Answers are grounded in this paper and cite their sources.
Perspective paper discusses optimising energy and crop productivity in agrivoltaic systems, highlighting research avenues.
The application of artificial intelligence (AI) and machine learning (ML) to the optimisation of agrivoltaic systems represents a promising frontier for enhancing dual land-use efficiency. Insights from the literature identify substantial opportunities for the transfer of mature AI methodologies from renewable energy and agriculture applications to the emerging field of agrivoltaics. Despite agrivoltaic systems achieving reported Land Equivalent Ratios (LERs) of between 1.2 and 1.6—corresponding to a 20 to 60% increase in combined energy and crop productivity per unit of land—the adoption of dynamic, real-time optimisation remains limited. Key research gaps include the absence of cross-domain learning architectures, the limited integration of economic considerations within optimisation frameworks, and the lack of adaptive, multi-temporal modelling approaches. This perspective paper proposes a research roadmap for the development of next-generation AI systems capable of simultaneously optimising energy generation and agricultural productivity, thereby supporting sustainable land-use transitions in integrated agri-energy landscapes.
No takes yet. Share an insight, caveat, or question.
Monasterio et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: