Remote Sensing, Artificial Intelligence, and the Internet of Things in Precision Agriculture: A Critical Review of Opportunities, Challenges, and Pathways to Sustainable Intensification
Akanksha Chaudhary
Department of Mycology and Plant Pathology, Institute of Agricultural Sciences, Banaras Hindu University, Varanasi, Uttar Pradesh-221005, India.
Viraj V. Pisal
Department of Agronomy, Mahatma Phule Krishi Vidyapeeth, Rahuri, Maharashtra-413722, India.
Jyotiish Werulkar
Faculty of Management, Dr. Vishwanath Karad MIT World Peace University, Pune, Maharashtra-411014, India.
J.A. Soochismita Priyadarshini
Department of Agricultural Meteorology, Odisha University of Agriculture and Technology, Odisha-751003, India.
Priyambada Palai
Department of Agricultural Meteorology, Odisha University of Agriculture and Technology, Odisha-751003, India.
Ashish Gupta
Department of Agricultural Statistics, The Graduate School, ICAR-IARI, New Delhi-110012, India.
Rakesh Chhalotre
The Graduate School, ICAR-IARI, New Delhi-110012, India.
Prabhakar Verma
Department of Agricultural Statistics, The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi-110012, India.
Apurva D. Fuladi
Department of Geology, S. S. E. S. A's Science College, Nagpur, M. S.-440012, India.
Ashu Sharma
College of Horticulture and Forestry Neri Hamirpur, Dr. Y S Parmar University, Himachal Pradesh-177211, India.
Seema Prajapat
Department of Agronomy, College of Agriculture, Ummedganj, Kota, Rajasthan, India.
Manju *
Department of Plant Biotechnology, SKRAU, Bikaner, Rajasthan, India.
*Author to whom correspondence should be addressed.
Abstract
Sustainable intensification requires more output from existing farmland with lower environmental costs, and digital precision agriculture is widely promoted as one of its principal instruments. Remote sensing, artificial intelligence (AI) and the Internet of Things (IoT) now generate crop, soil and microclimate data at unprecedented resolution, yet the extent to which these capabilities translate into verified agronomic, environmental and social gains remains contested. This critical narrative review examines the evidence linking the three technology families to sustainable intensification outcomes in crop production. Peer-reviewed literature published from January 2010 to September 2026 was identified through multidisciplinary, life-science, open-access and regional scholarly indexes, supplemented by citation tracking and institutional reports, and was appraised for design, validation practice, external validity and outcome relevance. The synthesis shows a persistent asymmetry between technical performance and demonstrated impact. Satellite and unmanned aerial observation reliably captures within-field and between-field variability, but its value is constrained by cloud cover, spectral saturation, scale mismatch with small fields and scarce ground truth. AI models frequently report near-perfect accuracy on curated datasets, whereas independent tests under field conditions, on new locations or in unseen seasons show marked degradation, a pattern amplified by non-spatial validation. IoT deployments are technically feasible but depend on sensor calibration, connectivity, energy supply, interoperability and cybersecurity that are seldom evaluated over multiple seasons. Field evidence for input savings is strongest for sensor-guided nitrogen management and spot spraying of herbicides, yet economic returns are variable, benefits are smaller and less stable on small farms, and efficiency gains in irrigation can be offset by expanded water use. Adoption remains skewed towards large commercial farms, while connectivity gaps, data-governance asymmetries and corporate lock-in shape who benefits. The review concludes that digital precision agriculture can contribute to sustainable intensification only conditionally, when sensing, inference and actuation are validated together against explicit sustainability metrics, embedded in on-farm experimentation and accompanied by institutional arrangements for inclusion and data stewardship.
Keywords: Digital agriculture, machine learning, site-specific crop management, variable-rate technology, nitrogen use efficiency, on-farm experimentation, smallholder farming, agricultural data governance