Regression analysis is widely applied in many fields of science to estimate important variables. In general, nonlinear regression is a complex optimization problem and presents intrinsic difficulties in estimating reliable parameters. Nonlinear optimization algorithms commonly require a precise initial estimate to return reasonable estimates. In this work, we introduce a new hybrid algorithm based on the association of a genetic algorithm with the Levenberg–Marquardt method (GALM) to adjust biological nonlinear models without knowledge of initial parameter estimates. The proposed hybrid algorithm was applied to 12 nonlinear models widely used in forest sciences and 12 databases under varying conditions considering classic hypsometric relationships to evaluate the robustness of this new approach. The hybrid method involves two stages; the curve approximation process begins with a genetic algorithm with a modified local search approach. The second stage involves the application of the Levenberg–Marquardt algorithm. The final performance of the hybrid method was evaluated using total fitting for all tested models and databases, confirming the reliability of the proposed algorithm in providing stable parameter estimates. The GA was able to predict the initial parameters, which assisted the LM in converging efficiently. The developed GALM method is effective, and its application is recommended for biological nonlinear analyses.

The insertion of stand variables allows for generalized mixed-effects height-diameter model, and the inclusion of random effects aids in model flexibility and application to new databases through calibration. This study aimed to develop a generalized mixed-effects model capable of accurately predicting the total height of Pinus taeda trees, subjected to different management regimes and at different ages.

The Global Ecosystem Dynamics Investigation (GEDI) instrument, as all FW systems, relies on very sophisticated pre-processing steps to generate a priori metrics in order to accurately estimate forest characteristics, such as forest heights and wood volume. The ever-expanding volume of acquired GEDI data, which to September 2020 comprised more than 25 billion shots, and requiring more than 90 TB of storage space, raises new challenges in terms of adapted preprocessing methods for the suitable exploitation of such a huge and complex amount of LiDAR data. Therefore, to avoid metric computation, we leveraged deep learning techniques in order to estimate canopy dominant heights (H dom ) and wood volume (V) of Eucalyptus plantations over five different regions in Brazil. Performance comparisons were conducted between a convolutional neural network based model that uses GEDI waveform data and a previously used, metric based, Random Forest regressor (RF). Cross-validated results showed that the CNN based model compared well against the RF counterpart for both H dom and V. Indeed, the RMSE on the estimation of H dom from the CNN based model was 1.61 m with a coefficient of determination R ² of 0.90, while the RF model produced an accuracy on H dom estimates of 1.45 m(R ² =0.92). For V, CNN based estimates was 27.35 m3.ha-1(R ² of 0.88), while for RF, the RMSE was 27.60 m3.ha-1 (R ² =0.88).

The objective of this work was to evaluate the variation in the fruit production of Brazil nut (Bertholletia excelsa) trees in the Eastern Amazon through geostatistical techniques and generalized linear models (GLMs). A nine-hectare permanent plot in the Cajari River extractive reserve was analyzed. All trees (61) with diameter at breast height (DBH) ≥10 cm were evaluated. Within each plot, 43 subplots of 250 m2 were established for sampling vegetation and soil at a depth of 0-20 cm. The data were processed using geostatistical techniques and the Poisson and negative binomial GLMs. The 20 evaluated variables showed spatial dependence. Although both models were fit to estimate fruit production, the negative binomial model better accommodated data variability. Tree diameter and soil physical attributes (density, clay, and water content) better explain the variation in fruit production, together with magnesium and carbon content that are the main chemical soil properties associated with higher yields.