Satellite-Based Environmental Monitoring: AI-Assisted Analysis for Land, Water, and Air Systems

Authors

  • Ayesha Naz Department of Meteorology, COMSATS Islamabad Author
  • Abdul Wasay Institute of Soil and Environmental Sciences, University of Agriculture, Faisalabad, Pakistan Author
  • Samsor Sherani Department of Forestry and Range Management, University of Agricultural Faisalabad, Author
  • Abdul Wahab Ul Murtaza Department of Forestry and Range Management, University of Agricultural Faisalabad, Author
  • Iqra Aslam Department of Geography, Government College University, Lahore, Author
  • Muhammad Haseeb Saleem Department of Forestry and Range Management, University of Agriculture Faisalabad Author
  • Saif ul Rehman Department of Geography. Government College University, Lahore Author
  • Muhammad Naveed Khalil National Centre of Excellence in Geology, University of Peshawar, Pakistan Author

DOI:

https://doi.org/10.63163/jpehss.v4i1.1003

Keywords:

Satellite Monitoring, Artificial Intelligence, Remote Sensing, Environmental Systemsg, Deep Learning, Vision Transformers, Precision Agriculture, Greenhouse Gas Detection, Edge Computing, Explainable AI

Abstract

The convergence of satellite technology and artificial intelligence (AI) has revolutionized

environmental monitoring, enabling real-time, high-resolution analysis of Earth's land, water, and

air systems. This paper explores the evolution from traditional remote sensing to AI-driven

paradigms, highlighting key orbital platforms such as Sentinel-5P, Landsat-8/9, and GHGSat for

data acquisition. Foundational AI methodologies, including Convolutional Neural Networks

(CNNs), Long Short-Term Memory (LSTM) networks, and Vision Transformers (ViTs), are

examined for their roles in feature extraction, time-series analysis, and global context capture.

Applications span terrestrial land cover change detection and precision agriculture; hydrospheric

water quality assessment, groundwater tracking, and cryospheric dynamics; and atmospheric

greenhouse gas detection and air quality modeling. Technological optimizations like edge

computing and image restoration address data bottlenecks, while socio-economic implications,

including Explainable AI (XAI), the AI digital divide, and environmental footprints, underscore

ethical considerations. Through a synthesis of emerging trends, the paper posits that AI-assisted

monitoring fosters proactive sustainability but risks rebound effects and inequities, urging

balanced policy frameworks for equitable planetary stewardship.

Downloads

Published

2026-03-31

Issue

Vol. 4 No. 1 (2026): Physical Education, Health and Social Sciences

Section

General Category