Detecting and predicting vegetation cover changes using sentinel 2 Data (A Case Study: Andika Region)
محورهای موضوعی : فصلنامه علمی پژوهشی سنجش از دور راداری و نوری و سیستم اطلاعات جغرافیاییsedigheh emami 1 , esmail emami 2
1 - Ms in GIS, remote sensing,Yazd Branch, Islamic Azad University, Yazd, Iran
2 - Graduate student University of electric power systems of the Islamic trends free khomeynishahr
کلید واژه: NDVI, Sentinel 2, Cellular Automata Markov and logistic regression,
چکیده مقاله :
The earth surface is itself a complex system, and land cover variation is a complexprocess influenced by the interference of variables. In this study, the data of Sentinel 2for 2017 and 2016 were processed and classified to study the changes in the Andikaarea. After discovering vegetation changes between two images over the mentionedtime, vegetation increased by 661.74 hectares. Multiple regressions have been used toidentify factors affecting vegetation changes. Multiple regressions can explain therelationship between vegetation changes and the factors affecting them. In order toinvestigate the factors affecting vegetation change, altitude data, distance from theroad, distance from residential areas of the village and river were introduced intoregression equation. Since this method uses three parameters such as Pseudo-R2 andRelative Operation Characteristic (ROC(, 0.23, and 0.696 values for the aboveparameters, which indicates that the model is in good agreement. The results ofregression analysis show that linear composition of height variable as independentvariables in comparison with other parameters has been able to estimate vegetationchange. Subsequently, by using two classified pictures of 2017 and 2016, the amountof vegetation changes was calculated, and Markov chain method was used for 2018forecast changes.
The earth surface is itself a complex system, and land cover variation is a complexprocess influenced by the interference of variables. In this study, the data of Sentinel 2for 2017 and 2016 were processed and classified to study the changes in the Andikaarea. After discovering vegetation changes between two images over the mentionedtime, vegetation increased by 661.74 hectares. Multiple regressions have been used toidentify factors affecting vegetation changes. Multiple regressions can explain therelationship between vegetation changes and the factors affecting them. In order toinvestigate the factors affecting vegetation change, altitude data, distance from theroad, distance from residential areas of the village and river were introduced intoregression equation. Since this method uses three parameters such as Pseudo-R2 andRelative Operation Characteristic (ROC(, 0.23, and 0.696 values for the aboveparameters, which indicates that the model is in good agreement. The results ofregression analysis show that linear composition of height variable as independentvariables in comparison with other parameters has been able to estimate vegetationchange. Subsequently, by using two classified pictures of 2017 and 2016, the amountof vegetation changes was calculated, and Markov chain method was used for 2018forecast changes.
