Determinants of Above-Ground Biomass and Its Spatial Variability in a Temperate Forest Managed for Timber Production

Spatial predictions of tree density and tree height across Mexico forests using ensemble learning and forest inventory data

The National Forestry Commission of Mexico continuously monitors forest structure within the country's continental territory by the implementation of the National Forest and Soils Inventory (INFyS). Due to the challenges involved in collecting data exclusively from field surveys, there are spatial information gaps for important forest attributes. This can produce bias or increase uncertainty when generating estimates required to support forest management decisions. Our objective is to predict the spatial distribution of tree height and tree density in all Mexican forests. We performed wall-to-wall spatial predictions of both attributes in 1-km grids, using ensemble machine learning across each forest type in Mexico. Predictor variables include remote sensing imagery and other geospatial data (e.g., mean precipitation, surface temperature, canopy cover). Training data is from the 2009 to 2014 cycle (n > 26,000 sampling plots). Spatial cross validation suggested that the model had a better performance when predicting tree height r 2 = .35 [.12, .51] (mean [min, max]) than for tree density r 2 = .23 [.05, .42]. The best predictive performance when mapping tree height was for broadleaf and coniferous-broadleaf forests (model explained ~50% of variance). The best predictive performance when mapping tree density was for tropical forest (model explained ~40% of variance). Although most forests had relatively low uncertainty for tree height predictions, e.g., values <60%, arid and semiarid ecosystems had high uncertainty, e.g., values >80%. Uncertainty values for tree density predictions were >80% in most forests. The applied open science approach we present is easily replicable and scalable, thus it is helpful to assist in the decision-making and future of the National Forest and Soils Inventory. This work highlights the need for analytical tools that help us exploit the full potential of the Mexican forest inventory datasets.

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

The forest stock volume (FSV) is one of the key indicators in forestry resource assessments on local, regional, and national scales. To date, scaling up in situ plot-scale measurements across landscapes is still a great challenge in the estimation of FSVs. In this study, Sentinel-2 imagery, the Google Earth Engine (GEE) cloud computing platform, three base station joint differential positioning technology (TBSJDPT), and three algorithms were used to build an FSV model for forests located in Hunan Province, southern China. The GEE cloud computing platform was used to extract the imagery variables from the Sentinel-2 imagery pixels. The TBSJDPT was put forward and used to provide high-precision positions of the sample plot data. The random forests (RF), support vector regression (SVR), and multiple linear regression (MLR) algorithms were used to estimate the FSV. For each pixel, 24 variables were extracted from the Sentinel-2 images taken in 2017 and 2018. The RF model performed the best in both the training phase (i.e., R2 = 0.91, RMSE = 35.13 m3 ha−1, n = 321) and in the test phase (i.e., R2 = 0.58, RMSE = 65.03 m3 ha−1, and n = 138). This model was followed by the SVR model (R2 = 0.54, RMSE = 65.60 m3 ha−1, n = 321 in training; R2 = 0.54, RMSE = 66.00 m3 ha−1, n = 138 in testing), which was slightly better than the MLR model (R2 = 0.38, RMSE = 75.74 m3 ha−1, and n = 321 in training; R2 = 0.49, RMSE = 70.22 m3 ha−1, and n = 138 in testing) in both the training phase and test phase. The best predictive band was Red-Edge 1 (B5), which performed well both in the machine learning methods and in the MLR method. The Blue band (B2), Green band (B3), Red band (B4), SWIR2 band (B12), and vegetation indices (TCW, NDVI_B5, and TCB) were used in the machine learning models, and only one vegetation index (MSI) was used in the MLR model. We mapped the FSV distribution in Hunan Province (3.50 × 108 m3) based on the RF model; it reached a total accuracy of 63.87% compared with the official forest report in 2017 (5.48 × 108 m3). The results from this study will help develop and improve satellite-based methods to estimate FSVs on local, regional and national scales.

Beta-Diversity Modeling and Mapping with LiDAR and Multispectral Sensors in a Semi-Evergreen Tropical Forest

Tree beta-diversity denotes the variation in species composition at stand level, it is a key indicator of forest degradation, and is conjointly required with alpha-diversity for management decision making but has seldom been considered. Our aim was to map it in a continuous way with remote sensing technologies over a tropical landscape with different disturbance histories. We extracted a floristic gradient of dissimilarity through a non-metric multidimensional scaling ordination based on the ecological importance value of each species, which showed sensitivity to different land use history through significant differences in the gradient scores between the disturbances. After finding strong correlations between the floristic gradient and the rapidEye multispectral textures and LiDAR-derived variables, it was linearly regressed against them; variable selection was performed by fitting mixed-effect models. The redEdge band mean, the Canopy Height Model, and the infrared band variance explained 68% of its spatial variability, each coefficient with a relative importance of 49%, 32.5%, and 18.5% respectively. Our results confirmed the synergic use of LiDAR and multispectral sensors to map tree beta-diversity at stand level. This approach can be used, combined with ground data, to detect effects (either negative or positive) of management practices or natural disturbances on tree species composition.