Instability and poor construction practices are responsible for the high accident rate in embankment construction in Spain. Applying a methodology based on data mining and attribute selection and using a 6-year database of accidents, key attributes in accidents associated with the construction of embankments were analyzed. Once the main predictors were identified, Bayesian networks in order to quantify the specific causes of different types of accidents were built. Thus, the main reasons for accidents as a preliminary phase to enhancing safety and embankment stability in mining and civil engineering works can be accurately identified and quantified.

Mining engineers and environmental experts around the world still identify and evaluate environmental risks associated with mining activities using field-based, basic qualitative methods The main objective is to introduce an innovative AI-based approach for the construction of environmental impact assessment (EIA) indexes that statistically reflects and takes into account the relationships between the different environmental factors, finding relevant patterns in the data and minimizing the influence of human bias. For that, an AutoML process developed with Bayesian networks is applied to the construction of an interactive EIA index tool capable of assessing dynamically the potential environmental impacts of a slate mine in Galicia (Spain) surrounded by the Natura 2000 Network. The results obtained show the moderate environmental impact of the whole exploitation; however, the strong need to protect the environmental factors related to surface and subsurface runoff, species or soil degradation was identified, for which the information theory results point to a weight between 6 and 12 times greater than not influential variables.

Increasing forest wildfires in Portugal remain a growing concern since forests in the Mediterranean region are vulnerable to recent global warming and reduction of precipitation. Therefore, a long-term negative effect is expected on the vegetation, with increasing drought and areas burnt by fires. The strawberry tree (Arbutus unedo L.) is particularly used in Portugal to produce a spirit by processing its fruits and is the main income for forestry owners. Other applications are possible due to the fruit and leaves’ anti-oxidant properties and bioactive compounds production, with a potential for clinical and food uses. It is a sclerophyllous plant, dry-adapted and fire resistant, enduring the Mediterranean climate, and recently considered as a possibility for afforestation, to intensify forest discontinuity where pines and eucalypts monoculture dominate the region. To improve our knowledge about the species’ spatial distribution we used 318 plots (the centroid of a 1 km² square grid) measuring the species presence and nine environmental attributes. The seven bioclimatic variables most impacting on the species distribution and two topographic features, slope and altitude, were used. The past, current and future climate data were obtained through WorldClim. Finally, the vulnerability of the strawberry tree to the effects of global climate change was examined in the face of two emission scenarios (RCP 4.5 and 8.5), to predict distribution changes in the years 2050 and 2070, using a species distribution models (MaxEnt). The reduction of suitable habitat for this species is significant in the southern regions, considering the future scenarios of global warming. Central and northern mountainous regions are putative predicted refuges for this species. Forest policy and management should reflect the impact of climate change on the usable areas for forestry, particularly considering species adapted to the Mediterranean regions and wildfires, such as the strawberry tree. The distribution of the species in the Last Glacial Maximum (LGM) and Mid-Holocene (MH) agrees with previous genetic and paleontological studies in the region, which support putative refuges for the species. Two in the southern and coastal-central regions, since the LGM, and one in the east-central mountainous region, considered as cryptic refugia.