Abstract: A neural network is utilized to improve the resolution of subsurface inversion. The neural network leverages posterior distribution of samples and adds high frequency components to the inversion by utilizing the data in both the time domain and the frequency domain. The improved resolution of the subsurface inversion enables more accurate prediction of subsurface characteristics (e.g., reservoir architecture).

Abstract: A method for predicting the quality and shelf life of fruits or vegetables includes: recording ambient temperatures of the fruits or vegetables continuously using a temperature recorder from the beginning of plucking the fruits or vegetables and throughout entire supply chain including harvesting, grading, storage, transport and shelf period, determining an effective accumulated temperature value of the fruits during the entire supply chain, and predicting marketable fruit rate and nutritional quality of the fruits based on the effective accumulated temperature value. The marketable fruit rate, firmness and vitamin C content negatively correlate with the accumulated temperature value, and thus it is possible to predict the marketable fruit rate and storage quality of fruits based on the effective accumulated temperature values of the fruits or vegetables during the post-harvest storage and shelf period.