Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method

Landslide displacement prediction is an essential component for developing landslide early warning systems. In the Three Gorges Reservoir area (TGRA), landslides experience step-like deformations (i.e., periods of stability interrupted by abrupt accelerations) generally from April to September due to the influence of precipitation and reservoir scheduled level variations. With respect to many traditional machine learning techniques, two issues exist relative to displacement prediction, namely the random fluctuation of prediction results and inaccurate prediction when step-like deformations take place. In this study, a novel and original prediction method was proposed by combining the wavelet transform (WT) and particle swarm optimization-kernel extreme learning machine (PSO-KELM) methods, and by considering the landslide causal factors. A typical landslide with a step-like behavior, the Baishuihe landslide in TGRA, was taken as a case study. The cumulated total displacement was decomposed into trend displacement, periodic displacement (controlled by internal geological conditions and external triggering factors respectively), and noise. The displacement items were predicted separately by multi-factor PSO-KELM considering various causal factors, and the total displacement was obtained by summing them up. An accurate prediction was achieved by the proposed method, including the step-like deformation period. The performance of the proposed method was compared with that of the multi-factor extreme learning machine (ELM), support vector regression (SVR), backward propagation neural network (BPNN), and single-factor PSO-KELM. Results show that the PSO-KELM outperforms the other models, and the prediction accuracy can be improved by considering causal factors.     

Improving basin scale shallow landslide modelling using reliable soil thickness maps

Soil thickness is a well-known factor controlling shallow landsliding. Notwithstanding, its spatial organisation over large areas is poorly understood, and in basin scale slope analyses it is often established using simple methods. In this paper, we apply five different soil thickness models in two test sites, and we use the obtained soil thickness maps to feed a slope stability model. Validation quantifies how errors in soil thickness influence the resulting factor of safety and points out which method grants the best results. In particular, in our cases, slope-derived soil thickness patterns produced the worst slope stability assessment, while the use of reliable soil thickness maps obtained by means of a more complex geomorphologically indexed model improved shallow landslides modelling.     

Soil erosion prediction at the basin scale using the revised universal soil loss equation (RUSLE) in a catchment of Sicily (southern Italy)

Soil erosion by water is a serious problem in southern Italy, particularly in Sicily which is one of the Italian administrative regions prone to desertification. Soil erosion not only affects soil quality, in terms of agricultural productivity, but also reduces the availability of water in reservoirs. This study was conducted in the Comunelli catchment in south-central Sicily, to predict potential annual soil loss using the revised universal soil loss equation (RUSLE) and to test the reliability of this methodology to predict reservoirs siltation. The RUSLE factors were calculated for the catchment using survey data and rain gauge measurement data. The R-factor was calculated from daily, monthly and annual precipitation data. The K-factor was calculated from soil samples collected in May and November 2004. The LS topographic factor was calculated from a 20 m digital elevation model. The C- and P-factors, in absence of detailed data, were set to 1. The results were compared with those obtained from another soil loss estimation method based on ¹³⁷Cs and with the soil loss estimated from the sediment volume stored in the Comunelli reservoir between 1968 and 2004.     

Increased aridity in the Mediterranean region under greenhouse gas forcing estimated from high resolution simulations with a regional climate model

We use three measures of aridity, the Köppen climate classification, the UNEP aridity index and the Budyko dryness index, to estimate the possible effects of late 21st century climate change on the Mediterranean region under increased greenhouse gas concentrations (A2 and B2 IPCC emission scenarios) as simulated with a high resolution (20 km grid interval) regional climate model (the ICTP RegCM). A basic validation of the reference simulation along with a brief discussion of the surface climate changes for the A2 and B2 scenarios is also provided. Analysis of the changes in all three aridity measures indicates that by the end of the 21st century the Mediterranean region might experience a substantial increase in the northward extension of dry and arid lands, particularly in the central and southern portions of the Iberian, Italian, Hellenic and Turkish peninsulas and in areas of southeastern Europe (e.g. Romania and Bulgaria), the Middle East, northern Africa and major Islands (Corsica, Sardinia and Sicily). Most Ice-Cap areas of the Alps are also projected to disappear. These effects are due to a large warming and pronounced decrease in precipitation, especially during the spring and summer seasons. In addition, fine scale topography and coastline features affect the aridity change signal. We identify the southern Mediterranean as a region particularly vulnerable to water stress and desertification processes under climate change conditions.     

Subsurface mass redistributions at Mount Etna (Italy) during the 1995–1996 explosive activity detected by microgravity studies

Gravity changes are presented from a series of field microgravity surveys conducted at Mt Etna between August 1994 and November 1996, a period including the 1995–1996 explosive summit activity. Data were collected along a microgravity network of 69 stations at a monthly to annual sampling rate, depending on each subarray of the network.
  Results show that seasonal changes in water level within the volcano may induce gravity changes of up to 20  μgal on Etna's southern slope, and indicate that significant magma movement occurred within and below Etna's edifice between 1994 and 1996. In particular, between September 1994 and October 1995, a mass increase of 2 × 10¹⁰  kg occurred 2000  m beneath the summit craters. Between October 1995 and July 1996 this mass was lost, while another 2 × 10¹⁰  kg was injected at about 1000  m  a.s.l. into the 1989 fracture system. From the gravity data alone, it is not possible to distinguish whether the first shallow intrusion (1994–1995) was then injected laterally into the 1989 fracture, or summit activity was fed by the first shallow intrusion, while new magma entered the 1989 fracture system.
  While magma was being redistributed within the volcanic edifice, measurements along an E–W-trending profile on the southern slope of the volcano detected some 1.5 × 10¹¹  kg of magma accumulating 2–3  km below sea level between October 1995 and November 1996.     

On the application of SAR interferometry to geomorphological studies: estimation of landform attributes and mass movements

This paper presents two examples of application of Synthetic Aperture Radar (SAR) interferometry (InSAR) to typical geomorphological problems. The principles of InSAR are introduced, taking care to clarify the limits and the potential of this technique for geomorphological studies. The application of InSAR to the quantification of landform attributes such as the slope and to the estimation of landform variations is investigated. Two case studies are presented. A first case study focuses on the problem of measuring landform attributes by interferometric SAR data. The interferometric result is compared with the corresponding one obtained by a Digital Elevation Model (DEM). In the second case study, the use of InSAR for the estimation of landform variations caused by a landslide is detailed.     

Resolution effects on regional climate model simulations of seasonal precipitation over Europe

We analyze a set of nine regional climate model simulations for the period 1961–2000 performed at 25 and 50 km horizontal grid spacing over a European domain in order to determine the effects of horizontal resolution on the simulation of precipitation. All of the models represent the seasonal mean spatial patterns and amount of precipitation fairly well. Most models exhibit a tendency to over-predict precipitation, resulting in a domain-average total bias for the ensemble mean of about 20% in winter (DJF) and less than 10% in summer (JJA) at both resolutions, although this bias could be artificially enhanced by the lack of a gauge correction in the observations. A majority of the models show increased precipitation at 25 km relative to 50 km over the oceans and inland seas in DJF, JJA, and ANN (annual average), although the response is strongest during JJA. The ratio of convective precipitation to total precipitation decreases over land for most models at 25 km. In addition, there is an increase in interannual variability in many of the models at 25 km grid spacing. Comparison with gridded observations indicates that a majority of models show improved skill in simulating both the spatial pattern and temporal evolution of precipitation at 25 km compared to 50 km during the summer months, but not in winter or on an annual mean basis. Model skill at higher resolution in simulating the spatial and temporal character of seasonal precipitation is found especially for Great Britain. This geographic dependence of the increased skill suggests that observed data of sufficient density are necessary to capture fine-scale climate signals. As climate models increase their horizontal resolution, it is thus a key priority to produce high quality fine scale observations for model evaluation.     

Future changes in Central Europe heat waves expected to mostly follow summer mean warming

Daily output from the PRUDENCE ensemble of regional climate simulations for the end of the twentieth and twenty-first centuries over Europe is used to show that the increasing intensity of the most damaging summer heat waves over Central Europe is mostly due to higher base summer temperatures. In this context, base temperature is defined as the mean of the seasonal cycle component for those calendar days when regional heat waves occur and is close, albeit not identical, to the mean temperature for July–August. Although 36–47% of future Central Europe July and August days at the end of the twenty-first century are projected to be extreme according to the present day climatology, specific changes in deseasonalized heat wave anomalies are projected to be relatively small. Instead, changes in summer base temperatures appear much larger, clearly identifiable and of the same order of magnitude as changes in the whole magnitude of heat waves. Our results bear important consequences for the predictability of central European heat wave intensity under global warming conditions.