From Pixels to Practice: Remote Sensing and Machine Learning Driving Agricultural Innovation

Session ID#: 281929

Session Description:
Rapid population growth, increasing pressure on natural resources, and persistent disruptions to supply chains continue to challenge global food and water availability. Recent advances in remote sensing and artificial intelligence are creating unprecedented opportunities to support the agricultural sector with timely, data‑driven insights by enabling more accurate assessments of cropland dynamics and production, often at previously unattainable spatial and temporal scales. This session invites contributions that highlight innovative datasets, analytical methods, or operational frameworks that advance our understanding of agricultural systems. Topics of interest include cropland and crop‑residue mapping; robust biomass/yield estimation across seasons and environments; multi-source data fusion; detection of crop stress, disease, or pests; evaluation of conservation or precision‑agriculture practices; uncertainty quantification and model interpretability; and scalable workflows for operational monitoring and decision support. Together, these efforts will showcase how next‑generation geospatial technologies can strengthen global food and water security in an increasingly complex and resource‑constrained world.
Index Terms:

0402 Agricultural systems [BIOGEOSCIENCES]
0452 Instruments and techniques [BIOGEOSCIENCES]
0480 Remote sensing [BIOGEOSCIENCES]
Primary Convener:  Itiya Aneece, USGS, Flagstaff, United States
Conveners:  Jyoti Jennewein, USDA, Agricultural Research Service, Sustainable Agricultural Systems Laboratory, Beltsville, United States, Alifu Haireti, Division of Geological and Planetary Sciences (GPS), California Institute of Technology (Caltech), Pasadena, United States and Adam Oliphant, USGS, Flagstaff, United States
See more of: Biogeosciences