Machine learning-based prediction and assessment of recent dynamics of forest net primary productivity in Romania.

While the analysis of spatio-temporal changes in the net primary productivity (NPP) of forests can provide critical information on carbon cycle and climate change, these ecological trends have remained unclear in many countries worldwide, including Romania. By using complex (satellite, forest and climate) data, many sophisticated (machine learning) algorithms and some widely applied (the Mann-Kendall test and Sen's slope estimator) statistical procedures, this study investigates, for the first time, recent forest NPP trends (1987-2018) that occurred in Romania, in relation to climate change that affected the country over the past decades. Following the modelling, mapping and assessment of NPP dynamics, results showed almost exclusively positive trends for this ecological parameter, which accounts for ∼99% of all forest NPP changes that occurred throughout the country, after 1987. Interestingly, almost three quarters (∼73%) of all NPP increasing trends are statistically significant, which indicates that Romania's forests have recently experienced a large-scale improvement in carbon fluxes and stocks. Investigations of eco-climatic relationships suggest that climate change has partially contributed to these surprising NPP dynamics observed in recent decades. All these findings can provide valuable information for forest management and for many stakeholders and policymakers who operate in the forestry and climate fields in Romania.

Climate change perception in Romania.

In the last decades, anthropogenic drivers have significantly influenced the natural climate variability of Earth's atmosphere. Climate change has become a subject of major interest for different levels of our society, such as national governments, businesses, local administration, or citizens. While national and local policies propose mitigation and adaptation strategies for different sectors, public perception is a key component of any implementation plan. This study investigates the CC perception in Romania, based on a national-scale online survey performed in the spring of 2020, aiming to outline the prominence of environmental and CC issues, level of information and interest, perceived causes, changes perceived in meteorological phenomena at the regional scale, perceived impacts, and the psychological representation of the CC. The study investigates single causal factors of perception. We found that particularly (i) the regional differences on climate change intensity strongly bias the perception of CC causes; (ii) age is very likely to influence the acceptance of CC, the importance of environmental issues, and the levels of information and interest; while (iii) age, gender, and place of residence (rural-urban) are very likely to control the changes perceived in the occurrence of various meteorological phenomena, and their impact. This research is the first statistically relevant analysis (± 4%, statistical significance) developed at national and regional scales and the only study of climate change perception performed during the COVID-19 pandemic in Romania. Its results may represent the baseline for more in-depth research. Supplementary Information: The online version contains supplementary material available at 10.1007/s00704-022-04041-4.