Live fish waterless transport strategy for the purpose of consumption or ornament is a novel technology, which can implement the larger volume transportation with high survival results as well as less wastewater pollution. The aim of this study was to establish an accurate survival prediction system based on the least physiological stress variations in different temperature ranges, which statistically analyzes the trend of key stress factors under the well life-supported temperatures to improve the final survival result. Furthermore, the accuracy of survival prediction can be adaptively and dynamically improved in consideration of the historical survival series in different seasons. In order to verify the practicability and performance of the system, Paralichthys olivaceus was selected as experimental subjects to carry out dynamic survival prediction experiments for over 30 hours waterless transportation, and the accuracy of the survival prediction system has verified over 97.2% in 0.5-2.5C°, which show that mean absolute error (MAE) and mean squared error (MSE) by less than 0.2 and 0.07 to produce the most accurate estimation in the comparison. The development of this survival prediction system can significantly optimize the current waterless delivery management by reducing the potential mortality and providing the managerial references for industrialization of the live fish waterless logistics.

Accurate prediction of forthcoming oxygen concentration during waterless live fish transportation plays a key role in reducing the abnormal occurrence, increasing the survival rate in delivery operations, and optimizing manufacturing costs. The most effective ambient monitoring techniques that are based on the analysis of historical process data when performing forecasting operations do not fully consider current ambient influence. This is likely lead to a greater deviation in on-line oxygen level forecasting in real situations. Therefore, it is not advisable for the system to perform early warning and on-line air adjustment in delivery. In this paper, we propose a hybrid method and its implementation system that combines a gray model (GM (1, 1)) with least squares support vector machines (LSSVM) that can be used effectively as a forecasting model to perform early warning effectively according to the dynamic changes of oxygen in a closed system. For accurately forecasting of the oxygen level, the fuzzy C-means clustering (FCM) algorithm was utilized for classification according to the flatfish’s physical features—i.e., length and weight—for more pertinent training. The performance of the gray model-particle swarm optimization-least squares support vector machines (GM-PSO-LSSVM) model was compared with the traditional modeling approaches of GM (1, 1) and LSSVM by applying it to predict on-line oxygen level, and the results showed that its predictions were more accurate than those of the LSSVM and grey model. Therefore, it is a suitable and effective method for abnormal condition forecasting and timely control in the waterless live transportation of flatfish.

Impact of climate change on crop growth is dynamic and difficult to quantify due to heterogeneity of the associated effects and their interactions within the Earth system. The main objective of this study is to establish how future climate change might affect agriculture, through an assessment of temperature and precipitation driven parameters. These include percentage number of rainy days with extreme precipitation, percentage of extreme precipitation relative to wet days, first fall frost days, last spring frost days, growing degree days, growing season length and the total precipitation. Results show modest increase in total precipitation with a slight increase in extreme precipitation, representing up to 2.2% increase by 2060 under representative concentration pathway (RCP 8.5) scenario. There would be late first fall frost days, early last spring frost days and increased growing season length by up to 2 weeks in 2060. The growing degree days are projected to increase under all scenarios for all crops, with cotton showing the largest increase of up to 37% relative to the baseline period.