Mining is a dominant industry which generates a lot of business for countries across the globe. It practically impacts every facet of the economy as it contributes to the raw materials needed for almost every sector from electronics to energy.

While the mining industry is hugely profitable, it also faces issues around power, infrastructure, health, safety, approach and allotment of capital, commodity prices, environmental consequences, among others. To make the scenario better and overcome existing challenges, artificial intelligence and machine learning are bringing a major breakthrough in the mining industry.

Artificial Intelligence In Mining

With the help of AI, job-related risks in mining such as dust inhalation, casualty to hearing due to the noise at the mining location, chemical risks and the exposure to collapse can be vanquished. Operations, productivity, and wastages can also be managed better.

Safety: A majority of mining applications use an immense cluster of sensors to assemble information on machinery, but organizing and applying the insights in real-time can be achieved only through ML algorithms. They can adopt classical equipment data, environment, weather and current situations to predict when a machine needs preservation or might fail.

Expenses: Integrating AI with mine monitoring algorithms, organizations can analyze various activities in the current operation and identify key areas of improvement. Using sensors in mining can also provide plenty of data which aids AI for better interpretation of mining operations.

Current Breakthroughs In Mining With AI

• Goldspot Discoveries.inc, a Canada-based company has successfully applied AI in mineral exploration. They were able to anticipate 86 percent of current gold deposits in the Canadian Abitibi gold belt by using only 4 percent of the geological, mineral and topological data of the surface area.
• Another Canadian company called Motion Metrics is using fragmentation analysis which is an AI-based prototype for accurate measuring of rock fragmentation within the shovel bucket. In this process, data which is collected can give valuable feedback to blasting engineers and increase productivity through payload monitoring and optimizing teeth changeouts by checking teeth wear.
• TOMRA, a Norwegian multinational corporation has developed mineral and ore sorting equipment which uses sensors to separate important mineral ores from waste rock. This helps to make operations more energy and cost-effective.
• A data science company called PETRA developed an AI algorithm which automatically fragments the assigned ore within a minute, which takes more than an hour when done manually.
• BHP, a Melbourne-headquartered mining company which undertook a copper mining project in Chile has used neural network technology based smart caps which analyses driver brain waves to act according to the situation. Once they were successfully tested these were integrated into 150 trucks to accelerate productivity and safety.
• VALE a Brazilian metal and mines multinational corporation uses predictive analysis to improve the machine lifespan and cut down their capital investment. They increased the lifespan of haul truck tires up to 30 percent which saves $5 million per year, by predicting up to 85 percent of rail breakdowns at the Carajas and Victoria (Brazil) mines.  They saved $7 million per year. In total, they hope to save nearly $26 million in the year 2018 alone.
• GoldCorp company recently collaborated with IBM to inject their smart technology for mining exploration. The IBM Watson services are being used to study drilling reports, geological survey data and specifying which areas to explore. This helps in swiftly locating the desired areas.
• A company called Dronedeploy is using drones to accumulate aerial data for analyzing. Once the data is analyzed it aids in creating maps and build 3D models for accurate planning and make critical calculations. This technique saves time and money for the companies.

Scenario In India

India has abundant reserves of iron, manganese, bauxite, chromite, coal and other minerals. According to the 2012 census, around 7,00,000 individuals are working in the mining industry. It contributes around 10 to 11 percent of the industrial sectors GDP, which is close to $106 billion. In spite of being the world’s largest producer of sheet mica, the third largest producer of iron ore and standing fifth in bauxite production there are hurdles which the Indian mining industry faces. Some of the predominant challenges are land availability, outdated mechanisms, and ineffective capital investments.

A report suggests that advanced use cases of deep learning techniques such as CNN and AI have helped the mining industry. Despite the huge potential and need for these technologies to be adopted in the mining industry, India lags behind in research and development in the space of AI and ML in the mining industry. However, with AI research in India speeding up and many startups coming up in the space of AI, let’s hope that a modernized mining industry in India comes sooner.