Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Abstract

Mapping the distribution of bamboo species is vital for the sustainable management of bamboo and for assessing its ecological and socioeconomic value. However, the spectral similarity between bamboo species makes this work extremely challenging through remote sensing technology. Existing related studies rarely integrate multiple feature variables and consider how to quantify the main factors affecting classification. Therefore, feature variables, such as spectra, topography, texture, and vegetation indices, were used to construct the XGBoost model to identify bamboo species using the Zhuhai-1 Orbita hyperspectral (OHS) imagery in the Southern Sichuan Bamboo Sea and its surrounding areas in Sichuan Province, China. The random forest and Spearman’s rank correlation analysis were used to sort the main variables that affect classification accuracy and minimize the effects of multicollinearity among variables. The main findings were: (1) The XGBoost model achieved accurate and reliable classification results. The XGBoost model had a higher overall accuracy (80.6%), kappa coefficient (0.708), and mean F1-score (0.805) than the spectral angle mapper (SAM) method; (2) The optimal feature variables that were important and uncorrelated for classification accuracy included the blue band (B1, 464–468 nm), near-infrared band (B27, 861–871 nm), green band (B5, 534–539 nm), elevation, texture feature mean, green band (B4, 517–523 nm), and red edge band (B17, 711–720 nm); and (3) the XGBoost model based on the optimal feature variable selection showed good adaptability to land classification and had better classification performance. Moreover, the mean F1-score indicated that the model could well balance the user’s and producer’s accuracy. Additionally, our study demonstrated that OHS imagery has great potential for land cover classification and that combining multiple features to enhance classification is an approach worth exploring. Our study provides a methodological reference for the application of OHS images for plant species identification.

Research on Estimation Model of Carbon Stock Based on Airborne LiDAR and Feature Screening

“…LiDAR is an active remote sensing technology that uses short-wavelength laser pulses to penetrate forest canopies and obtain vertical structure information [35]. In contrast to Zhou et al [36]'s study on categorizing feature variables based on the Random Forest algorithm and the SCC method, this study compares the effectiveness of an integrated algorithm of gradient boosting by iteratively training a series of weak learners and combining them with a statistical approach based on monotonic equations evaluating correlations of multiple statistical variables for the preferential selection of feature variables.…”

Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features

“…It builds a strong predictive model by sequentially combining multiple weak learners (usually decision trees). The idea is to correct the errors of the previous model at each iteration, effectively reducing the bias and variance of the overall model [ 39 ]. Decision trees are the base learners used in XGBoost.…”

Estimating carbon sequestration potential and optimizing management strategies for Moso bamboo (Phyllostachys pubescens) forests using machine learning

“…Finally, this biomass was multiplied by the conversion factor of 0.5042 to obtain the aboveground carbon stock in the Moso bamboo forests (Eq. 8) (Zhou, 2006).…”

“…Currently, numerous statistical methods are available for predicting forest carbon stocks. Traditional regression analysis methods may not be sufficient, and the use of machine learning algorithms can quickly and accurately assess the current carbon stock status in Moso bamboo forests (Poorazimy et al, 2020;Zhou et al, 2022;Li et al, 2023).…”