Currently, greenhouses are widely applied for plant growth, and environmental parameters can also be controlled in the modern greenhouse to guarantee the maximum crop yield. In order to optimally control greenhouses’ environmental parameters, one indispensable requirement is to accurately predict crop yields based on given environmental parameter settings. In addition, crop yield forecasting in greenhouses plays an important role in greenhouse farming planning and management, which allows cultivators and farmers to utilize the yield prediction results to make knowledgeable management and financial decisions. It is thus important to accurately predict the crop yield in a greenhouse considering the benefits that can be brought by accurate greenhouse crop yield prediction. In this work, we have developed a new greenhouse crop yield prediction technique, by combining two state-of-the-arts networks for temporal sequence processing—temporal convolutional network (TCN) and recurrent neural network (RNN). Comprehensive evaluations of the proposed algorithm have been made on multiple datasets obtained from multiple real greenhouse sites for tomato growing. Based on a statistical analysis of the root mean square errors (RMSEs) between the predicted and actual crop yields, it is shown that the proposed approach achieves more accurate yield prediction performance than both traditional machine learning methods and other classical deep neural networks. Moreover, the experimental study also shows that the historical yield information is the most important factor for accurately predicting future crop yields.

Sharp wave-ripples (SWRs) are population oscillatory patterns in hippocampal LFPs during deep sleep and immobility, involved in the replay of memories acquired during wakefulness. SWRs have been extensively studied, but their exact generation mechanism is still unknown. A computational model has suggested that fast perisomatic inhibition may generate the high frequency ripples (~200 Hz). Another model showed how replay of memories can be controlled by various classes of inhibitory interneurons targeting specific parts of pyramidal cells (PC) and firing at particular SWR phases. Optogenetic studies revealed new roles for interneuronal classes and rich dynamic interplays between them, shedding new light in their potential role in SWRs. Here, we integrate these findings in a conceptual model of how dendritic and somatic inhibition may collectively contribute to the SWR generation. We suggest that sharp wave excitation and basket cell (BC) recurrent inhibition synchronises BC spiking in ripple frequencies. This rhythm is imposed on bistratified cells which prevent pyramidal bursting. Axo-axonic and stratum lacunosum/moleculare interneurons are silenced by inhibitory inputs originating in the medial septum. PCs receiving rippling inhib