A New Method to Evaluate Gold Mineralisation-Potential Mapping Using Deep Learning and an Explainable Artificial Intelligence (XAI) Model
نویسندگان
چکیده
Geoscientists have extensively used machine learning for geological mapping and exploring the mineral prospect of a province. However, interpretation results becomes challenging due to complexity models. This study uses convolutional neural network (CNN) Shapley additive explanation (SHAP) estimate potential locations gold mineralisation in Rengali Province, tectonised mosaic volcano-sedimentary sequences juxtaposed at interface Archaean cratonic segment north Proterozoic granulite provinces Eastern Ghats Belt India. The objective is integrate multi-thematic data involving geological, geophysical, mineralogical geochemical surveys on 1:50 K scale with aim prognosticating mineralisation. available utilised during integration include aero-geophysical (aeromagnetic aerospectrometric), (national mapping), ground geophysical (gravity), satellite gravity, remote sensing (multispectral) National Geomorphology Lineament Project structural lineament maps obtained from Geological Survey India Database. CNN model has an overall accuracy 90%. SHAP values demonstrate that major contributing factors are, sequential order, antimony, clay, lead, arsenic content magnetic anomaly modelling. Geochemical pathfinders, including factors, high importance, followed by shear zones mapping. According results, central parts area, river valley, higher prospects than surrounding areas. Gold possibly associated intermediate metavolcanics along zone, which later intruded quartz veins northern part Province. work intends known occurrences respect multiple themes so can be replicated
منابع مشابه
Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching, or even exceeding, the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of ...
متن کاملBuilding Explainable Artificial Intelligence Systems
As artificial intelligence (AI) systems and behavior models in military simulations become increasingly complex, it has been difficult for users to understand the activities of computer-controlled entities. Prototype explanation systems have been added to simulators, but designers have not heeded the lessons learned from work in explaining expert system behavior. These new explanation systems a...
متن کاملExplainable Artificial Intelligence for Training and Tutoring
This paper describes an Explainable Artificial Intelligence (XAI) tool that allows entities to answer questions about their activities within a tactical simulation. We show how XAI can be used to provide more meaningful after-action reviews and discuss ongoing work to integrate an intelligent tutor into the XAI framework.
متن کاملAn Explainable Artificial Intelligence System for Small-unit Tactical Behavior
As the artificial intelligence (AI) systems in military simulations and computer games become more complex, their actions become increasingly difficult for users to understand. Expert systems for medical diagnosis have addressed this challenge though the addition of explanation generation systems that explain a system’s internal processes. This paper describes the AI architecture and associated...
متن کاملExplainable Artificial Intelligence via Bayesian Teaching
Modern machine learning methods are increasingly powerful and opaque. This opaqueness is a concern across a variety of domains in which algorithms are making important decisions that should be scrutable. The explainabilty of machine learning systems is therefore of increasing interest. We propose an explanation-byexamples approach that builds on our recent research in Bayesian teaching in which...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2022
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs14184486