Forecasting PM10 Concentration from Blasting Operations in Open-Pit Mines Using Unmanned Aerial Vehicles and Adaptive Neuro-Fuzzy Inference System

In this paper, a state-of-the-art technology for modeling and controlling dust concentration from blasting operations in open-pit mines was introduced. Accordingly, a variety of smart sensors were mounted on an unmanned aerial vehicle to measure dust concentration (i.e., PM10) from blasting operations at the Thuong Tan IV quarry (Binh Duong). The meteorological conditions were also considered related to the air quality in open-pit mines. The dataset was then used to develop an artificial intelligence model for forecasting PM10 concentration in the spatial of the quarry, namely adaptive neuro-fuzzy inference system (ANFIS). The results indicated that PM10 induced by blasting operations in the quarry exceeds the allowable limit many times, and the ANFIS model can forecast PM10 concentration in the quarry with a high acceptable accuracy (~90%). It can be used to evaluate and control the air quality in the entire quarry. The paper also provided the evidence to develop better machine learning/artificial intelligence models for forecasting PM10 concentration induced by blasting operations, as well as other parameters in the air quality controlling in open-pit mines.