AI Resilience Report forRemote Sensing Scientists and Technologists

Remote sensing is one of the fields where AI is being used heavily right now — but mostly to help scientists, not replace them. The integration of artificial intelligence (AI) in remote sensing and satellite image processing has significantly transformed the field, offering advanced tools for data analysis, feature extraction, and environmental monitoring. A big shift is the rise of "foundation models ^[1]" — giant AI systems trained on huge satellite datasets.

NASA and IBM's open-source Prithvi Geospatial AI foundation model was recently demonstrated aboard two in-orbit platforms, making it the first geospatial foundation model deployed in orbit. Trained on 13 years' worth of data, Prithvi can facilitate a wide variety of Earth observation tasks, including mapping flood plains, monitoring disasters, and predicting crop yields. University researchers are doing similar things — using AI to monitor croplands, track air quality and identify invasive species more efficiently and accurately via satellite and drone imagery ^[2].

This automates the repetitive image-processing tasks (which is why land cover mapping and data organization show ~60%+ automation scores), while humans still handle interpretation, system design, and validation.

Adoption is moving fast because the economic payoff is huge: satellites generate more imagery than humans could ever label manually, and AI dramatically multiplies what a small team can analyze. The ISPRS 2026 Congress program ^[3] highlights how machine learning and deep learning are being applied to automate plume detection, source attribution, and uncertainty reduction, signaling that the profession itself is embracing these tools. The job market reflects this: employers are seeking GIS professionals with AI literacy, including LLM workflows, machine learning for spatial analysis, and geospatial automation.

AI is projected to eliminate 92 million jobs globally by 2030, [but] it will simultaneously create 170 million new ones, according to the World Economic Forum's Future of Jobs Report ^[4]. Some friction remains — researchers like those at Minnesota are grappling with [AI's] broader environmental implications, and other jobs, including some in the computer, legal, business and financial, and architecture and engineering occupational groups are also potentially susceptible to AI-related impacts per the U.S. Bureau of Labor Statistics ^[5]. The encouraging takeaway: human judgment — recommending hardware, training others, and asking should we do this — remains the hardest part to automate, and that's exactly where your career can shine.