Enhancing Vegetation Mapping in Mexico through Artificial Intelligence and Remote Sensing Techniques
Mexico, recognized for its exceptional biodiversity, is home to over 58 vegetation types and nearly 30,000 documented plant species. This remarkable ecological variety is influenced by the country’s complex topography, diverse climates, and varying soil conditions. Since 1978, the National...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1131/2025/isprs-archives-XLVIII-G-2025-1131-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Mexico, recognized for its exceptional biodiversity, is home to over 58 vegetation types and nearly 30,000 documented plant species. This remarkable ecological variety is influenced by the country’s complex topography, diverse climates, and varying soil conditions. Since 1978, the National Institute of Statistics and Geography (INEGI) has been pivotal in understanding the distribution and condition of Mexico's vegetation. INEGI’s methods have progressed from traditional analogue mapping to sophisticated digital formats, utilizing satellite imagery, other ancillary geospatial data layers and advanced photointerpretation techniques.<br />The data generation process follows rigorous methodologies that are publicly accessible, and dedicated teams across Regional Directorates and State Coordination Offices oversee the mapping of nearly 2 million km<sup>2</sup> of territory with a lean workforce of just 30 personnel. This information serves as a National Interest Information, mandated for use by government entities.<br />Recent advancements have underscored the need for innovative modelling and processing capabilities. INEGI are currently exploring artificial intelligence applications, particularly the use of multilayer perceptron neural networks, to enhance vegetation and land-use detection. Robust quality assurance and control measures aligned with ISO-2859 standards are integrated. This article showcases how these initiatives leverage AI to improve data accuracy and processing efficiency, thereby revolutionizing national vegetation mapping and contributing to sustainable land management practices. By highlighting collaborative efforts and outcomes achieved, this work aims to foster a deeper understanding of ecological dynamics and resource management in Mexico. |
|---|---|
| ISSN: | 1682-1750 2194-9034 |