One of the six major copper companies in the world and one of the largest deposits in Chile needs to advance in the automation of its processes. Through an analysis carried out with geologists, systems engineers and data scientists, the exact definition of the problem was reached: to assist geologists with artificial intelligence during geotechnical mapping.
The process of drilling in mining consists of obtaining a soil sample by diamond drilling. These samples, which easily reach thousands of feet, are placed in trays intended for this purpose, tabulated and high-resolution photographs are taken. The geologist visually detects and counts fractures, classifying them as natural or induced, depending on whether they are real fractures existing in the earth layers or were caused by drilling or moving the samples.
Mototech received a set of images pertaining to approximately 3000 meters of drill holes. The development team designed and provided a team of geologists with a tool for labeling fractures and classifying them as induced or natural.
Our data scientists selected semantic segmentation algorithms for image processing and model training with the previously labeled data.
CRISP-DM methodology was used and at each completed iteration benchmarking was performed with different experts (geologists) to feed back the model with new training.
Once the iterations of improvements on the selected algorithms were completed, fracture detection tests were performed and we obtained a 90% success rate.
Geologists have a visual tool that preloads (in less than a second) all the fractures detected in an image and their task is reduced to verify this information in an agile and efficient way.
In addition to the reduction of analysis time, the introduction of the prototype reduced the seniority level required for this task and collaborated in the process of unification of criteria for fracture selection.
Deep Learning – Semantic Segmentation