India’s CSIR-National Environmental Engineering Research Institute (CSIR-NEERI) has won the First Prize at the National Hackathon on R&D-2026 for a proposal that uses artificial intelligence, machine learning and Geographic Information System (GIS) technology to improve tree assessment.
The award-winning proposal, titled “Development of an AI- and ML-Based GIS Model for Tree Enumeration, Species Identification and Tree Height Estimation,” was recognised under Problem Statement 2 of the national-level hackathon organised by Central Mine Planning & Design Institute Limited (CMPDI), Ranchi, a subsidiary of Coal India Limited under the Ministry of Coal.
Editorial Insight
Key Highlights
Important points readers should notice.
Issue/Event: CSIR-NEERI won First Prize at the National Hackathon on R&D-2026 for an AI-based tree assessment proposal.
Location: India.
Authority/Organisation: CSIR-NEERI, CMPDI, Coal India Limited and the Ministry of Coal.
Action Taken: Researchers presented an AI, machine learning and GIS-based proposal for automated tree enumeration, species identification and tree-height estimation.
- Impact: The proposed approach could support environmental monitoring, forest assessment and sustainable mining practices.
The award was presented by Union Minister of State for Coal and Mines Satish Chandra Dubey during the Star Rating Award Ceremony for Coal and Lignite Mines held in Raipur on November 2, 2026. The achievement was officially announced by the Ministry of Science and Technology on November 5.
The CSIR-NEERI team was led by Dr. Asheesh Sharma, Lead Principal Investigator, and Dr. Kanchan Kumari, Co-Principal Investigator. The team also included AcSIR PhD student Mandeep Poonia and project associates working on the research proposal.
The hackathon, organised around the theme “NextGen AI for Smart Mining”, received 70 proposals. CSIR-NEERI’s proposal was shortlisted for presentation and selected for the First Prize because of its potential application in the coal sector.
Editorial Analysis
Why This Matters
Environmental assessment requires reliable information about vegetation, tree populations and local ecosystems. Collecting this information manually across large or difficult-to-access areas can be time-consuming. An AI- and GIS-based approach could help streamline parts of this process by supporting automated analysis of tree numbers, species and height. For the mining sector, improved vegetation assessment could contribute to environmental planning and monitoring. It may also help researchers and institutions develop more systematic methods for studying ecosystems around industrial areas. The award is significant because it demonstrates how Indian research institutions are exploring applications of AI beyond conventional digital services, including environmental protection and resource management.
The proposed model combines AI, machine learning and GIS-based analysis to support automated tree enumeration, identification of tree species and estimation of tree height. Such capabilities could help improve the collection and analysis of environmental data in areas where mining and other industrial activities require ecological assessment.
Tree enumeration and species identification are important components of environmental monitoring. Reliable information about tree numbers, species composition and height can support forest assessment, biodiversity monitoring and planning for sustainable land management.
The proposed technology could also be relevant to mining-related environmental assessments, where information about vegetation and surrounding ecosystems can help authorities and organisations evaluate environmental conditions.
However, the award recognises the research proposal and its potential applications. It does not establish that the model has already been deployed across mining areas or that its performance has been validated at nationwide scale.
The recognition highlights the growing role of Indian scientific institutions in applying emerging technologies to environmental monitoring and sustainable industrial development.
