Next Article in Journal
Assessing the Use of Satellite-Based Estimates and High-Resolution Precipitation Datasets for the Study of Extreme Precipitation Events over the Iberian Peninsula
Next Article in Special Issue
Barrier-based Longitudinal Connectivity Index for Managing Urban Rivers
Previous Article in Journal
Sensing the Submerged Landscape of Nisida Roman Harbour in the Gulf of Naples from Integrated Measurements on a USV
Previous Article in Special Issue
Detecting Snowfall Events over Mountainous Areas Using Optical Imagery
Article

Automated Geospatial Models of Varying Complexities for Pine Forest Evapotranspiration Estimation with Advanced Data Mining

1
Institute of Environmental Spatial Analysis, University of North Georgia, 3820 Mundy Mill Road, Oakwood, GA 30566, USA
2
Center for Forested Wetlands Research, USDA Forest Service, 3734 Highway 402, Cordesville, SC 29434, USA
3
Warnell School of Forestry, University of Georgia, Athens, GA 30606, USA
4
Eastern Forest Environmental Threat Assessment Center, USDA Forest Service, Raleigh, NC 27606, USA
5
Department of Forestry and Environmental Resources. North Carolina State University, Raleigh, NC 27606, USA
*
Author to whom correspondence should be addressed.
Water 2018, 10(11), 1687; https://doi.org/10.3390/w10111687
Received: 25 April 2018 / Revised: 31 August 2018 / Accepted: 12 September 2018 / Published: 19 November 2018
(This article belongs to the Special Issue Applications of Remote Sensing and GIS in Hydrology)
The study goal was to develop automated user-friendly remote-sensing based evapotranspiration (ET) estimation tools: (i) artificial neural network (ANN) based models, (ii) ArcGIS-based automated geospatial model, and (iii) executable software to predict pine forest daily ET flux on a pixel- or plot average-scale. Study site has had long-term eddy-flux towers for ET measurements since 2006. Cloud-free Landsat images of 2006−2014 were processed using advanced data mining to obtain Principal Component bands to correlate with ET data. The regression model’s r2 was 0.58. The backpropagation neural network (BPNN) and radial basis function network (RBFN) models provided a testing/validation average absolute error of 0.18 and 0.15 Wm−2 and average accuracy of 81% and 85%, respectively. ANN models though robust, require special ANN software and skill to operate; therefore, automated geospatial model (toolbox) was developed on ArcGIS ModelBuilder as user-friendly alternative. ET flux map developed with model tool provided consistent ET patterns for landuses. The software was developed for lay-users for ET estimation. View Full-Text
Keywords: evapotranspiration; modeling; Remote Sensing Landsat; pine forests; artificial neural networks; BPNN; RBFN; Modelbuilder; Visual Basics evapotranspiration; modeling; Remote Sensing Landsat; pine forests; artificial neural networks; BPNN; RBFN; Modelbuilder; Visual Basics
Show Figures

Figure 1

MDPI and ACS Style

Panda, S.; Amatya, D.M.; Jackson, R.; Sun, G.; Noormets, A. Automated Geospatial Models of Varying Complexities for Pine Forest Evapotranspiration Estimation with Advanced Data Mining. Water 2018, 10, 1687. https://doi.org/10.3390/w10111687

AMA Style

Panda S, Amatya DM, Jackson R, Sun G, Noormets A. Automated Geospatial Models of Varying Complexities for Pine Forest Evapotranspiration Estimation with Advanced Data Mining. Water. 2018; 10(11):1687. https://doi.org/10.3390/w10111687

Chicago/Turabian Style

Panda, Sudhanshu, Devendra M. Amatya, Rhett Jackson, Ge Sun, and Asko Noormets. 2018. "Automated Geospatial Models of Varying Complexities for Pine Forest Evapotranspiration Estimation with Advanced Data Mining" Water 10, no. 11: 1687. https://doi.org/10.3390/w10111687

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop