Abstract: Perishable products, such as food items or biological samples, often require specific temperature control to prolong their shelf life or maintain their integrity during storage and transportation. Supercooling, achieved by subjecting the products to pulsed electric fields, can effectively reduce their temperature while preserving their quality. The present disclosure addresses the various drawbacks in the related art by providing a method and system for selectively applying pulsed electric fields to perishable products using a plurality of electrodes. The method includes supplying power to different combinations of electrodes positioned within a container housing the perishable products, obtaining measurement data for each combination, selecting the combination based on the obtained measurement data, and applying a pulsed electric field between the selected electrodes to cool the perishable products.

Abstract: Machine learning based forest management is disclosed. A set of input data related to a forest stand is accessed. A forest management plan defining at least one forest management activity for the forest stand is determined based on the accessed set of input data and at least one forest management preference. The determining of the forest management plan for the forest stand is performed by applying a parameterized policy to the accessed set of input data. The parameterized policy has been trained via a machine learning process using a forest development related simulation model.