Abrupt changes in environmental temperature, wind and humidity can lead to great threats to human life safety. The Gansu marathon disaster of China highlights the importance of early warning of hypothermia from extremely low apparent temperature (AT). Here a deep convolutional neural network model together with a statistical downscaling framework is developed to forecast environmental factors for 1 to 12 h in advance to evaluate the effectiveness of deep learning for AT prediction at 1 km resolution. The experiments use data for temperature, wind speed and relative humidity in ERA-5 and the results show that the developed deep learning model can predict the upcoming extreme low temperature AT event in the Gansu marathon region several hours in advance with better accuracy than climatological and persistence forecasting methods. The hypothermia time estimated by the deep learning method with a heat loss model agrees well with the observed estimation at 3-hour lead. Therefore, the developed deep learning forecasting method is effective for short-term AT prediction and hypothermia warnings at local areas.

Lettuce (Lactuca sativa L.) is the main leafy vegetable grown in Brazil. Its productivity and quality are limited by the growing season, the nearby environment and the type of cultivar adopted. The objective of this work was to verify at different times of the year the best planting environment for lettuce cultivation in a semi-humid tropical climate. For this purpose, an experiment was set up in three different seasons (October–November 2014, January–March, May–July 2015). The experimental design was randomized blocks, in a 3 × 3 × 2 factorial arrangement, consisting of three seasons, three cultivars (cvs. Vera^®, Tainá^® and Rafaela^®) and two growing environments (low tunnel with beds protected with mulching consisting of soil protection with plastic fabric covering, and beds without protection or conventional cultivation) and four replicates per treatment. Plant biomass, stem length, head diameter, number of leaves per head and crop productivity were evaluated as response parameters. The results showed that the May–July period favored biomass production, head diameter and productivity. Despite the similarity between varieties, the variety Vera^® is more productive in biomass, number of leaves per head, stem length and productivity. The low tunnel planting system with mulching is adequate under the conditions evaluated for lettuce cultivation. This system in the May–July period favors a superior development in the characteristics biomass, head diameter and productivity, if compared to conventional cultivation during the October–November period.

In this paper, a new compound health drink of aloe and balsam pear was developed by using high-quality aloe and balsam pear as main raw materials and white granulated sugar and citric acid as auxiliary materials. The effects of the addition of aloe juice, balsam pear juice, white granulated sugar and citric acid on the sensory quality of the beverage were investigated and analyzed. On this basis, the orthogonal test was conducted to determine the best formula for the beverage. The results showed that the order of the factors affecting the quality of the finished product was the addition of aloe juice > white granulated sugar > citric acid > balsam pear juice; the optimal formula is 24% aloe juice, 10% balsam pear juice, 7% white granulated sugar and 0.09% citric acid and the resulting beverage was bright in color, sweet and sour with good flavor, and its physical, chemical and health indicators meet the national standards.

The objective of this study was to evaluate the growth of four lettuce cultivars in Southern Piauí to recommend the best ones for the region. The experiment was conducted in a greenhouse with randomized blocks, with evaluation in subdivided time plots, evaluated in six seasons (20, 24, 28, 32, 36, 40 days after sowing—DAS) and with treatments corresponding to four cultivars (Americana Rafaela^®, Grand Rapids TBR^®, Crespa Repolhuda^® and Repolhuda Todo ano^®) with five repetitions. Leaf area, number of leaves, collar diameter, aboveground fresh mass, aboveground dry mass, root dry mass and total and the physiological indices of growth analysis were evaluated. The lettuce cultivars interfered significantly in the studied parameters, being that Americana Rafaela^® and Repolhuda todo ano^®, in the conditions that they were submitted, presented better performances and bigger morphophysiological indexes, cultivated in pot. The cultivars Americana Rafaela^® and Repolhuda todo ano^® can be produced under the conditions of the south of Piauí.

The temporomandibular joint (TMJ) is considered a bicondylar diarthrosis type joint. Imaging evaluation is a fundamental part of its assessment, which should include both bony and soft tissue characteristics and the relationship between them. Magnetic resonance imaging (MRI) represents the gold standard for the study of soft tissues; however, up to now, its main application continues to be the visualization of the articular disc. For this reason, the present article aimed to point out the information available in the literature regarding the visualization of the joint capsule in MRI and to evaluate it as an independent structure.

The micro staring hyperspectral imager can simultaneously acquire two spatial and one spectral images, and only record the external orientation elements of the entire hyperspectral image rather than the external orientation elements of each frame of the image, which avoids the geometric instability during scanning, effectively solves the problem of large geometric deformation of the small line scanning hyperspectral imager, and is suitable for the small UAV load platform with unstable attitude. At present, most of the research focuses on the radio-metric correction method of line scan hyperspectral imager. The application time of staring hyperspectral imager is short, and there is no mature data processing re-search at home and abroad, which hinders the application of UAV micro staring hyperspectral imaging system. In this paper, the calibration method of the linearity and variability of the radiation response of the micro staring hyperspectral imager on the UAV is studied, and the effectiveness of this method is quantitatively evaluated. The results show that the hyperspectral image has obvious vignetting effect and strip phenomenon before the correction of radiation response variability. After the correction, the radiation response variation coefficient of pixels in different bands decreases significantly, and the vignetting effect and image strip decrease significantly. In this paper, a multi-target radiometric calibration method is proposed, and the accuracy of radiometric calibration is verified by comparing the calibrated hyperspectral image spectrum with the measured ground object spectrum of the ground spectrometer. The results show that the calibration results of the multi-target radiometric calibration method show better results, especially for the near-infrared band, and the difference with the surface reflectance measured by the spectrometer is small.