In this scientific report, a new technique of artificial intelligence which is based on k-nearest neighbors (KNN) and particle swarm optimization (PSO), named as PSO-KNN, was developed and proposed for estimating blast-induced ground vibration (PPV). In the proposed PSO-KNN, the hyper-parameters of the KNN were searched and optimized by the PSO. Accordingly, three forms of kernel function of the KNN were used, Quartic (Q), Tri weight (T), and Cosine (C), which result in three models and abbreviated as PSO-KNN-Q, PSO-KNN-T, and PSO-KNN-C models. The valid of the proposed models was surveyed through comparing with those of benchmarks, random forest (RF), support vector regression (SVR), and an empirical technique. A total of 152 blasting events were recorded and analyzed for this aim. Herein, maximum explosive per blast delay (W) and the distance of PPV measurement (R), were used as the two input parameters for predicting PPV. RMSE, R², and MAE were utilized as performance indicators for evaluating the models’ accuracy. The outcomes instruct that the PSO algorithm significantly improved the efficiency of the PSO-KNN-Q, PSO-KNN-T, and PSO-KNN-C models. Compared to the three benchmarks models (i.e., RF, SVR, and empirical), the PSO-KNN-T model (RMSE = 0.797, R² = 0.977, and MAE = 0.385) performed better; therefore, it can be introduced as a powerful tool, which can be used in practical blasting for reducing unwanted elements induced by PPV in surface mines.

Interferometric synthetic aperture radar (InSAR), one of the most commonly used remote sensing methods for observing and monitoring land subsidence, has been applied in Hanoi, Vietnam in several studies with results showing deformation up to 2014. However, freely accessible Sentinel-1 InSAR data have not been investigated thoroughly to date. Here, we investigate the most recent land surface deformation in Hanoi for the period 2016 $-$2020 using Sentinel-1A SAR data. The analysis is conducted on 114 SAR scenes with both the Persistent Scatterer InSAR (PSInSAR) and Small BAseline Subset (SBAS) methods. The GPS-based deformation time series are used to verify InSAR results and borehole groundwater level measurements are employed to evaluate the relationship between groundwater depletion and surface subsidence. The results show that observed deformation from SBAS and PSInSAR is consistent in both spatial patterns and statistics, in which two high-rate subsiding bowls were detected in Dan Phuong/Hoai Duc and Ha Dong/Thanh Tri districts with the mean subsiding rates of ∼5 mm per year. GPS and InSAR deformation generally agree well except for the comparison at the JNAV station after 2017, which can be attributable to the local deformation detected by GPS and the average movement of a 100-m radius area captured by InSAR. An agreement in the drawdown trend between borehole groundwater and InSAR-derived deformation was found at four wells located within or in proximity to the two bowls. The declining rates of groundwater level at about 0.31 m per year were found at the two wells Q57a and Q58a located within the Dan Phuong/Hoai Duc bowl, corresponding to the surface subsidence rates found at 6–8 mm per year. The Q68a well was found to experience groundwater level declining at the highest rate of ∼0.9 m per year corresponding to the subsidence rate of ∼7 mm per year found by InSAR.

Flash floods induced by torrential rainfalls are considered one of the most dangerous natural hazards, due to their sudden occurrence and high magnitudes, which may cause huge damage to people and properties. This study proposed a novel modeling approach for spatial prediction of flash floods based on the tree intelligence-based CHAID (Chi-square Automatic Interaction Detector)random subspace, optimized by biogeography-based optimization (the CHAID-RS-BBO model), using remote sensing and geospatial data. In this proposed approach, a forest of tree intelligence was constructed through the random subspace ensemble, and, then, the swarm intelligence was employed to train and optimize the model. The Luc Yen district, located in the northwest mountainous area of Vietnam, was selected as a case study. For this circumstance, a flood inventory map with 1866 polygons for the district was prepared based on Sentinel-1 synthetic aperture radar (SAR) imagery and field surveys with handheld GPS. Then, a geospatial database with ten influencing variables (land use/land cover, soil type, lithology, river density, rainfall, topographic wetness index, elevation, slope, curvature, and aspect) was prepared. Using the inventory map and the ten explanatory variables, the CHAID-RS-BBO model was trained and verified. Various statistical metrics were used to assess the prediction capability of the proposed model. The results show that the proposed CHAID-RS-BBO model yielded the highest predictive performance, with an overall accuracy of 90% in predicting flash floods, and outperformed benchmarks (i.e., the CHAID, the J48-DT, the logistic regression, and the multilayer perception neural network (MLP-NN) models). We conclude that the proposed method can accurately estimate the spatial prediction of flash floods in tropical storm areas.

Dust is one of the components causing heavy environmental pollution in open-pit mines, especially PM₁₀. Some pathologies related to the lung, respiratory system, and occupational diseases have been identified due to the effects of PM₁₀ in open-pit mines. Therefore, the prediction and control of PM₁₀ concentration in the production process are necessary for environmental and health protection. In this study, PM₁₀ concentration from drilling operations in the Coc Sau open-pit coal mine (Vietnam) was investigated and considered through a database including 245 datasets collected. A novel hybrid artificial intelligence model was developed based on support vector regression (SVR) and a swarm optimization algorithm (i.e., particle swarm optimization (PSO)), namely PSO-SVR, for estimating PM₁₀ concentration from drilling operations at the mine. Polynomial (P), radial basis function (RBF), and linear (L) kernel functions were considered and applied to the development of the PSO-SVR models in the present study, abbreviated as PSO-SVR-P, PSO-SVR-RBF, and PSO-SVR-L. Also, three benchmark artificial intelligence techniques, such as k-nearest neighbors (KNN), random forest (RF), and classification and regression trees (CART), were applied and developed for estimating PM₁₀ concentration and then compared with the PSO-SVR models. Root-mean-squared error (RMSE) and determination coefficient (R²) were used as the statistical criteria for evaluating the performance of the developed models. The results exhibited that the PSO algorithm had an essential role in the optimization of the hyper-parameters of the SVR models. The PSO-SVR models (i.e., PSO-SVR-L, PSO-SVR-P, and PSO-SVR-RBF) had higher performance levels than the other models (i.e., RF, CART, and KNN) with an RMSE of 0.040, 0.042, and 0.043; and R² of 0.954, 0.948, and 0.946; for the PSO-SVR-L, PSO-SVR-P, and PSO-SVR-RBF models, respectively. Of these PSO-SVR models, the PSO-SVR-L model was the most dominant model with an RMSE of 0.040 and R² of 0.954. The remaining three benchmark models (i.e., RF, CART, and KNN) yielded a more unsatisfactory performance with an RMSE of 0.060, 0.052, and 0.067; and R² of 0.894, 0.924, and 0.867, for the RF, CART, and KNN models, respectively. Furthermore, the findings of this study demonstrated that the density of rock mass, moisture content, and the penetration rate of the drill were essential parameters on the PM₁₀ concentration caused by drilling operations in open-pit mines.