The coupling and coordination relationship between ecology and the economy in the Yellow River Basin is a hot topic in sustainable development research. Said research has important guiding significance for the ecological security and comprehensive development of the Yellow River Basin. Taking the Yellow River Basin as the object of our study, based on the data of the economy, energy consumption data, ecology data and water resources data, we construct an indicator system of the economic development and ecological status of the Yellow River Basin and use the principal component analysis method to calculate the economic development and ecological status index. Then, we use the evaluation method, the coupling degree model and the coupling coordination degree model to analyze the time and space evolution trends of economic development and ecological state, coupling degree and coupling coordination degree. The results show that: (1) From 2000 to 2018, the economic development index of the Yellow River Basin rose steadily; the ecological status index showed a slow rise and then a downward trend. (2) The degree of coupling between economic development and ecological state has been considered as intensity coupling after 2005. The coupling trend slowly increased and then decreased, indicating that the interaction effect between the economy and ecology was first significantly enhanced and then slowly weakened. (3) The degree of coupling coordination increased from 0.2994 to 0.6266 and then decreased to 0.5917, reflecting the continuous improvement of the relationship between the regional economy and the ecological environment and the trend toward coordination. From 2015 to 2018, due to the gradual increase in the difference between economic development and ecological conditions, the coupling and coordination between the two decreased. Studies have shown that ecological construction and protection should be strengthened to ease the contradiction between the economy and ecology and achieve coordinated development.

In recent years, alternating periods of floods and droughts, possibly related to climate change and/or human activity, have occurred in the Liao River Basin of China. To monitor and gain a deep understanding of the frequency and severity of the hydro-meteorological extreme events in the Liao River Basin in the past 30 years, the total storage deficit index (TSDI) is established by the Gravity Recovery and Climate Experiment (GRACE)-based terrestrial water storage anomalies (TWSAs) and the general regression neural network (GRNN)-predicted TWSA. Results indicate that the GRNN model trained with GRACE-based TWSA, model-simulated soil moisture, and precipitation observations was optimal, and the correlation coefficient and the root mean square error (RMSE) of the predicted TWSA and GRACE TWSA for the testing period equal 0.90 and 18 mm, respectively. The drought and flood conditions monitored by the TSDI were consistent with those of previous studies and records. The extreme climate events could indirectly reflect the status of the regional hydrological cycle. By monitoring the extreme climate events in the study area with TSDI, which was based on the TWSA of GRACE and GRNN, the decision of water resource management in the Liao River Basin could be made reasonably.

The leakage of underground natural gas has a negative impact on the environment and safety. Trace amounts of gas leak concentration cannot reach the threshold for direct detection. The low concentration of natural gas can cause changes in surface vegetation, so remote sensing can be used to detect micro-leakage indirectly. This study used infrared thermal imaging combined with deep learning methods to detect natural gas micro-leakage areas and revealed the different canopy temperature characteristics of four vegetation varieties (grass, soybean, corn and wheat) under natural gas stress from 2017 to 2019. The correlation analysis between natural gas concentration and canopy temperature showed that the canopy temperature of vegetation increased under gas stress. A GoogLeNet model with Bilinear pooling (GLNB) was proposed for the classification of different vegetation varieties under natural gas micro-leakage stress. Further, transfer learning is used to improve the model training process and classification efficiency. The proposed methods achieved 95.33% average accuracy, 95.02% average recall and 95.52% average specificity of stress classification for four vegetation varieties. Finally, based on Grad-Cam and the quasi-circular spatial distribution rules of gas stressed areas, the range of natural gas micro-leakage stress areas under different vegetation and stress durations was detected. Taken together, this study demonstrated the potential of using thermal infrared imaging and deep learning in identifying gas-stressed vegetation, which was of great value for detecting the location of natural gas micro-leakage.