Multi-class imbalanced problems have attracted growing attention from the real-world classification tasks in engineering. The underlying skewed distribution of multiple classes poses difficulties for learning algorithms, which becomes more challenging when considering overlapping between classes, lack of representative data and mixed-type data. In this work, we address this problem in a data-oriented way. Motivated by a recently proposed over-sampling technique designed for numeric data sets, Mahalanobis Distance-based Over-sampling (MDO), we use this technique to capture the covariance structure of the minority class and to generate synthetic samples along the probability contours for learning algorithms. Based on MDO, we further improve the over-sampling strategy and generalize it for mixed-type data sets. The established technique, Adaptive Mahalanobis Distance-based Over-sampling (AMDO), introduces GSVD (Generalized Singular Value Decomposition) for mixed-type data, develops a partially balanced resampling scheme and optimizes the sample synthesis. Theoretical analysis is conducted to demonstrate the reasonability of AMDO. Extensive experimental testing is performed on 15 multi-class imbalanced benchmarks and two data sets for precipitation phase recognition in comparison with several state-of-the-art multi-class imbalanced learning methods. The results validate the effectiveness and robustness of our proposal.

Based on the hourly visibility data, visibility and its changes during 2010–2020 at monthly and annual time scales over 47 international airports in China are investigated, and nine artificial-intelligence-based hourly visibility prediction models are trained (hourly data in 2018–2019) and tested (hourly data in 2020) at these airports. The analyses show that the visibility of airports in eastern and central China is at a poor level all year round, and LXA (in Lhasa) has good visibility all year round. Airports in south and the northwest China have better visibility from May to October and poorer visibility from November to April. In all months, the increasing visibility mainly occurs in the central, northeast and coastal areas of China, while decreasing visibility mainly appears in the western and northern parts of China. In spring, summer and autumn, the changes difference between east and west is particularly obvious. This East–West distribution of trends is obviously different from the North–South distribution shown by the mean. For all airports, good visibility mainly occurs from 14:00–18:00 p.m. Beijing Time, while poor visibility mainly concentrates from 22:00 p.m. to 12:00 p.m. the next day, especially between 3:00–9:00 a.m. Our proposed artificial intelligence algorithm models can be reasonably used in airport visibility prediction. In particular, most algorithm models have the best results in the visibility prediction over HFE (in Hefei) and SJW (in Shijiazhuang). On the contrary, the worst forecast results appear at LXA and LHW (in Lanzhou) airports. The prediction results of airport visibility in the cold season (October–December) are better than those in the warm season (May–September). Among the algorithm models, the prediction performance of the RF-based model is the best.

An accurate, high-resolution precipitation estimation based on rain gauge and radar observations is essential in various meteorological applications. Although numerous studies have demonstrated the effectiveness of merging two information sources rather than using separate sources, approaches that simultaneously consider the local radar reflectivity, the neighborhood rain gauge observations, and the temporal information are much less common. In this paper, we present a new framework for real-time quantitative precipitation estimation (QPE). By formulating the QPE as a continuous conditional random field (CCRF) learning problem, the spatiotemporal correlations of precipitation can be explored more thoroughly. Based on the CCRF, we further improve the accuracy of the precipitation estimation by introducing geographical and temporal attention. Specifically, we first present a data-driven weighting scheme to merge the first law of geography into the proposed framework, and hence, the neighborhood sample closer to the estimated grid can receive more attention. Second, the temporal attention penalizes the similarity between two adjacent timestamps via the discrepancy of two-view estimates, which can model the local temporal consistency and tolerate some drastic changes. A sufficient evaluation is conducted on 11 rainfall processes that occurred in 2015, and the results confirm the advantage of our proposal for real-time precipitation estimation.

Based on observed minute precipitation data during Lekima influencing Zhejiang (from 2019–08-07 00:00:00 to 2019–08-12 23:55:00), the rainfall thresholds for debris flow and landslide are investigated. The rainfall intensity and duration (I-D) thresholds are I = 1247.73D^−403.44 + 19.09 and I = 142.63D^−0.58–3.37 for debris flow and landslide, respectively. Hourly meteorological data and soil data reveal that (1) the soil volume water content (SVWC) at deep soil layers (50–100 cm) fluctuated continuously during the occurrence of debris flow and landslide. At the end of the landslide period, SVWC at deep soil layers returned stable. (2) At the same soil layer, there was little difference between the upper adjacent values of SVWC in the periods of debris flow and landslide, but the lower adjacent values in the period of landslide were smaller. However, different from the distribution of soil moisture, the lower adjacent values of the soil temperature at all layers were basically the same when debris flow and landslide occurred, while the upper adjacent values were higher when landslide occurred than when debris flow occurred. (3) Compared with the whole typhoon influencing period and debris flow occurrence period, ground surface temperature and surface air temperature, soil temperature, and surface air temperature showed better correlations in landslide occurrence period. (4) Both during debris flow and landslide occurrence time, the soil temperature at all layers did not change with the change of soil depth. Soil temperature and moisture at shallow soil layers owned better correlations than at deep soil layers.

Based on second-level L-band sounding data, the vertical distribution and variation of meteorological elements at airports in 2010–2020 are investigated. At the same time, the relationships between airport visibility and meteorological elements at different potential heights are also investigated. Then, based on hourly measurements of 26 meteorological elements in 2018–2020, the hourly visibility of airports is predicted by 9 artificial intelligence algorithm models. The analyses show: (1) For the vertical changes in four meteorological elements of the airports, the negative vertical trends of temperature and relative humidity increase clearly from northwestern to southeastern China. The significant negative trend of air pressure in the vertical direction in the eastern China is greater. (2) Within about 2000 geopotential metres (gpm) from the ground, the visibility has a strong correlation with the air pressure, and most of them are negative. Within 400 gpm from the ground, airport visibility is negatively correlated with the relative humidity. At 8:00 a.m., airport visibility is positively correlated with the wind speed within 2000 gpm from the ground at most airports, while at 20:00 p.m., the positive correlation mainly appears within 400 gpm from the ground. (3) The passive aggressive regression-(PAR) and isotonic regression-(IST) based models have the worst effect on airport visibility prediction. The dispersion degree of the visibility simulation results obtained by Huber regression-(HBR) and random sample consensus regression-(RANSAC) based models is relatively consistent with the observations.