In recent years, concern has been raised that the trend of continuous productivity improvements of forest harvesting has stagnated and even declined in the Nordics. This selective literature review therefore examines human factors research with regard to the performance of the harvesting system, and outlines how human factors research can stimulate continued performance improvements. The focus is on implications for mechanized cut-to-length (CTL) operations and, especially, research of importance to the operation of the single grip harvester and the harvester-forwarder system. Most literature for this review was found in the Web of Knowledge and Google Scholar databases or as a consequence of the snowballing approach also applied. A conceptual framework was used to facilitate the analysis of the interrelated elements – Human, Technology, Organization and Environment (HTO-E). The right abilities, skills, techniques and training alone are not sufficient for ensuring high performance of the logging system. To address this discrepancy, education, training, (semi-) automation, shift scheduling, harvester-forwarder cooperation, inter- and intra- organizational knowledge exchange were all recognized as important areas for improvement and development. Great difficulties exist in predicting outcomes when introducing change, for example automation, into a system. However, the consequences of not trying may be detrimental to productivity as well as safety in mechanized forestry. Thus, it is important to research into methods, interfaces, forms of interaction, risk analyses and automation technology. HTO-E and a systems perspective provide a good basis for understanding the work today and making educated predictions for the future.

Modern forest harvesters automatically collect large amounts of standardized work-related data. Statistical machine learning methods enable detailed analyses of large databases from wood harvesting operations. In the present study, gradient boosted machine (GBM), support vector machine (SVM) and ordinary least square (OLS) regression were implemented and compared in predicting the productivity of cut-to-length (CTL) harvesting based on operational monitoring files generated by the harvesters’ on-board computers. The data consisted of 1,381 observations from 27 operators and 19 single-grip harvesters. Each tested method detected the mean stem volume as the most significant factor affecting productivity. Depending on the modeling approach, 33–59% of variation was due to the operators. The best GBM model was able to predict the productivity with 90.2% R², whereas OLS and the SVM machine reached R²-values of 89.3% and 87% R², respectively. OLS regression still proved to be an effective method for predicting productivity of CTL harvesting with a limited number of observations and variables, but more powerful GBM and SVM show great potential as the amount of data increases along with the development of various big data applications.