The overall goal of this project is to develop an automated method for identifying surface hazards identified asanomalies in reclaimed mine lands using an unmanned aerial vehicle (UAV)

Active Cooperative Agreement Awarded

Award ID
S26AC00095
Recipient
Awarding agency
Obligated
$199,551

Award facts

Completion date 9% complete
Place of performance
West Virginia, USA

Award details come from USAspending.gov.

About this award

The Department of the Interior Office of Surface Mining Reclamation and Enforcement awarded West Virginia University Research Corporation $199,551 on September 14, 2026, under Cooperative Agreement S26AC00095, funded through the Science and Technology Projects Related to Coal Mining and Reclamation program (CFDA 15.255). The recipient will develop an automated method for detecting, localizing, and quantifying surface anomalies on reclaimed mine lands using unmanned aerial vehicle (UAV) imagery and machine learning. The targeted anomalies are sinkholes, seeps, slope sloughs and bulges, tension cracks (linear anomalies), and discontinuities in the ground profile, which the source identifies as indicators of latent geotechnical hazards. The award also funds a prototype that uses machine learning and deep learning to generate reports from UAV imagery, structured to conform to mine field inspection reports and Emergency Action Plan (EAP) notification priority. The recipient will prepare UAV data outputs and discuss report format and content with regulatory agencies. The period of performance ends August 31, 2028, and work is performed in West Virginia. The program funds science and technology projects that develop and demonstrate improved technologies for public safety and environmental issues related to coal mining and reclamation, and its funding is discretionary and subject to congressional appropriations.

Description

These anomalies include sinkholes, seeps, slope sloughs and bulges, tension cracks (linear anomalies), and discontinuities in the ground profilewhich are indicators of latent geotechnical hazards. This project directly aligns with the objective mentioned inthe nofo document in enhancing the protection of the public and environment associated with surface coal mining by leveraging machine learning (ML) tools to detect, localize, and quantify mining-related time-variableparameters using aerial imagery. The primary mining impacts consideredsinkholes and seep formationsare often imperceptible to the human eye or require extensive on-site inspections. To address this, the team will employcomputer vision techniques on aerial imagery, combined with advanced ML algorithms, to automatically identify, localize, and quantify these features. The ML models, driven by artificial intelligence (AI), will process UAV collectedaerial imagery, enabling automation of the proposed detection and analysis tasks. We will detect, identify, locate, and experimentally quantify surface anomaliessuch as seeps, slope sloughs and bulges, tensioncracks (linear anomalies), and discontinuities in the ground profile discontinuities. We will also develop aprototype for automated report generation by processing UAV-collected imagery with machine learning (ML) and deep learning (DL) techniques to be able to develop a response approach conforming to the mines field inspection reports and emergency action plan (EAP) notification priority. We will prepare UAV collected data output and discuss with regulatory agencies on report format and content. Our design strategy offers a scalable and cost effective solution for anomaly detection, localization, and quantification in reclaimed and active mine landfacilities. By automating inspection tasks, this approach ensures efficiency, speed, and objectivity, enhancingthe robustness of mine site monitoring.

Quick answers

Who received award S26AC00095?

S26AC00095 was awarded to West Virginia University Research Corporation by Office of Surface Mining Reclamation and Enforcement (Department of the Interior) on September 14, 2026.

How much is award S26AC00095 worth?

$199,551 has been obligated on S26AC00095.

On GovTribe

See this award's full record

  • Every transaction and subaward
  • The recipient's other awards and teaming partners
  • Similar grant awards
  • Ask GovTribe AI about this award