AI driven shadow model detection in agropv farms

TL;DR

This paper presents AI-based neural network methods, including CNN and GAN, for detecting shadows in agro-photovoltaic farms to improve crop growth understanding and farm management.

Contribution

It introduces the application of CNN and GAN neural networks for shadow detection in APV farms, demonstrating their effectiveness in this context.

Findings

CNN and GAN models effectively detect shadows in APV farms

Shadow detection improves understanding of microclimate impacts

Challenges include partial shadows and real-time monitoring

Abstract

Agro-photovoltaic (APV) is a growing farming practice that combines agriculture and solar photovoltaic projects within the same area. This emerging market is expected to experience significant growth in the next few years, with a projected investment of $9 billion in 2030. Identifying shadows is crucial to understanding the APV environment, as they impact plant growth, microclimate, and evapotranspiration. In this study, we use state-of-the-art CNN and GAN-based neural networks to detect shadows in agro-PV farms, demonstrating their effectiveness. However, challenges remain, including partial shadowing from moving objects and real-time monitoring. Future research should focus on developing more sophisticated neural network-based shadow detection algorithms and integrating them with control systems for APV farms. Overall, shadow detection is crucial to increase productivity and profitability while supporting the environment, soil, and farmers.