Inicio  /  Water  /  Vol: 10 Par: 11 (2018)  /  Artículo
ARTÍCULO
TITULO

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

Sudhanshu Panda    
Devendra M. Amatya    
Rhett Jackson    
Ge Sun and Asko Noormets    

Resumen

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.

 Artículos similares

       
 
Radek Barvir, Alena Vondrakova and Jan Brus    
Despite the growing efficiency of the map-design process in general, tactile mapping has remained peripheral to mainstream cartography. For a specific group of people with visual impairment, however, tactile maps are the only effective way to obtain a co... ver más

 
James Flynn and Cinzia Giannetti    
With Electric Vehicles (EV) emerging as the dominant form of green transport in the UK, it is critical that we better understand existing infrastructures in place to support the uptake of these vehicles. In this multi-disciplinary paper, we demonstrate a... ver más
Revista: AI

 
Thomas Albrecht, Ignacio González-Álvarez and Jens Klump    
Landscapes evolve due to climatic conditions, tectonic activity, geological features, biological activity, and sedimentary dynamics. Geological processes at depth ultimately control and are linked to the resulting surface features. Large regions in Austr... ver más

 
Yoganand Korgaonkar, David Phillip Guertin, Thomas Meixner and David C Goodrich    
Green Infrastructure (GI) practices are being implemented in numerous cities to tackle stormwater management issues and achieve co-benefits such as mitigating heat island effects and air pollution, as well as water augmentation, health, and economic bene... ver más

 
Martina E. Deininger, Maximilian von der Grün, Raul Piepereit, Sven Schneider, Thunyathep Santhanavanich, Volker Coors and Ursula Voß    
The concept and implementation of Smart Cities is an important approach to improve decision making as well as quality of life of the growing urban population. An essential part of this is the presentation of data from different sources within a digital c... ver más