Based on the daily temperature data from 26 meteorological stations in the Minjiang River Basin, for 1961 to 2016, the temporal trend and spatial distribution of extreme temperature in this region were analyzed using 16 extreme temperature indices. The results show that in terms of time variation, determined using linear trend analysis and a Mann–Kendall trend test, the warm and day indices mainly show an upward trend while the cold and night indices mainly show a downward trend in the entire basin. Among them, FD0, TN10, and CSDI significantly decrease at −1.3, −2.9, and −1.1 d/10a, respectively. TN90, TX90, SU25, and TR20 significantly increase at 3.0, 2.6, 2.1, and 2.2 d/10a, respectively. The crop growth period in the basin showed a significant increasing trend at 1.4 days/decade, while the diurnal temperature range showed a nonsignificant increasing trend at 0.03 days/decade. On comparing the change range of each index, it was found that the change range of the warm index is greater than that of the cold index, while the change range of the day index is smaller than that of the night index; thus, the change trends of the maximum and minimum temperatures in the whole basin are not obvious. Analysis of the changing trend at each station showed that the relative index of the extreme temperature in the basin has good climatic consistency in terms of spatial distribution. The distributions of the absolute and extreme indices are not uniform, which is consistent with the change in elevation in the basin. Further, the diurnal temperature range in the upper reaches of the basin is greater than that in the middle and lower reaches. However, because of the more obvious upward trends of the day and warm indices in the middle and lower reaches, and the more obvious downward trends of the night and cold indices in the upper reaches, the daily temperature differences in the upper, middle, and lower reaches of the Minjiang River Basin tend to be consistent. Therefore, the precipitation in the Minjiang River Basin shows a significant decreasing trend; thus, the basin shows a trend of drying and warming.

The contradiction between increasing demand and current supply has affected the healthy development of industry. Investigating the key influence factors of industrial water use change has important practical significance for water resource management. In this study, the authors propose the vector autoregression model to analyze the dynamic influences of industrial development, technological progress, and environmental protection on industrial water use change, and take Jiangsu Province, China as a case study. Results show that each of the factors had different effects during 2001–2015, in which industrial development was the greatest contributor to the change of industrial water use and showed a positive effect in the forecast period; technological progress played a major role in reducing industrial water use, but the negative effect weakened periodically over time; environmental protection also had a positive influence in the early forecast period, and then showed a marginal effect with time. Results of this study could assist the relevant authorities to formulate appropriate industrial development planning and water saving policies, and to reasonably control the industrial water demand.

Driven by the rapid advancement of Unmanned Aerial Vehicle (UAV) technology, the field of UAV object tracking has witnessed significant progress. This study introduces an innovative single-stream UAV tracking architecture, dubbed NT-Track, which is dedicated to enhancing the efficiency and accuracy of real-time tracking tasks. Addressing the shortcomings of existing tracking systems in capturing temporal relationships between consecutive frames, NT-Track meticulously analyzes the positional changes in targets across frames and leverages the similarity of the surrounding areas to extract feature information. Furthermore, our method integrates spatial and temporal information seamlessly into a unified framework through the introduction of a temporal feature fusion technique, thereby bolstering the overall performance of the model. NT-Track also incorporates a spatial neighborhood feature extraction module, which focuses on identifying and extracting features within the neighborhood of the target in each frame, ensuring continuous focus on the target during inter-frame processing. By employing an improved Transformer backbone network, our approach effectively integrates spatio-temporal information, enhancing the accuracy and robustness of tracking. Our experimental results on several challenging benchmark datasets demonstrate that NT-Track surpasses existing lightweight and deep learning trackers in terms of precision and success rate. It is noteworthy that, on the VisDrone2018 benchmark, NT-Track achieved a precision rate of 90% for the first time, an accomplishment that not only showcases its exceptional performance in complex environments, but also confirms its potential and effectiveness in practical applications.