Hybrid AI model for estimating the canopy photosynthesis of eggplants.

Modern models for estimating canopy photosynthetic rates (Ac) can be broadly classified into two categories, namely, process-based mechanistic models and artificial intelligence (AI) models, each category having unique strengths (i.e., process-based models have generalizability to a wide range of situations, and AI models can reproduce a complex process using data without prior knowledge about the underlying mechanism). To exploit the strengths of both categories of models, a novel "hybrid" canopy photosynthesis model that combines process-based models with an AI model was proposed. In the proposed hybrid model, process-based models for single-leaf photosynthesis and image analysis first transform raw inputs (environmental data and canopy images) into the single-leaf photosynthetic rate (AL) and effective leaf area index (Lc)), after which AL and Lc are fed into an artificial neural network (ANN) model to predict Ac. The hybrid model successfully predicted the diurnal cycles of Ac of an eggplant canopy even with a small training dataset and successfully reproduced a typical Ac response to changes in the CO2 concentration outside the range of the training data. The proposed hybrid AI model can provide an effective means to estimate Ac in actual crop fields, where obtaining a large amount of training data is difficult.

Rapid movement of water and cryoprotectants in pig expanded blastocysts via channel processes: its relevance to their higher tolerance to cryopreservation.

Pig oocytes and embryos are highly sensitive to cryopreservation; however, tolerance to cryopreservation increases in embryos at the expanded blastocyst stage. This increased tolerance may be attributed to a decrease in cytoplasmic lipid droplets at this stage. We previously showed that an increase in the permeability of the plasma membrane in mouse oocytes to water and cryoprotectants, caused by the artificial expression of aquaporin 3, an aquaglyceroporin, enhanced tolerance to cryopreservation. In the present study, we investigated whether membrane permeability was also involved in the tolerance of pig embryos to cryopreservation. The permeability of oocytes and morulae to water and glycerol was low, whereas that of expanded blastocysts was high. Activation energy for permeability to water, glycerol, ethylene glycol, and dimethyl sulfoxide was markedly lower for expanded blastocysts than for oocytes. This suggests that water and these cryoprotectants move through expanded blastocysts predominantly by facilitated diffusion and through oocytes predominantly by simple diffusion. Aquaporin 3 mRNA was expressed in expanded blastocysts abundantly, but less so in oocytes. On the other hand, the permeability of expanded blastocysts to propylene glycol was as low as that of oocytes, and activation energy for its permeability was similar to that of oocytes, which suggests that propylene glycol moves through oocytes and embryos predominantly by simple diffusion. These results suggest that the higher tolerance of pig expanded blastocysts to cryopreservation is also related to high membrane permeability due to the expression of water/cryoprotectant channels, in addition to the decrease in cytoplasmic lipid droplets.