Artificial intelligence (AI) and its subfields-machine learning (ML), deep learning (DL), and data-driven analytics - are transforming environmental science by enabling large-scale monitoring, improved forecasting, decision support, and resource optimization. This paper reviews major application areas where AI has shown measurable impact: remote sensing and land-cover mapping, biodiversity monitoring and species distribution modeling, climate and extreme-event forecasting, air and water quality assessment, disaster risk reduction, sustainable energy management, and agriculture. We summaries representative methods, highlight case studies, discuss limitations (data quality, bias, interpretability, energy footprint), and outline research priorities for responsible, high-impact AI in environmental science. Key references and recent reviews are cited to orient readers to the current literature and practical deployments.