A Comparative Study of Least Square Support Vector Machines and Multiclass Alternating Decision Trees for Spatial Prediction of Rainfall-Induced Landslides in a Tropical Cyclones Area

The objective of this study is to explore and compare the least square support vector machine (LSSVM) and multiclass alternating decision tree (MADT) techniques for the spatial prediction of landslides. The Luc Yen district in Yen Bai province (Vietnam) has been selected as a case study. LSSVM and MADT are effective machine learning techniques of classification applied in other fields but not in the field of landslide hazard assessment. For this, Landslide inventory map was first constructed with 95 landslide locations identified from aerial photos and verified from field investigations. These landslide locations were then divided randomly into two parts for training (70 % locations) and validation (30 % locations) processes. Secondly, landslide affecting factors such as slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to faults, distance to rivers, and rainfall were selected and applied for landslide susceptibility assessment. Subsequently, the LSSVM and MADT models were built to assess the landslide susceptibility in the study area using training dataset. Finally, receiver operating characteristic curve and statistical index-based evaluations techniques were employed to validate the predictive capability of these models. As a result, both the LSSVM and MADT models have high performance for spatial prediction of landslides in the study area. Out of these, the MADT model (AUC = 0.853) outperforms the LSSVM model (AUC = 0.803). From the landslide study of Luc Yen district in Yen Bai province (Vietnam), it can be conclude that the LSSVM and MADT models can be applied in other areas of world also for and spatial prediction. Landslide susceptibility maps obtained from this study may be helpful in planning, decision making for natural hazard management of the areas susceptible to landslide hazards.     

Haeundae Beach in Korea: Seasonal-to-decadal wave statistics and impulsive beach responses to typhoons

Haeundae Beach represents Korean pocket beaches that are currently erosional and dominated by summertime typhoons. The decadal wave characteristics 9 km offshore of Haeundae Beach were analyzed using the WAM model that was validated through the 2007 wave observations. The wave statistics modelled for 1979–2007 indicates that the seasonal mean significant wave height (H _s ) is highest (0.6–0.7 m) in summer due to typhoons, in contrast to the lowest (around 0.5 m) autumn analog. The wave direction is also pronouncedly seasonal with the principal bearings of SSW and NE in the summer and winter seasons, respectively. The WAM results additionally show that the H _s has gradually increased over the region of Haeundae Beach since 1993. Beach profiling during June–November 2014 shows the opposite processes of the typhoon and fair-weather on beach sands. During a typhoon, foreshore sands were eroded and then accumulated as sand bars on the surf zone. In the subsequent fair-weather, the sand bars moved back to the beach resulting in the surf-zone erosion and foreshore accretion. A total of 5 cycles of these beach-wide sand movements yielded a net retreat (up to 20 m) of the shoreline associated with large foreshore erosion. However, the surf zone only slightly accumulated as a result of the sand cycles. This was attributed to the sand escape offshore from the westernmost tip of the beach. The present study may provide an important clue to understanding the erosional processes in Haeundae Beach.     

Assessment of the impacts of climate change and brackish irrigation water on rice productivity and evaluation of adaptation measures in Ca Mau province,Vietnam

This paper presents applications of the peaks-over-threshold methodology for both the univariate and the recently introduced bivariate case, combined with a novel bootstrap approach. We compare the proposed bootstrap methods to the more traditional profile likelihood. We have investigated 63 years of the European Climate Assessment daily precipitation data for five Hungarian grid points, first separately for the summer and winter months, then aiming at the detection of possible changes by investigating 20 years moving windows. We show that significant changes can be observed both in the univariate and the bivariate cases, the most recent period being the most dangerous in several cases, as some return values have increased substantially. We illustrate these effects by bivariate coverage regions.     

Equatorial electrojet as part of the global circuit: a case-study from the IEEY

Geomagnetic storm-time variations often occur coherently at high latitude and the day-side dip equator where they affect the normal eastward Sq field. This paper presents an analysis of ground magnetic field and ionospheric electrodynamic data related to the geomagnetic storm which occured on 27 May 1993 during the International Equatorial Electrojet Year (IEEY) experiment. This storm-signature analysis on the auroral, mid-latitude and equatorial ground field and ionospheric electrodynamic data leads to the identification of a sensitive response of the equatorial electrojet (EEJ) to large-scale auroral return current: this response consists in a change of the eastward electric field during the pre-sunrise hours (0400–0600 UT) coherently to the high-, mid-, and equatorial-latitude H decrease and the disappearance of the EEJ irregularities between the time-interval 0800–0950 UT. Subsequent to the change in hF during pre-sunrise hours, the observed foF2 increase revealed an enhancement of the equatorial ionization anomaly (EIA) caused by the high-latitude penetrating electric field. The strengthening of these irregularities attested by the Doppler frequency increase tracks the H component at the equator which undergoes a rapid increase around 0800 UT. The H variations observed at the equator are the sum of the following components: S_R, DP, DR, DCF and DT.     

Biomass estimation of Sonneratia caseolaris (l.) Engler at a coastal area of Hai Phong city (Vietnam) using ALOS-2 PALSAR imagery and GIS-based multi-layer perceptron neural networks

This study tested the use of machine learning techniques for the estimation of above-ground biomass (AGB) of Sonneratia caseolaris in a coastal area of Hai Phong city, Vietnam. We employed a GIS database and multi-layer perceptron neural networks (MLPNN) to build and verify an AGB model, drawing upon data from a survey of 1508 mangrove trees in 18 sampling plots and ALOS-2 PALSAR imagery. We assessed the model’s performance using root-mean-square error, mean absolute error, coefficient of determination (R²), and leave-one-out cross-validation. We also compared the model’s usability with four machine learning techniques: support vector regression, radial basis function neural networks, Gaussian process, and random forest. The MLPNN model performed well and outperformed the machine learning techniques. The MLPNN model-estimated AGB ranged between 2.78 and 298.95 Mg ha^?1 (average = 55.8 Mg ha^?1); below-ground biomass ranged between 4.06 and 436.47 Mg ha^?1 (average = 81.47 Mg ha^?1), and total carbon stock ranged between 3.22 and 345.65 Mg C ha^?1 (average = 64.52 Mg C ha^?1). We conclude that ALOS-2 PALSAR data can be accurately used with MLPNN models for estimating mangrove forest biomass in tropical areas.     

Comparison of marine insolation estimating methods in the adriatic sea

We compare insolation results calculated from two well-known empirical formulas (Seckel and Beaudry’s SB73 formula and the original Smithsonian (SMS) formula) and a radiative transfer model using input data predicted from meteorological weather-forecast models, and review the accuracy of each method. Comparison of annual mean daily irradiance values for clear-sky conditions between the two formulas shows that, relative to the SMS, the SB73 underestimates spring values by 9 W m^-2 in the northern Adriatic Sea, although overall there is a good agreement between the annual results calculated with the two formulas. We also elucidate the effect on SMS of changing the ‘Sun-Earth distance factor (f)’, a parameter which is commonly assumed to be constant in the oceanographic context. Results show that the mean daily solar radiation for clear-sky conditions in the northern Adriatic Sea can be reduced as much as 12 W m^-2 during summer due to a decrease in thef value. Lastly, surface irradiance values calculated from a simple radiative transfer model (GM02) for clear-sky conditions are compared to those from SB73 and SMS. Comparison within situ data in the northern Adriatic Sea shows that the GM02 estimate gives more realistic surface irradiance values than SMS, particularly during summer. Additionally, irradiance values calculated by GM02 using the buoy meteorological fields and ECMWF (The European Centre for Medium Range Weather Forecasts) meteorological data show the suitability of the ECMWF data usage. Through tests of GM02 sensitivity to key regional meteorological factors, we explore the main factors contributing significantly to a reduction in summertime solar irradiance in the Adriatic Sea.     

Robust path-following of underactuated ships: Theory and experiments on a model ship

A method is proposed to design a new global controller that forces an underactuated ship to follow a reference path under disturbances induced by wave, wind and ocean-current. The controller is designed such that the ship moves on the path with an adjustable forward speed and its total velocity is tangential to the path. The ship under consideration is not actuated in the sway axis, and the mass and damping matrices are not assumed to be diagonal. Nonlinear damping terms are also included to cover both low- and high-speed applications. The new result is facilitated by choosing an appropriate origin of the body-fixed frame, designing a suitable filter of sway velocity, several nonlinear coordinate changes, the backstepping technique, and utilizing the ship dynamic structure. Experimental results on a model ship illustrate the effectiveness of the proposed method.     

Ecological risk assessment of heavy metals sampled in sediments and water of the Houjing River,Taiwan

The Houjing River flows through Kaohsiung, the most industrialized city in southern Taiwan. In this study, heavy metal concentrations in water and sediments from samples along the river were investigated to illustrate metal contamination levels and call for the awareness of industrial pollution prevention. The heavy metal concentrations in the water samples were low and appear to pose little direct risk to aquatic life and irrigation, but heavy metal concentrations in the sediments are locally very high and present an environmental risk. Cadmium, Cu, and Zn were found in higher concentrations in the river sediments than those recommended in some sediment quality guidelines and findings of river sediments in similar studies worldwide. Hence, the ecological risk of heavy metal contamination in sediments was assessed using the pollution load index (PLI) and potential ecological risk index (RI). Three of the eleven sites sampled were found to have PLI values higher than 1 and 8 of them had ‘considerable’ to ‘very high’ RI values, suggesting a considerable ecological risk. These findings provide an insight into elemental metal contamination of the Houjing River and present a baseline data set, which will be critical for future development and environmental protection plans devised for the region.     

Susceptibility assessment of the precursor stage of a landslide threatening Haivan Railway Station,Vietnam

Haivan Station is an important station on the North-South railway line in central Vietnam. Field investigation has identified a precursor stage of a landslide that would threaten this railway. Therefore, a landslide susceptibility assessment for Haivan Station was urgently needed to protect passenger safety and the national railway. Conducted investigations included air-photo interpretation, drilling, ground water and inclinometer monitoring, laboratory testing, and landslide simulation. This research applied the undrained dynamic loading ring shear apparatus ICL-2 to drill-core samples from the precursor landslide. Samples for ring shear tests were taken from sandy soil layers found at depths of ~21, ~31, and ~50 m in the cores. Each of these was believed to be a possible sliding surface of a landslide, and all were tested to shear failure in the ICL-2 apparatus. The boundary between highly weathered granitic rock and weathered granitic rock was identified at about 50 m depth. The inclinometer monitoring detected slight movement at this depth. Therefore, the present day risk of a landslide forming at 50 m is higher than for one forming at either 21 or 31 m. The landslide dynamic parameters obtained from the ring shear test of the 50-m-deep sample were used in an integrated numerical simulation model LS-RAPID. The simulation result gave the critical pore-pressure ratio for landslide occurrence, and landslide’s likely maximum speed, total volume, and depth of landslide debris that could cover the railway. These estimates serve to raise awareness of the vulnerability of the Vietnam national railway sector to landslide impact.     

The October 13, 2020, deadly rapid landslide triggered by heavy rainfall in Phong Dien,Thua Thien Hue,Vietnam

Landslides - At about 12:00 a.m., on October 13, 2020, a rapid rotational landslide induced by rainfall swept over Ranger Station-7 in Phong Xuan commune, Phong Dien district, Thua Thien Hue...