The paper is devoted to the application of a machine learning model with reinforcement for automating the planning of the deployment of logging sites in forestry. A method for optimizing the selection of cutting areas based on the algorithm of optimization of the Proximal Policy Optimization is proposed. An information system adapted for processing forest management data in a matrix form and working with geographic information systems has been developed. The experiments conducted demonstrate the ability to find rational options for the placement of cutting areas using the proposed method. The results obtained are promising for the use of intelligent systems in the forestry industry.

Keywords: reinforcement learning, deep learning, cutting areas location, forestry, artificial intelligence, planning optimization, clear-cutting

Utilisation a waste of stone processing in production of other kinds products is an actual task for stone-cutting enterprises. In this study, the possibilities of using basalt dust generated during sawing, grinding and polishing of basalt and related minerals in the manufacture with concrete are studied. Three groups were prepared with different content of basalt dust - 0 %, 5 % and 20 %. After the final hardening performance of the concrete, the compressive strength testing was conducted on the specimens. The results showed that the addition (5%) added basalt dust practically did not reduce the strength ratio practically, the increase of basalt dust content up to 20% caused an average 16% reduction in the strength of the specimens. The fracture character that occurred in the specimens containing basalt dust corresponded to the fracture character that happened to similarly shaped concrete products.

Keywords: concrete, stone waste, strength, basalt