Diego Aparecido Camargo

Tactical planning in timber harvesting involves aspects related to forest macro-planning and, particularly, the allocation of resources and sequencing of activities, all of which affect the allocation of timber in forest yards and roads and the productivity of forest machines. Data-driven approaches encourage the use of information obtained from data to enhance decision-making efficiency and support the development of short-term strategies. Therefore, our investigation was intended to determine whether a data-driven approach can generate sufficient input for modeling forwarder productivity in timber forwarding in Pinus and Eucalyptus planted forests, to support tactical planning. We utilized 3812 instances of raw data that were generated over a 36-month period. The data were collected from 23 loggers who operated in Pinus and Eucalyptus planted forests. We applied 22 regression algorithms that applied a supervised learning method from an experimental machine learning approach to the data instances. We evaluated the fitted models using three performance metrics. Out of the tested algorithms, the default mode of light gradient boosting produced a root mean squared error of 14.80 m³ h⁻¹, a mean absolute error of 2.70, and a coefficient of determination of 0.77. Therefore, data-driven methods adequately support forwarder productivity modeling in timber forwarding in planted forests and help forest managers with tactical planning.

Aim of study: We checked if an infrastructure investment project for a nursery to produce Eucalyptus forest seedlings using the real options approach was economically viable, in order to verify the influence of the deferral, expansion and abandonment options on the investment project value, as well as their concatenation. Area of study: Our study was based on technical-economic coefficients of a nursery infrastructure to be installed in the São Paulo’s state Midwest region, Brazil. Material and methods: The investment was assessed by addressing the uncertainties inherent in the investment project. We used the dynamic model for real option approach and, to determine the volatility of the project, we applied the Monte Carlo simulation method. As real options for the project, we employed deferral, expansion, and abandonment. Main results: Using the traditional valuation methodology, we obtained a negative static net present value of USD 50,957. When incorporating the real options of the abandonment, deferral and expansion in the form of managerial flexibility to forest managers, we obtained the expanded net present value of USD 216,498, that is, 524.8% of valuation. The traditional method of investment evaluation undervalues the project in infrastructures to produce Eucalyptus forest seedlings nursery, and the increase in managerial flexibility, through the real options for deferral, expansion and abandonment, promotes value to forest managers and enables the feasibility of the project. Research highlights: Infrastructure investment project for a nursery to produce Eucalyptus forest seedlings is not economically viable through the traditional economic evaluation techniques. However, by incorporating managerial flexibilities, through real options, the investment project was valued and it became economically viable.

Among the activities that burden capital in the supply chain of forest-based industries, the activity of road transport of wood deserves to be highlighted. Machine learning techniques are applied the knowledge extracted from real data, and support strategies that aim to maximize the resources destined for it. Based on variables inherent to the wood transport activity, we verified whether machine learning models can act as predictors of the volume of wood to be transported and support strategic decision-making. The database came from companies in the pulp and paper segments, which totaled 26,761 data instances. After the data wrangling process, machine learning algorithms were used to build models, which were optimized from the hyperparameter adjustment and selected to compose the blended learning hierarchy. In addition to belonging to different methodological basis, a CatBoost Regressor, Decision Tree Regressor, and K Neighbors Regressor were selected mainly for providing minimal values to errors metrics and maximal values to determination coefficient. The learning by stack stands out, with a coefficient of determination of 0.70 and an average absolute percentage error of 6% in the estimation of the volume of wood to be transported. Based on variables inherent to the wood transport process, we verified that machine learning models can act in the prediction of the volume of wood to be transported and support strategic decision-making.

Forest plantations with Toona ciliata are presented as economically viable thanks to the suitability of their wood for high-quality niche products. However, this study verifies whether investment projects in T. ciliata plantations are economically viable with the incorporation of managerial flexibility. We apply technical-economic coefficients from T. ciliata forest plantations over a 15-year planning horizon, considering the investment project as an underlying asset and the price of wood as the only source of uncertainty. Using the Monte Carlo method, we model uncertainty to obtain project volatility, so that, using the Real Option Approach, managerial flexibility for deferral, expansion and abandonment is added to the underlying assets. Based on the traditional economic valuation methodology, we obtained a static net present value of USD 5,075, which reflects the economic viability of the investment project in T. ciliata forest plantations. Due to the uncertainty arising from timber prices, project volatility was 131.7%. Afterwards, it was found that incorporating the deferral and abandonment options added a premium of USD 2,147 to the value of the project, redirecting it towards an expanded net present value of USD 7,223. Incorporation of the real deferral and abandonment options provides flexibility and support for the decision-making process in the management of T. ciliata forest plantations, resulting in a 42.3% increase in the value of the investment project.

The activity of the mechanized extraction of wood, carried out by means of self-propelled forest machines, consists of moving the wood cut inside the forest stand from the planted forests to the roadside. During displacements, these machines normally travel over forest residues and stumps, which can demand greater motor power from the engine, in addition to the possible increase in occupational noise levels. In this context, we evaluated whether, when operating different self-propelled forest machines in the wood extraction of planted Eucalyptus forests, operators are exposed to different levels of occupational noise, especially to thresholds above those established for prevention purposes. Occupational noise data were collected during the workday, weighing six self-propelled forest machine operators who performed the wood-extraction operation, performed by two forwarders, two self-loading tractors, and two grapple skidders, in three areas with Eucalyptus plantations located in the southeastern region of Brazil. The sound-pressure level was collected using two integrative meters following the strategic measurement criterion recommendation for the whole day in the guidelines of the acoustic determination of occupational noise exposure and analyzed according to the American Conference of Government Industrial Hygienists. Operators of forest machines for the mechanized extraction of wood were exposed to occupational noise levels above the recommended level, which can affect health and well-being; this occupation also required above-average levels of attention during the execution of work activities.

The correct capture of forest operations information carried out in forest plantations can help in the management of mechanized harvesting timber. Proper management must be able to dimension resources and tools necessary for the fulfillment of operations and helping in strategic, tactical, and operational planning. In order to facilitate the decision making of forest managers, this work aimed to analyze the performance of machine learning algorithms in estimating the productivity of timber harvesters. As predictors of productivity, we used the availability of hours of machine use, individual mean volumes of trees, and terrain slopes. The dataset was composed of 144,973 records, carried out over a period of 28 months. We tested the predictive performance of 24 machine learning algorithms in default mode. In addition, we tested the performance of blending and stacking joint learning methods. We evaluated the model’s fit using the root mean squared error, mean absolute error, mean absolute percentage error, and determination coefficient. After cleaning the initial database, we used only 1.12% to build the model. Learning by blending ensemble stood out with a determination coefficient of 0.71 and a mean absolute percentage error of 15%. From the use of data from machine learning algorithms, it became possible to predict the productivity of timber harvesters. Testing a variety of machine learning algorithms with different dynamics contributed to the machine learning technique that helped us reach our goal: maximizing the model’s performance by conducting experimentation.

The decision to harvest planted forests transcends the adopted silvicultural schedule, given that external market factors such as fluctuations in demand for timber products intensify managerial responses regarding the supply of raw materials. Therefore, forest managers need prior planning to correctly model market uncertainties and risks and thus remain nimble in decision-making. We identify the best probability distribution for modelling the price of Eucalyptus wood to assist managerial decision-making when advanced- or postponed-harvesting options are available for planted forests. Our study was based on a planted forest of Eucalyptus in an area of 11 677 ha belonging to a forest-based company in the Midwest region of the state of São Paulo, Brazil. We tested harvesting in the sixth, seventh and eighth year under the single-rotation silvicultural management system of forest reform. Our decisions are based on econometric tests and incorporate flexibility through the Real Options Approach with the Monte Carlo simulation method. The modelling of the recommended wood price was performed using fractional Brownian motion, which resulted in an expanded present value of USD 40 747 966 – that is, an increase of 161% over the static present value, with a 62.7% probability of the harvest occurring in the seventh year. Thus, we conclude that the incorporation of managerial flexibility in decisions on the timing of planted-forest harvesting adds value to forest investment projects considered economically unfeasible by traditional methodologies.

Wood harvesting operations involve mechanized and semi-mechanized machines that expose operators to occupational noise. It was verified that the emission of occupational noise levels in the harvest of mechanized and semi-mechanized wood in Brazilian forests planted with eucalyptus were in compliance with Directive 2003/10/EC. Noise data were collected using two personal-use integrative meters. The lower action level of 80 dB(A), the upper action level of 85 dB(A) and the exposure limit of 87 dB(A) were evaluated. The results showed that 16.6% of the operators were exposed to thresholds above the lower action level, but remained below the upper level of 85 dB(A), 8.3% of the operators were exposed to occupational noise levels above the upper action level, without exceeding the exposure limit of 87 dB(A) and 25% of operators were exposed to levels above the exposure limit. Therefore, the occupational noise levels achieved when harvesting mechanized and semi-mechanized wood in forests planted with eucalyptus do not comply with Directive 2003/10/EC.

Physical agent noise can be considered one of the main disturbances that compromise the occupational health of self-propelled forest machine operators. We evaluated whether occupational noise levels emitted by self-propelled forest machines employed in the full tree system are in accordance with both the National Institute for Occupational Safety and Health and ISO 1999:2013 standards, while also proposing mitigating measures aimed at protecting the operators hearing. Seventeen operators, who performed wood harvesting operations in Eucalyptus forests in Brazil, were analyzed. Noise levels were collected in a daily shift of eight hours as recommended by the Acoustics – Determination of occupational noise exposure - Engineering method for full-day measurements (ISO 9612:2009). The standards adopted for the evaluation were the exposure action value of 80 dBA and the exposure limit of 85 dBA based on the National Institute for Occupational Safety and Health – NIOSH and on Acoustics – Estimation of noise-induced hearing loss (ISO 1999:2013) Directive 2003/10/EC. The operators were arranged in homogeneous groups according to the Acoustics recommendation – Determination of occupational noise exposure - Engineering method for full-day measurements (ISO 9612:2009), classified by the operations of felling, skidding of tree bundles and bucking. The results showed that 17 self-propelled forest machines exceeded the exposure action value of 80 dBA, of which 10 machines exceeded the exposure limit of 85 dBA. It was concluded that the levels of occupational noise emitted by self-propelled forest machines used in the full tree system are higher than those recommended by both standards, National Institute for Occupational Safety and Health and ISO 1999:2013. Therefore, the allocation of self-propelled forest machines to homogeneous groups allows inferring mitigation actions that protect operators' hearing. The correct use of hearing protectors during the daily workday provides hearing protection for operators in mechanized wood harvesting. Adoption of actions such as maintenance of cabin seals and mechanical components, breaks for fatigue relief, reduction of daily working hours and rotation of operators in different self-propelled forest machines can mitigate the damage to the occupational health of operators.

Exposure to noise in the working environment of forest machine operators harvesting wood in planted forests can compromise their health, safety and quality of life. The objective of the study reported here was to assess whether full-time occupational noise exposure among forest machine operators employed in the harvesting of Pinus taeda in southern Brazil aligns with the standards of Brazil's National Institute for Occupational Safety and Health (NIOSH). Data were collected from four operators of self-propelled forestry machines that performed mechanised wood harvesting operations, including felling, extraction and processing of trees in planted P. taeda forests. The noise levels were collected during an eight-hour workday using the strategic measurement criterion for the whole day in the guidelines of Acoustics - Determination of occupational noise exposure. Noise levels were analysed according to the criteria established by NIOSH. The percentage of the risk of hearing loss was estimated according to the Portuguese Standard. In felling and processing operations, results show that the average daily exposure levels to occupational noise exceeded the action level of 80 dB(A). During timber extraction, the operators were exposed to noise levels above the exposure limit of 85 dB(A). However, given that the study's statistics were directed to a comparative analysis, it was not possible to establish a hypothesis of inference on the observed variables.