{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2998"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2998","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"A reinforcement learning-based approach for adaptive real-time sensor data denoising in mining operations","abstract":"The mining industry has traditionally relied on geostatistical models for estimating and managing mineral resources. In modern mining operations, real-time updates to these models are critical, as sensor data plays a vital role in characterizing deposit properties. However, noise often affects sensor measurements, compromising the accuracy and reliability of resource models. This study presents a novel reinforcement learning (RL) framework designed to dynamically denoise sensor readings and improve resource model updates. The methodology begins by reviewing current approaches to integrating sensor data into geostatistical models, highlighting their vulnerability to noise. The proposed framework leverages a Deep Deterministic Policy Gradient (DDPG) algorithm with a recurrent neural network (RNN) agent. This self-learning system sequentially processes noisy sensor data, using state representations that incorporate noise characteristics, spatial locations of sensor data, and uncertainty metrics derived from Monte Carlo (MC) Dropout. The RNN-based actor network generates actions to iteratively denoise the sensor value, while the critic network evaluates the denoising performance to optimize the process. The reward function is designed to prioritize the agent's proximity to the clean sensor value, minimize uncertainty, and promote exploration in high-variance scenarios. Training involves experience replay and interaction across multiple episodes, enabling the agent to learn robust denoising strategies. Experimental validation using a public dataset demonstrates improvements in signal quality and model reliability. By integrating this RL-based denoising algorithm into geostatistical resource model updating frameworks enables more robust tracking of mineral quality variations and enhances decision-making during mining operations. This approach offers a scalable solution for real-time data processing, with potential applications in other domains requiring dynamic sensor data refinement.","abstract_html":"The mining industry has traditionally relied on geostatistical models for estimating and managing mineral resources. In modern mining operations, real-time updates to these models are critical, as sensor data plays a vital role in characterizing deposit properties. However, noise often affects sensor measurements, compromising the accuracy and reliability of resource models. This study presents a novel reinforcement learning (RL) framework designed to dynamically denoise sensor readings and improve resource model updates. The methodology begins by reviewing current approaches to integrating sensor data into geostatistical models, highlighting their vulnerability to noise. The proposed framework leverages a Deep Deterministic Policy Gradient (DDPG) algorithm with a recurrent neural network (RNN) agent. This self-learning system sequentially processes noisy sensor data, using state representations that incorporate noise characteristics, spatial locations of sensor data, and uncertainty metrics derived from Monte Carlo (MC) Dropout. The RNN-based actor network generates actions to iteratively denoise the sensor value, while the critic network evaluates the denoising performance to optimize the process. The reward function is designed to prioritize the agent&#x27;s proximity to the clean sensor value, minimize uncertainty, and promote exploration in high-variance scenarios. Training involves experience replay and interaction across multiple episodes, enabling the agent to learn robust denoising strategies. Experimental validation using a public dataset demonstrates improvements in signal quality and model reliability. By integrating this RL-based denoising algorithm into geostatistical resource model updating frameworks enables more robust tracking of mineral quality variations and enhances decision-making during mining operations. This approach offers a scalable solution for real-time data processing, with potential applications in other domains requiring dynamic sensor data refinement.","abstract_has_math":false,"creators":["Sanchez Aguilar, Jhuleyssy Liesseth"],"institution":null,"degree_name":"Master of Science in Geological Engineering (MS)","degree_level":"Campus Access Master's Thesis","degree_discipline":"Department of Geological and Mining Engineering and Sciences","degree_department":null,"school":null,"contributors":["Snehamoy Chatterjee"],"advisors":[],"committee_chairs":[],"committee_members":["Xiang Li","Ashish Kumar"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:19:12Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1864"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1864","href":"https://digitalcommons.mtu.edu/etdr/1864","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1864","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1864","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2998","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Snehamoy Chatterjee"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Xiang Li","Ashish Kumar"]},{"key":"dc:creator","label":"Author","values":["Sanchez Aguilar, Jhuleyssy Liesseth"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-12-03T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Geological and Mining Engineering and Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Campus Access Master's Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Geological Engineering (MS)"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1864","https://digitalcommons.mtu.edu/etdr/1864"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The mining industry has traditionally relied on geostatistical models for estimating and managing mineral resources. In modern mining operations, real-time updates to these models are critical, as sensor data plays a vital role in characterizing deposit properties. However, noise often affects sensor measurements, compromising the accuracy and reliability of resource models. This study presents a novel reinforcement learning (RL) framework designed to dynamically denoise sensor readings and improve resource model updates. The methodology begins by reviewing current approaches to integrating sensor data into geostatistical models, highlighting their vulnerability to noise. The proposed framework leverages a Deep Deterministic Policy Gradient (DDPG) algorithm with a recurrent neural network (RNN) agent. This self-learning system sequentially processes noisy sensor data, using state representations that incorporate noise characteristics, spatial locations of sensor data, and uncertainty metrics derived from Monte Carlo (MC) Dropout. The RNN-based actor network generates actions to iteratively denoise the sensor value, while the critic network evaluates the denoising performance to optimize the process. The reward function is designed to prioritize the agent's proximity to the clean sensor value, minimize uncertainty, and promote exploration in high-variance scenarios. Training involves experience replay and interaction across multiple episodes, enabling the agent to learn robust denoising strategies. Experimental validation using a public dataset demonstrates improvements in signal quality and model reliability. By integrating this RL-based denoising algorithm into geostatistical resource model updating frameworks enables more robust tracking of mineral quality variations and enhances decision-making during mining operations. This approach offers a scalable solution for real-time data processing, with potential applications in other domains requiring dynamic sensor data refinement."]},{"key":"dc:title","label":"Title","values":["A reinforcement learning-based approach for adaptive real-time sensor data denoising in mining operations"]}]}],"canonical_facts":{"dc:contributor":["Snehamoy Chatterjee"],"dc:contributor.committeemember":["Xiang Li","Ashish Kumar"],"dc:creator":["Sanchez Aguilar, Jhuleyssy Liesseth"],"dc:date.available":["2025-12-03T08:00:00Z"],"dc:date.created":["2024-01-01T08:00:00Z"],"dc:description.abstract":["The mining industry has traditionally relied on geostatistical models for estimating and managing mineral resources. In modern mining operations, real-time updates to these models are critical, as sensor data plays a vital role in characterizing deposit properties. However, noise often affects sensor measurements, compromising the accuracy and reliability of resource models. This study presents a novel reinforcement learning (RL) framework designed to dynamically denoise sensor readings and improve resource model updates. The methodology begins by reviewing current approaches to integrating sensor data into geostatistical models, highlighting their vulnerability to noise. The proposed framework leverages a Deep Deterministic Policy Gradient (DDPG) algorithm with a recurrent neural network (RNN) agent. This self-learning system sequentially processes noisy sensor data, using state representations that incorporate noise characteristics, spatial locations of sensor data, and uncertainty metrics derived from Monte Carlo (MC) Dropout. The RNN-based actor network generates actions to iteratively denoise the sensor value, while the critic network evaluates the denoising performance to optimize the process. The reward function is designed to prioritize the agent's proximity to the clean sensor value, minimize uncertainty, and promote exploration in high-variance scenarios. Training involves experience replay and interaction across multiple episodes, enabling the agent to learn robust denoising strategies. Experimental validation using a public dataset demonstrates improvements in signal quality and model reliability. By integrating this RL-based denoising algorithm into geostatistical resource model updating frameworks enables more robust tracking of mineral quality variations and enhances decision-making during mining operations. This approach offers a scalable solution for real-time data processing, with potential applications in other domains requiring dynamic sensor data refinement."],"dc:identifier":["10.37099/mtu.dc.etdr/1864","https://digitalcommons.mtu.edu/etdr/1864"],"dc:title":["A reinforcement learning-based approach for adaptive real-time sensor data denoising in mining operations"],"thesis:degree_discipline":["Department of Geological and Mining Engineering and Sciences"],"thesis:degree_level":["Campus Access Master's Thesis"],"thesis:degree_name":["Master of Science in Geological Engineering (MS)"]},"updated_at":"2026-11-19T08:19:12Z"}