Modeling of Aboveground Carbon stock using Sentinel -1, 2 satellite Imagery and Parametric and Nonparametric Relationships (Case Study: District 3 of Sangdeh Forests)

Subject Areas : Agriculture, rangeland, watershed and forestry

Seyed Mahdi Rezaei Sangdehi ¹ , Asghar Fallah ² , Homan Latifi ³ , Nastaran Nazariani ⁴

1 - Ph.D. student in Forestry, Faculty of Natural Resources, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran.
2 - Prof. Department of Forestry, Faculty of Natural Resources. Sari Agricultural Sciences and Natural Resources. University-IRAN
3 - Assistant Professor, Faculty of Surveying Engineering, Khajeh Nasir Tusi University of Technology, Tehran, Iran.
4 - Postdoctoral researcher, Department of Forestry, Faculty of Natural Resources, Sari University of Agricultural Sciences and Natural Resources

Received: 2022-01-21 Accepted : 2022-04-20 Published : 2023-05-22

Keywords: Vegetation indices, Bias, remote sensing, Support Vector Machines: SVM, biomass,

Abstract :

In this study, the goal is; Find suitable statistical and experimental models for estimating ground carbon storage by combining spectral and radar data from Sentinel 1, 2. There are 150 random circular samples with an area of 10 acres and a total of 150 samples. With global coverage, all height classes were selected. Species of species type, the total height of trees, and diameter equal to the chest of trees with more than 7.5 cm were recorded in each sample plot. After that, the amount of biomass at the surface of the sample parts was calculated based on the FAO global model and the amount of carbon storage on the ground by applying a coefficient. Radar and spectral images were subjected to various preprocessing operations and necessary processing. Then, the numerical values corresponding to the ground sample plots were extracted from the spectral bands and considered as independent variables. Modeling was performed by non-parametric methods of RF, SVM, kNN, and parametric methods of multiple linear regressions. The results showed that the average ground biomass was 469.07 tons per hectare and carbon storage was 234.53 tons per hectare. Also, the highest correlation was obtained between the main and artificial bands with the two characteristics related to the near-infrared band. The results of modeling validation showed the combination of optical and radar data of Sentinel 1, 2 satellites with biomass and surface carbon storage; Random forest method with the RMSE%, and percentage of bias. The studied characteristics (32.79, -2.24) and (30.79 and 0.01), respectively, have had a better performance in modeling. In general, the results obtained from the validation showed that in estimating the two characteristics the RF method showed better results if the Sentinel 1, 2 data were combined, and in contrast to the SVM.