multivariate linear regression

Biomass is a crucial component of the carbon cycle; thus, accurate evaluation is essential to manage the forest and understand its role in climate change. Biomass estimation also supports the international reduced emission from deforestation and forest degradation (REDD), including cases such as deforestation reduction, sustainable management of forests, protection and enhancement of forest carbon reserves). Today, using remote sensing techniques with the help of field data has revolutionized the estimation of forest biomass. Forest biomass estimation can be based on the processing of remote sensing data obtained from active sensors (for example, lidar and radar) and passive sensors (for example, optical sensors). In most previous studies, mainly vegetation indices (such as Normalized Difference Vegetation Index (NDVI), Ratio Vegetation Index (RVI), and Soil-Adjusted Vegetation Index (SAVI)) have been used to estimate biomass. Using terrain data, the amount of biomass is estimated using allometric equations, and the required pre-processing is done on optical and radar images. The attributes obtained from the scattering matrix and the ratios of the components of the scattering matrix and the attributes obtained from H/α decomposition are extracted from the radar image and the attributes of vegetation, soil and water are extracted from the optical image. Results and discussion  In this study, in order to improve the accuracy of estimating the biomass of forest areas, the features extracted from the optical images of Sentinel-2 sensor and Sentinel-1 radar data as well as field data of Noor forest areas, Mazandaran province, whose forest cover type, Carpinus betulus and Quercus Castaneifolia and also includes rare species such as Populus Caspica Bornm trees. In this study, we used the genetic optimization method in four classes of mixed vegetation, natural forest, degraded forest, and forest reserves were studied. In this regard, multivariate linear regression and support vector regression have been used to model between ground data and radar and optical features. Genetic algorithm (GA) is one of the most common evolutionary algorithms. This method finds potential solutions to optimize problems at the right time, especially when the search space is very wide. Also, a genetic algorithm has been used during the modeling process using multivariate linear regression to select the optimal features extracted from radar and optical images. Evaluation of the results showed that the use of the multivariate regression method led to more accurate results than the support vector regression method in the study area. Also, evaluation of the results showed that using features selected by a genetic algorithm led to an accurate R2 of 0.78, 0.87, 0.68, and 0.79 for first to fourth vegetation classes, respectively. Therefore, the results showed that the efficiency of the genetic algorithm in feature selection for biomass estimation from satellite images using the multivariate regression method.

Point and nonpoint sources of pollution both affect water quality (Wang and Choi, 2005). Among the factors of non-point source, land use and land cover are the most important resources, which numerous research studied relationships between land use and water quality in different watersheds (Jun, 2011; Seeboonruang, 2012; Jun, 2013). There is a significant correlation between land use and water quality (Su et al. 2012; Wan et al., 2014) and this relationship is influenced by types and their spatial patterns land use. Landscape metrics have been used since 1980s to determine the degree of heterogeneity of spatial and landscape structure, including composition and configuration. Three features of the landscape are structure, composition and configuration based on landscape ecology (Amiri et al., 2016; Forman and Godron, 1986), which can be measured and analyzed based on the specific landscape metrics (Rutledge, 2003). Landscape structure has a great influence on the flow of nutrients at the catchment area (Amiri and Nakane 2009; Turner and Rabalais 2003). Due to the fact that non-point pollution has contributed to water pollution, the effect of non-point sources due to the change in landscape patterns is very important (Basnyat et al. 1999; Bhaduri, 2000). Moreover, landscape shows spatial heterogeneity of specific basin, and different patterns can be observed at various scales (Herold et al., 2005). A better understanding of the relationship between landscape metrics and water quality indicators can increase efforts in water management and research (Kearns et al., 2005).