Flash floods are widely recognized as one of the most devastating natural hazards in the world, therefore prediction of flash flood-prone areas is crucial for public safety and emergency management. This research proposes a new methodology for spatial prediction of flash floods based on Sentinel-1 SAR imagery and a new hybrid machine learning technique. The SAR imagery is used to detect flash flood inundation areas, whereas the new machine learning technique, which is a hybrid of the firefly algorithm (FA), Levenberg–Marquardt (LM) backpropagation, and an artificial neural network (named as FA-LM-ANN), was used to construct the prediction model. The Bac Ha Bao Yen (BHBY) area in the northwestern region of Vietnam was used as a case study. Accordingly, a Geographical Information System (GIS) database was constructed using 12 input variables (elevation, slope, aspect, curvature, topographic wetness index, stream power index, toposhade, stream density, rainfall, normalized difference vegetation index, soil type, and lithology) and subsequently the output of flood inundation areas was mapped. Using the database and FA-LM-ANN, the flash flood model was trained and verified. The model performance was validated via various performance metrics including the classification accuracy rate, the area under the curve, precision, and recall. Then, the flash flood model that produced the highest performance was compared with benchmarks, indicating that the combination of FA and LM backpropagation is proven to be very effective and the proposed FA-LM-ANN is a new and useful tool for predicting flash flood susceptibility.

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.

The monitoring of highwall slopes at open-pit mines is an important task to ensure safe mining. For this reason, several techniques such as total station, radar, terrestrial Light Detection and Ranging (LIDAR) can be employed for surface measurement. The objective of this study is to investigate mesh algorithms, which can be used to interpolate 3D models of pit walls. Experiments were carried out at Coc Sau open-pit mine at Quang Ninh province of Vietnam, and at experimental mine of Akademia Górniczo-Hutnicza University of Science and Technology in Cracow, Poland. First, 3D point cloud data for the study area was acquired by using terrestrial LIDAR, then was used to generate mesh surfaces using three algorithms—Delaunay 2.5D XY Plane, Delaunay 2.5D Best Fitting Plane, and Mesh from Points. After that, the results were rectified and optimized. Subsequently, the optimized meshes were used for generation of non-uniform rational basis spline (NURBS) surfaces. Then, the NURBS surface accuracy was assessed. The results showed that the average distance between surface and point cloud was within range of 5.6–5.8 mm with deviation of 6.2–6.8 mm, depending on the used mesh. Additionally, the quality of surfaces depends on the quality of input data set and the algorithm used to generate mesh network, and the accuracy of computed NURBS surfaces fitting into pointset was 4–5 times lower than that of optimized mesh fitting. However, the accuracy of the final product allows determining displacements on the level of centimeters.

Khanh Hoa coal mine (Thai Nguyen province) is one of the largest coal mines in the north of Vietnam. For many years, this area suffered from underground fires at coal mine waste dumps, seriously affecting production activities and the environment. This paper presents the results of classification of underground fire areas at Khanh Hoa coal mine using Normalized Diference Coal Fire Index (NDCFI). 03 Landsat 8 OLI_TIRS images taken on December 2, 2013, December 10, 2016, and December 3, 2019 were used to calculate NDCFI index, and then classify the underground fire areas by thresholding method. In the study, the land surface temperature was also calculated from Landsat 8 thermal infrared bands data, and then compared with the results of underground coal fire classification at Khanh Hoa coal mine. The obtained results showed that the NDCFI index can be used effectively in detecting and monitoring underground fire areas at coal mines. The use of the NDCFI index also has many advantages due to its calculation simplicity and rapidness compared to other methods for classifying underground coal fire areas.