The construction of an interval prediction model capable of explaining deformation uncertainties is crucial for the long-term safe operation of dams. High effective coverage and narrow interval coverage widths are two key benchmarks to ensure that the prediction interval (PI) can accurately quantify deformation uncertainties. The vast majority of existing models neglect to control the interval coverage width, and overly wide PIs can cause decision confusion when operators are developing safety plans for hydraulic structures. To address this problem, this paper proposes a novel interval prediction model combining bidirectional long-short-term memory network (Bi-LSTM) and split conformal quantile prediction (SCQP) for dam deformation prediction. The model uses Bi-LSTM as a benchmark regressor to extract and explain the nonlinear feature of dam deformation in the continuous time domain. SCQP is used to quantify the uncertainties in dam deformation prediction to ensure that the constructed PI can achieve high effective coverage while further improving the accuracy of the quantification of deformation uncertainties. The effectiveness of the proposed model is validated using deformation monitoring data collected from an arch dam in China. The results show that the average prediction interval effective coverage (PICP) of the proposed model is as high as 0.951 while the mean prediction interval width (MPIW) and coverage width-based criterion (CWC) are both only 5.815 mm. Compared with other models, the proposed method can construct higher-quality PIs, thus providing a better service for the safety assessment of dams.

AI-based multi-hazard susceptibility mapping has become an important approach for identifying slope-instability hazards over large areas. However, in multi-hazard modeling, negative samples do not have a consistent stable meaning across hazard types: a background unit that is stable for one hazard may correspond to a potentially susceptible environment for another. Existing studies mainly focus on model optimization and accuracy improvement, but pay limited attention to task-level label confusion and background-sample mismatch caused by this issue. To address this gap, this study proposes a task-specific negative sample selection method based on the feature-space distribution of hazard-specific positive samples. Specifically, for each hazard type, the method uses its positive-sample centroid as a reference to rank the shared candidate background pool by feature-space distance. Rather than selecting only hard or easy negatives, it combines hard negatives closer to the centroid, easy negatives farther from it, and randomly supplemented background units to improve diversity. Taking the Minjiang River Basin in southeastern coastal China as the study area, the proposed method was compared with five benchmark strategies—random sampling, easy negative sampling, hard negative sampling, outside-buffer sampling, and buffer-ring sampling—using random forest (RF), boosted regression tree (BRT), multilayer perceptron (MLP), support vector machine (SVM), and logistic regression (LR). The results show that the dataset constructed using the proposed method improves the overall classification performance of the models, with average improvements of 14.47% and 12.25% in AUC and F1-score, respectively. The corresponding susceptibility maps also show the highest spatial screening efficiency, with the top 10% susceptible areas capturing 39.26% of historical hazard events, and only 27.06% of slope units were required to cover 80% of the hazards. In addition, this study further discusses the influence of hazard-specific adaptability on the feature-space distribution of negative samples, as well as the relationships among negative-sample selection strategies, classification performance, and study area-wide susceptibility-map quality. This study provides a new method for constructing reliable negative samples in regional multi-hazard susceptibility mapping of slope-instability hazards.

Long-term chlorophyll-a (Chl-a) phenology and recurrent high-Chl-a conditions provide important evidence for identifying spatially persistent water-quality concerns in coastal bays. However, seasonally normalized screening of high-Chl-a recurrence at the sampling-cell scale remains limited for subtropical multi-bay coastlines, where regional monsoon forcing, hydrodynamic retention, riverine inputs, aquaculture, and coastal development jointly shape phytoplankton variability. Based on Copernicus Marine ocean-colour records from 2003 to 2024, this study developed a reproducible ~4 km sampling-cell framework for seven coastal bays in Fujian, China. Monthly geometric-mean climatologies, phenological metrics, P90-based high-Chl-a exceedance frequencies, monitoring-priority classes, and exploratory machine-learning diagnostics were derived. Bay-scale phenology showed clear divergence: Sansha and Xinghua Bays exhibited winter or year-end Chl-a enhancement, Xiamen Bay peaked in summer, and Quanzhou Bay reached an early-autumn maximum. Four seasonal phenological regimes further revealed cell-scale heterogeneity, with C2 representing winter-enhanced, high-amplitude cycles and C3 identifying cells with the most frequent seasonally normalized high-Chl-a exceedances. High- and moderate-priority cells were concentrated mainly in Sansha and Xinghua Bays, whereas Dongshan and Quanzhou Bays showed only localized priority cells. Exploratory diagnostics indicated that distance to the bay mouth was the most important correlate of recurrent high-Chl-a susceptibility, suggesting the role of bay-scale exchange and retention gradients. This framework converts long-term ocean-colour archives into spatially explicit phenological and anomaly-screening evidence to support targeted coastal water-quality monitoring and ecosystem management.