Extreme temperature events are becoming more frequent due to global warming, and have critical effects on natural ecosystems, social and economic spheres, human production and life. Predicting changes in temperature extremes and trends under future climate scenarios helps to assess the impact of climate change accurately. Based on climate observations from 54 meteorological stations in the North China Plain and the projection data from seven general circulation models (GCMs) from the Coupled Model Intercomparison Project phase 6 (CMIP6), this paper researches nine representative extreme temperature indices under four typical climate scenarios. The aim is to reveal the temporal and spatial variations in extreme temperature indices in the North China Plain during the past (1971–2010) and the future (2061–2100). The results show that: using a support vector machine (SVM) to perform regression analysis on the multi-GCMs prediction results, the root mean square error (RMSE) and relative standard deviation (RSD) of the multi-model ensemble simulations obtained by the SVM method are lower than those of the arithmetic mean method and can better match the trend of the historical extreme temperature index; the extreme high temperature index is predicted to show a significant upward trend in the future, while the extreme low temperature index will decrease significantly; and there are significant spatial differences in the extreme temperature index in both historical and future periods, with the extreme temperature index under the high radiation forcing scenario (SSP585) showing the most considerable variation and the most significant spatial differences.

Anomaly identification is important to ensure the safe and stable operation of oil pipelines and prevent leaks. Leak identification is performed to divide abnormal samples from normal oil transfer samples in monitoring data, and it is a dichotomous problem. However, the traditional machine learning binary classification method is no longer suitable for identifying leak anomalies in complex production environments. The main problem is that leaks in production environments are very rare, and traditional methods cannot directly identify the leaking pattern with their generalizability. The recognized normal pattern lacks the ability to adapt to dynamic environmental changes and an artificial adjustment of the pump frequency, instrument calibration, and other monitoring data mutations. These are known as false anomalies, and they are difficult to distinguish from true anomalies. This results in a lower recall rate for leak anomaly identification and a higher rate of false positives. To solve this problem, this study proposes a leak anomaly recognition method based on the distinction between true and false anomalies. A one-class SVM is used to learn the normal working mode of oil pipelines, and the model is used to screen out suspected pipeline anomalies, namely, true and false anomalies. It increases the morphological difference between true and false anomaly curves by superimposing multisource data and uses similarity clustering to discover anomaly patterns that indicate leak events. The results show that the leakage anomaly recall rate is 100%, and the false anomaly exclusion rate is 83.49%. This method achieves real-time and efficient monitoring of pipeline leaking events in complex production environments, and it is practical for the application of machine learning methods in production environments.