Spatio-temporal characterization of crop growth with multi-category data based on deep learning

Monitoring plant growth is critical for sustainable agriculture. Traditionally, this complex analysis has been done manually as a trial and error or by growers' perception. Encouraged by the recent advances in precision agriculture and deep learning, we sought further improvements to facilitate the efficient use of resources and avoid losses caused by internal or external conditions that affect the growth process. In this work, we proposed a learnable approach based on deep learning techniques to understand the influence of these factors and automatically determine the appropriate conditions of crop growth in the spatio-temporal domain using multi-category data. To demonstrate the performance of our research, we collected data from various sensors installed in controlled tomato greenhouse environments in South Korea. Our model enables plant growth prediction based on the measured variables and formalizes a systematic and learnable way to analyze the growing conditions of crops by combining spatio-temporal characterization of multi-category data with existing deep learning-based research. The result of this research could potentially help farmers and researchers to understand the changes in the behavior of plants and thus achieve maximum productivity and avoid losses caused during the growth process.