Metrics
11 Record Views
Thesis
Land Use/Cover Change Detection And Modeling Using A Multi-Layer Perception Neural Network Deep Learning Model For Orlando, Florida Metropolitan Area
University of West Florida Libraries
Master of Science (MS), University of West Florida
2025
Abstract
This study utilizes multi-temporal datasets derived from remotely sensed imagery to assess changes in land use/cover (LULC) and to forecast future trends, with a particular emphasis on urban growth in the Orlando, Florida Metropolitan Statistical Area (MSA). The modeling employed the LCM within the TerrSet remote sensing and GIS software platform. The methodology consists of three main components: (1) analyzing and mapping historical LULC changes; (2) identifying the topographical and socio-economic variables influencing these changes; and (3) simulating potential land use and cover scenarios. A model was calibrated using the multilayer perceptron (MLP) neural network algorithm in conjunction with publicly available spatial datasets. Alongside model calibration, future projections of LULC changes were mapped through the year 2031. The data reveals that urban land experienced a growth of 19.76% from 2001 to 2021, and it is projected to rise by an additional 7.88% by 2031. The model exhibited impressive performance, attaining an overall accuracy of 0.88, a kappa coefficient of 0.84, and a Relative Operating Characteristic (ROC) value of 0.83.
The findings reveal notable transformations in the metropolitan area over the past two decades and predict continued urban growth into both natural and semi-natural regions of the city. Identifying spatial and temporal patterns of LULCC along with their drivers enables policymakers to make decisions about future land use and development. Consequently, it supports sustainable urban growth and the conservation of natural resources.
Details
- Title
- Land Use/Cover Change Detection And Modeling Using A Multi-Layer Perception Neural Network Deep Learning Model For Orlando, Florida Metropolitan Area
- Resource Type
- Thesis
- Contributors
- Zhiyong Hu (Committee Chair)Jason Ortegren (Committee Member)Lakshmi Prayaga (Committee Member)
- Publisher
- University of West Florida Libraries
- Format
- pdf
- Number of pages
- 92
- Copyright
- Permission granted to the University of West Florida Libraries by the author to digitize and/or display this information for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires the permission of the copyright holder.
- Identifiers
- 99381469353806600
- Academic Unit
- Earth and Environmental Sciences
- Language
- English
- Awarding Institution
- University of West Florida; Master of Science (MS)
- Theses and Dissertations
- Master of Science (MS), University of West Florida