A comparative mapping of plant species diversity using ensemble learning algorithms combined with high accuracy surface modeling

Abstract

Plant species diversity (PSD) has always been an essential component of biodiversity and plays an important role in ecosystem functions and services. However, it is still a huge challenge to simulate the spatial distribution of PSD due to the difficulties of data acquisition and unsatisfactory performance of predicting algorithms over large areas. A surge in the number of remote sensing imagery, along with the great success of machine learning, opens new opportunities for the mapping of PSD. Therefore, different machine learning algorithms combined with high-accuracy surface modeling (HASM) were firstly proposed to predict the PSD in the Xinghai, northeastern Qinghai-Tibetan Plateau, China. Spectral reflectance and vegetation indices, generated from Landsat 8 images, and environmental variables were taken as the potential explanatory factors of machine learning models including least absolute shrinkage and selection operator (Lasso), ridge regression (Ridge), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF). The prediction generated from these machine learning methods and in situ observation data were integrated by using HASM for the high-accuracy mapping of PSD including three species diversity indices. The results showed that PSD was closely associated with vegetation indices, followed by spectral reflectance and environmental factors. XGBoost combined with HASM (HASM-XGBoost) showed the best performance with the lowest MAE and RMSE. Our results suggested that the fusion of heterogeneous data and the ensemble of heterogeneous models may revolutionize our ability to predict the PSD over large areas, especially in some places limited by sparse field samples.

Relationship between plant species diversity and aboveground biomass in alpine grasslands on the Qinghai–Tibet Plateau: Spatial patterns and the factors driving them

“…In contrast, Wang et al (2022) used 1,620 samples obtained over 10 years, on the one hand the sample size was larger, and on the other hand the model was trained for environmental changes over a 10 year period, so the model accuracy was higher than this study. The R 2 of the optimal model in this study was 0.60, and the RMSE was 1.65 n/m 2 in the simulation of PSD; the RMSE of the RF model in Zhao et al (2022) was 1.94 n/m 2 , and the RMSE of the optimal HASM-XGBoot model reached 1.19 n/m 2 . HASM can effectively solve ecological environmental surface modeling errors, thus improving the accuracy of conventional machine learning models, we aim to test combinations of HASM methods in the future.…”

“…In previous studies in which biomass has been monitored via remote sensing, several variables including vegetation indices, climate, topography, soil, and other variables have been used to increase model accuracy (Liang et al, 2016). However, few studies have integrated variables such as effective vegetation index, climate, topography, soil, and other variables into models for large-scale grassland species diversity monitoring (Choe et al, 2021;Zhao et al, 2022). In addition, some studies (Fauvel et al, 2020;Ge et al, 2022) have compared the efficacy of multiple machine learning models for modeling grassland species diversity and biomass, previous studies have shown that the random forest (RF) model is particularly effective.…”

A data-driven machine learning approach for discovering potent LasR inhibitors

“…QSAR models attempt to derive the relationship between bioactivity and chemical features to predict potential inhibitors. Recently, incorporating machine learning (ML) methods, such as hyperparameter tuning [ 50 ] and ensemble methods [ 51 , 52 ] into QSAR modeling has improved the hit rate of QSAR models.…”