Atmospheric correction and image classification on MODIS images by nonparametric regression splines

Kuter, Semih
In this study, two novel applications of nonparametric regression splines are introduced within the frame of remote sensing: (i) For the first time ever, atmospheric correction models are generated for moderate resolution imaging spectroradiometer (MODIS) images by using multivariate adaptive regression splines (MARS), and its recently introduced version, conic multivariate adaptive regression splines (CMARS). The obtained models are applied on the predefined test areas of twenty four different MODIS scenes. Simplified model for atmospheric correction (SMAC) algorithm, a radiative transfer-based approach, is also employed on the same test data. The performance of the MARS, CMARS and SMAC models are assessed against MODIS surface reflectance products. (ii) Additionally, implementation of MARS algorithm in image classification for snow mapping on MODIS images is demonstrated within a well-elaborated framework. The relation between the variations in MARS model building parameters and their effect on the predictive performance are presented in various perspectives. Performance of MARS in classification is compared with the traditional maximum-likelihood method. For the atmospheric correction, results reveal that MARS and CMARS approaches over perform SMAC method on all test areas. In classification, significant improvement in the classification accuracy of MARS models is observed as the number of basis functions and the degree of interaction increase. On three image sets out of four, the MARS approach gives better classification accuracies when compared to maximum-likelihood method.


Development of free/libre and open source spatial data analysis system fully coupled with geographic information system
Kepoğlu, Volkan Osman; Düzgün, H. Şebnem; Department of Geodetic and Geographical Information Technologies (2011)
Spatial Data Analysis (SDA) is relatively narrower and constitutes one of the areas of Spatial Analysis. Geographic Information System (GIS) offers a potentially valuable platform for supporting SDA techniques. Integration of SDA with GIS helps SDA to benefit from the data input, storage, retrieval, data manipulation and display capabilities of GIS. Also, GIS can benefit from SDA techniques in which the integration of these techniques can increase the analysis capabilities of GIS. This integration serves fo...
Statistical downscaling of monthly reservoir inflows for Kemer watershed in Turkey: use of machine learning methods, multiple GCMs and emission scenarios
OKKAN, UMUT; İnan, Gül (Wiley, 2015-09-01)
In this study, statistical downscaling of general circulation model (GCM) simulations to monthly inflows of Kemer Dam in Turkey under A1B, A2, and B1 emission scenarios has been performed using machine learning methods, multi-model ensemble and bias correction approaches. Principal component analysis (PCA) has been used to reduce the dimension of potential predictors of National Centers for Environmental Prediction and National Center for Atmospheric Research (NCEP/NCAR) reanalysis data. Then, the reasonabl...
Investigation of housing valuation models based on spatial and non-spatial techniques
Boza, Ertuğrul; Düzgün, H. Şebnem; Türel, Ali; Department of Geodetic and Geographical Information Technologies (2015)
The aim of this thesis is to develop hedonic housing valuation models based on spatial (SAR-simultaneous spatial autoregression and GWR - geographically weighted regression) and non-spatial (OLS - ordinary least squares) techniques, to compare the performances of these models and to investigate significant factors affecting housing value. The developed housing valuation models were tested at the Çankaya and Keçiören districts of Ankara province, Turkey. The results of the analyses revealed that significant ...
Hybrid statistical and machine learning modeling of cognitive neuroscience data
Çakar, Serenay; Gökalp Yavuz, Fulya (2023-01-01)
The nested data structure is prevalent for cognitive measure experiments due to repeatedly taken observations from different brain locations within subjects. The analysis methods used for this data type should consider the dependency structure among the repeated measurements. However, the dependency assumption is mainly ignored in the cognitive neuroscience data analysis literature. We consider both statistical, and machine learning methods extended to repeated data analysis and compare distinct algorithms ...
3D Object Modeling by Structured Light and Stereo Vision
Ozenc, Ugur; Tastan, Oguzhan; GÜLLÜ, MEHMET KEMAL (2015-05-19)
In this paper, we demonstrate a 3D object modeling system utilizing a setup which consists of two CMOS cameras and a DLP projector by making use of structured light and stereo vision. The calibration of the system is carried out using calibration pattern. The images are taken with stereo camera pair by projecting structured light onto the object and the correspondence problem is solved by both epipolar constraint of stereo vision and gray code constraint of structured light. The first experimental results s...
Citation Formats
S. Kuter, “Atmospheric correction and image classification on MODIS images by nonparametric regression splines,” Ph.D. - Doctoral Program, Middle East Technical University, 2014.