Abstract
ABSTRACTRemote-sensing technology has been a useful tool for mapping and characterizing forest cover types and species composition, providing valuable information for effective forest management. This study investigates the application of a genetic algorithm (GA)-based approach on Normalized Difference Vegetation Index (NDVI) to separate local forest communities at Huntington Wildlife Forest (HWF), located in New York State of the United States, into deciduous, mixed/coniferous and nonforests using Landsat TM imagery. Overall accuracy, producer’s accuracy, user’s accuracy and kappa coefficient of agreement are employed to assess the performance of the proposed method. Its overall effectiveness is supported by the accuracy of 80.41% and kappa coefficient of 0.56, and its capability of separating the forest cover types is endorsed by the class-wise accuracy measures. This method shows advantages in its limited demands for input features, that only multi-temporal NDVI indices are required; and in its simple and efficient mechanism, which refers to threshold optimization and feature selection.
Highlights
Results from Analysis of Variance (ANOVA) suggest a rejection of the hypothesis that the mean Normalized Difference Vegetation Index (NDVI) of the 6 months are equal
A genetic algorithm-based method was proposed for classifying the Huntington Wildlife Forest into deciduous, mixed/coniferous, and nonforests types, using multi-temporal NDVI derived from the Landsat Thematic Mapper (TM) imagery
Statistical approaches such as ANOVA and canonical discriminant analysis were utilized for priori knowledge of the NDVI variables, facilitating subsequent decisions on selecting different groups of predicting variables for model calibration
Summary
Forest type composition provides valuable information for forest inventory and management, it is increasingly desirable to obtain the spatially explicit forest type distribution for a range of applications such as forest monitoring (Lehmann et al 2015; Liu, Im, and Quackenbush 2015; Sankey et al 2017), natural resources (Corona 2016; Li et al 2014), biodiversity and ecosystems (Barlow et al 2016; Laurin et al 2014; Van der Plas et al 2018) and climate change (Charney et al 2016; Asner et al 2017). Advanced remote sensing technology offers a unique capability of large-scale forest mapping in a costeffective manner (Gudex-Cross, Pontius, and Adams 2017; Khatami, Mountrakis, and Stehman 2016; Zhen, Quackenbush, and Zhang 2016). The usefulness of multi-temporal Landsat imagery for forest species/type classification has been extensively explored, and favorable performances have been achieved at varied geographical scales (Gudex-Cross, Pontius, and Adams 2017; Li, Im, and Beier 2013; Zhu and Woodcock 2014). In the Landsat family, the Landsat Thematic Mapper (TM) data have been proved ideal for mapping forest type composition at local and regional scales, considering its moderate spatial resolution (30 m) and temporal frequency (16 days) (NASA 2018), as well as the low cost and wide availability (Mancino et al 2014; Foody and Hill 1996; Li et al 2018)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.