) / Femiani, John (Thesis advisor) / Razdan, Anshuman (Committee member) / Amresh, Ashish (Committee member) / Arizona State University (Publisher)

Created2016

The Water, Energy, & Infrastructure Co-Benefits of Smart Growth Planning in Phoenix

Description

Phoenix is the sixth most populated city in the United States and the 12th largest metropolitan area by population, with about 4.4 million people. As the region continues to grow, the demand for housing and jobs within the metropolitan area is projected to rise under uncertain climate conditions.

Undergraduate and graduate students from Engineering, Sustainability, and Urban Planning in ASU’s Urban Infrastructure Anatomy and Sustainable Development course evaluated the water, energy, and infrastructure changes that result from smart growth in Phoenix, Arizona. The Maricopa Association of Government's Sustainable Transportation and Land Use Integration Study identified a market for 485,000 residential dwelling units in the urban core. Household water and energy use changes, changes in infrastructure needs, and financial and economic savings are assessed along with associated energy use and greenhouse gas emissions.

The course project has produced data on sustainable development in Phoenix and the findings will be made available through ASU’s Urban Sustainability Lab.

ContributorsNahlik, Matthew (Author) / Chester, Mikhail Vin (Author) / Andrade, Luis (Author) / Archer, Melissa (Author) / Barnes, Elizabeth (Author) / Beguelin, Maria (Author) / Bonilla, Luis (Author) / Bubenheim, Stephanie (Author) / Burillo, Daniel (Author) / Cano, Alex (Author) / Guiley, Keith (Author) / Hamad, Moayyad (Author) / Heck, John (Author) / Helble, Parker (Author) / Hsu, Will (Author) / Jensen, Tate (Author) / Kannappan, Babu (Author) / Kirtley, Kelley (Author) / LaGrou, Nick (Author) / Loeber, Jessica (Author) / Mann, Chelsea (Author) / Monk, Shawn (Author) / Paniagua, Jaime (Author) / Prasad, Saransh (Author) / Stafford, Nicholas (Author) / Unger, Scott (Author) / Volo, Tom (Author) / Watson, Mathew (Author) / Woodruff, Abbie (Author) / Arizona State University. School of Sustainable Engineering and the Built Environment (Contributor) / Arizona State University. Center for Earth Systems Engineering and Management (Contributor)

California High Speed Resilience to Climate Change

Description

This LCA used data from a previous LCA done by Chester and Horvath (2012) on the proposed California High Speed Rail, and furthered the LCA to look into potential changes that can be made to the proposed CAHSR to be more resilient to climate change. This LCA focused on the energy, cost, and GHG emissions associated with raising the track, adding fly ash to the concrete mixture in place of a percentage of cement, and running the HSR on solar electricity rather than the current electricity mix. Data was collected from a variety of sources including other LCAs, research studies, feasibility studies, and project information from companies, agencies, and researchers in order to determine what the cost, energy requirements, and associated GHG emissions would be for each of these changes. This data was then used to calculate results of cost, energy, and GHG emissions for the three different changes. The results show that the greatest source of cost is the raised track (Design/Construction Phase), and the greatest source of GHG emissions is the concrete (also Design/Construction Phase).

ContributorsBarnes, Elizabeth (Author) / Arizona State University. School of Sustainable Engineering and the Built Environment (Contributor) / Arizona State University. Center for Earth Systems Engineering and Management (Contributor)

Created2014-06-13