Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

Abstract

Background: In fast-growing forests such as Eucalyptus plantations, the correct determination of stand productivity is essential to aid decision making processes and ensure the efficiency of the wood supply chain. In the past decade, advances in remote sensing and computational methods have yielded new tools, techniques, and technologies that have led to improvements in forest management and forest productivity assessments. Our aim was to estimate and map the basal area and volume of Eucalyptus stands through the integration of forest inventory, remote sensing, parametric, and nonparametric methods of spatial prediction. Methods: This study was conducted in 20 5-year-old clonal stands (362 ha) of Eucalyptus urophylla S.T.Blake x Eucalyptus camaldulensis Dehnh. The stands are located in the northwest region of Minas Gerais state, Brazil. Basal area and volume data were obtained from forest inventory operations carried out in the field. Spectral data were collected from a Landsat 5 TM satellite image, composed of spectral bands and vegetation indices. Multiple linear regression (MLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN) methods were used for basal area and volume estimation. Using ordinary kriging, we spatialised the residuals generated by the spatial prediction methods for the correction of trends in the estimates and more detailing of the spatial behaviour of basal area and volume. Results: The ND54 index was the spectral variable that had the best correlation values with basal area (r = − 0.91) and volume (r = − 0.52) and was also the variable that most contributed to basal area and volume estimates by the MLR and RF methods. The RF algorithm presented smaller basal area and volume errors when compared to other machine learning algorithms and MLR. The addition of residual kriging in spatial prediction methods did not necessarily result in relative improvements in the estimations of these methods. Conclusions: Random forest was the best method of spatial prediction and mapping of basal area and volume in the study area. The combination of spatial prediction methods with residual kriging did not result in relative improvement of spatial prediction accuracy of basal area and volume in all methods assessed in this study, and there is not always a spatial dependency structure in the residuals of a spatial prediction method. The approaches used in this study provide a framework for integrating field and multispectral data, highlighting methods that greatly improve spatial prediction of basal area and volume estimation in Eucalyptus stands. This has potential to support fast growth plantation monitoring, offering options for a robust analysis of high-dimensional data.

Analysis of Ice Storm Impact on and Post-Disaster Recovery of Typical Subtropical Forests in Southeast China

“…By studying the correlation between various remote-sensing vegetation indices and measured forestry data, scholars have evaluated the feasibility of using remote-sensing data to study forest changes, as well as the applicability of various remote-sensing indices [38][39][40]. Macedo et al [41] used forest inventory data (24 plots) and forest indices (NDVI, EVI, SR, and SAVI) derived from high-spatial-resolution satellite images, to estimate and map the aboveground biomass of Mediterranean Quercus rotundifolia in Southern Portugal.…”

Modelling and Predicting the Growing Stock Volume in Small-Scale Plantation Forests of Tanzania Using Multi-Sensor Image Synergy

“…Optical satellite sensors have been widely used to estimate and model forest attributes, such as forest area and character [11,12], volume [13][14][15], and above ground biomass (AGB) See survey by [16] due to their sensitivity to vegetation response observed in multispectral bands. However, optical sensors are obstructed by atmospheric conditions and cloud cover, which reduces their potential operational use especially in cloudy prone areas.…”

Monitoring sustainable development by means of earth observation data and machine learning: a review

“…Land use The approach based on CNN achieved an accuracy of ≅ 98% for land use and land cover analysis [84] The proposed approach confirmed its suitability for urban planning because it had a superior performance compared to the global one [56] Living conditions Deep learning demonstrated a high potential to map areas of deprived living conditions [85] Land cover The multivariate time series algorithm showed high accuracy for rare land cover classes Forest Sentinel-2 is considered a powerful source of data for forest monitoring and mapping [52] RF was the best method to predict and map the area and volume of eucalyptus [88] is to group image pixels or sub-pixels into unlabelled classes [11]. Table 8 lists some recent examples regarding the application of unsupervised classification techniques.…”