Investigating the effect of radar images in classifying land use classes in machine learning based algorithms
Journal Title: Human Ecology - Year 2023, Vol 2, Issue 2
Abstract
Acquiring knowledge about the types of land uses and the stages of their change provides basic and very important information to researchers and decision makers. One of the most common and useful methods in remote sensing is to access the maximum information contained in satellite data by combining radar and optical satellite images. In general, the main purpose of this study was to investigate the effect of the presence of SAR images in the classification of optical multi-temporal satellite images in machine learning-based classification algorithms, including random forest, Cart Decision Tree and Support Vector Machine. In the above paper, the Normalized Difference Vegetation Index (NDVI) dataset, along with slope layers, a digital elevation model and a corrected Sentinel-2 satellite image was supervised by the three methods mentioned. Once again, this was done with the presence of the Sentinel-1 satellite SAR image database. Finally, in the post-processing stage, the individual pixels were connected to neighboring classes. This was done by majority filtering. The final results were validated with ground data. The results showed that in the study of all classes, the overall accuracy and kappa coefficient in the presence of SAR dataset and for all three classification methods improved by only 3%, but in the one-to-one study of the classes, the producer accuracy of the random forest method in the dual agriculture class improved. It has been significant and its value has increased from 0.74 to 0.84. In the support vector machine method, dry farming and orchard classes have had a more significant improvement, which have increased from 0.75 and 0.78 to 0.84 and 0.92, respectively. Finally, it can be said that the addition of radar images to the classification has a positive and significant effect only in the mentioned classes, and also the obvious advantage of the random forest method compared to other methods is quite obvious.
Authors and Affiliations
Torabi, O. , Karimi, N. , shesh angosht, S. , Rashtbari, M. , & Sarbazvatan, A. H.
Keywords
Related Articles
- EP ID EP715799
- DOI 10.22034/el.2023.392546.1011
- Views 59
- Downloads 0
Investigating The Effect of ClimateChange On The FutureTourism of Lorestan Province using The TCI index And RCP Scenarios
It is said that climate change will have a negative impact on the tourism industry, since climate is one of the fundamental variables of tourism. In order to investigate the impact of climate change on the future situati...
The Impact of Climate Change on Jiroft Spring Wheat Yield Using Radiative Forcing Scenarios
Iran is considered one of the most arid and semi-arid regions in the world, where wheat accounts for about 65-70% of the cultivated land for the main crops. To predict the impact of climate change on the yield of fall wh...
Evaluating The Effectiveness Of Fuzzy Logic In Modeling Inner-City Highway Accidents
In this study, the effectiveness of fuzzy models in modelling inner-city highway accidents is evaluated using the Mashhad highway accident data as a case study. For modelling based on fuzzy logic, the variables related t...
Survey Of Urban Areas Based On TheIndicators Of The Happy City(Gorgan City)
Today's urban and modern life, despite the latest and most up-to-date technologies, has been able to make people's lives much easier than in the past and remove the hardships that people had to endure in the past, but th...
Analyzing The Causes And factor AffectingThe Production Of Garden City in Peri-Urban Areas Of Zanjan
Most of the cities in the country have encroached upon the agricultural lands around them, which were once called Garden City. These lands have been converted into construction sites, removing them from the scope of prof...