CONTAIN™ - The new evolution in AI-powered ore sorting
CONTAIN™ gives you clarity where there was uncertainty
Most sorting systems work with what they see, CONTAIN™ with what it understands. By using deep learning, it detects inclusion-type ores like tin, tungsten, nickel, copper and sulfides - helping miners unlock value previously lost in the tailings stream. Transform unknows into insights. Transform ore variability into opportunity. Transform buried value into measurable output. CONTAIN™ doesn't just sort - it thinks. it sees beyond the surface to detect what others can't, making your plant smarter, leaner, and more profitable.
AI and deep learning will give us amazing opportunities for the future by improving sorting performance and add significant value to the mineral processing industry.
Benefits
Transforming pattern recognition into operational value
Unlike traditional optical sorting systems, which often struggle to detect low-grade or inclusion-type ores, CONTAIN™ introduces a fundamentally different approach to classification. By analyzing the structure of each rock using advanced deep learning algorithms, the system identifies subtle mineralogical patterns that indicate the presence of valuable metals such as tungsten, nickel or tin. Each rock is assigned a probability score based on its likelihood of containing subsurface mineralization, enabling precise, data-driven sorting decisions. This capability allows mining operations to adapt their strategies in real time – whether the goal is to maximize concentrate grade, minimize valuable material loss, or align with processing cost constraints.
Sorting Performance across ore grades
CONTAIN™ has been engineered to handle a wide spectrum of ore grades – from high-value deposits to low-grade, large rocks with sparse inclusions that have historically been difficult to process efficiently. Conventional sorting systems can be configured to detect some low-grade material, but they tend to let large volumes of gangue enter the product stream, diluting output and eroding profitability. By contrast, CONTAIN™ uses deep learning to classify mineralizations with exceptional accuracy, enabling precise sorting thresholds that make the recovery of low-grade ores economically viable.
Our sorters now empowers customers with intuitive control over sorting performance. Using a single slider, they can fine-tune the balance between product purity and recovery to meet their specific economic needs, achieving optimal performance without compromise.
Developed for XRT machines
The CONTAIN™ software has been developed for TOMRA’s XRT sorters. It will be available on new models, but there will also be an upgrade package available for existing machines, providing a significant opportunity for customers already operating TOMRA XRT sorters, to substantially enhance the sorting performance where it proves to be a suitable solution.
COM TERTIARY XRT
